diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index a278c0f..d57b0f6 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -14,9 +14,9 @@ jobs: working-directory: web steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v6 - - uses: actions/setup-node@v4 + - uses: actions/setup-node@v6 with: node-version: 20 cache: npm diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml index 5067888..b34f74c 100644 --- a/.github/workflows/test.yml +++ b/.github/workflows/test.yml @@ -55,7 +55,7 @@ jobs: - uses: actions/checkout@v6 - name: Set up Node.js - uses: actions/setup-node@v4 + uses: actions/setup-node@v6 with: node-version: "20" cache: "npm" diff --git a/agents/s03_todo_write.py b/agents/s03_todo_write.py index 1755415..fd41e10 100644 --- a/agents/s03_todo_write.py +++ b/agents/s03_todo_write.py @@ -163,11 +163,7 @@ TOOLS = [ def agent_loop(messages: list): rounds_since_todo = 0 while True: - # Nag reminder: if 3+ rounds without a todo update, inject reminder - if rounds_since_todo >= 3 and messages: - last = messages[-1] - if last["role"] == "user" and isinstance(last.get("content"), list): - last["content"].insert(0, {"type": "text", "text": "Update your todos."}) + # Nag reminder is injected below, alongside tool results response = client.messages.create( model=MODEL, system=SYSTEM, messages=messages, tools=TOOLS, max_tokens=8000, @@ -189,6 +185,8 @@ def agent_loop(messages: list): if block.name == "todo": used_todo = True rounds_since_todo = 0 if used_todo else rounds_since_todo + 1 + if rounds_since_todo >= 3: + results.insert(0, {"type": "text", "text": "Update your todos."}) messages.append({"role": "user", "content": results}) diff --git a/agents/s05_skill_loading.py b/agents/s05_skill_loading.py index cc8edd2..2a5ff73 100644 --- a/agents/s05_skill_loading.py +++ b/agents/s05_skill_loading.py @@ -7,19 +7,25 @@ Two-layer skill injection that avoids bloating the system prompt: Layer 1 (cheap): skill names in system prompt (~100 tokens/skill) Layer 2 (on demand): full skill body in tool_result + skills/ + pdf/ + SKILL.md <-- frontmatter (name, description) + body + code-review/ + SKILL.md + System prompt: +--------------------------------------+ | You are a coding agent. | | Skills available: | - | - git: Git workflow helpers | <-- Layer 1: metadata only - | - test: Testing best practices | + | - pdf: Process PDF files... | <-- Layer 1: metadata only + | - code-review: Review code... | +--------------------------------------+ - When model calls load_skill("git"): + When model calls load_skill("pdf"): +--------------------------------------+ | tool_result: | | | - | Full git workflow instructions... | <-- Layer 2: full body + | Full PDF processing instructions | <-- Layer 2: full body | Step 1: ... | | Step 2: ... | | | @@ -44,10 +50,10 @@ if os.getenv("ANTHROPIC_BASE_URL"): WORKDIR = Path.cwd() client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL")) MODEL = os.environ["MODEL_ID"] -SKILLS_DIR = WORKDIR / ".skills" +SKILLS_DIR = WORKDIR / "skills" -# -- SkillLoader: parse .skills/*.md files with YAML frontmatter -- +# -- SkillLoader: scan skills//SKILL.md with YAML frontmatter -- class SkillLoader: def __init__(self, skills_dir: Path): self.skills_dir = skills_dir @@ -57,10 +63,10 @@ class SkillLoader: def _load_all(self): if not self.skills_dir.exists(): return - for f in sorted(self.skills_dir.glob("*.md")): - name = f.stem + for f in sorted(self.skills_dir.rglob("SKILL.md")): text = f.read_text() meta, body = self._parse_frontmatter(text) + name = meta.get("name", f.parent.name) self.skills[name] = {"meta": meta, "body": body, "path": str(f)} def _parse_frontmatter(self, text: str) -> tuple: diff --git a/agents/s_full.py b/agents/s_full.py index 7a3f1fd..d4dcfd3 100644 --- a/agents/s_full.py +++ b/agents/s_full.py @@ -199,7 +199,7 @@ class SkillLoader: def __init__(self, skills_dir: Path): self.skills = {} if skills_dir.exists(): - for f in sorted(skills_dir.glob("*.md")): + for f in sorted(skills_dir.rglob("SKILL.md")): text = f.read_text() match = re.match(r"^---\n(.*?)\n---\n(.*)", text, re.DOTALL) meta, body = {}, text @@ -209,7 +209,8 @@ class SkillLoader: k, v = line.split(":", 1) meta[k.strip()] = v.strip() body = match.group(2).strip() - self.skills[f.stem] = {"meta": meta, "body": body} + name = meta.get("name", f.parent.name) + self.skills[name] = {"meta": meta, "body": body} def descriptions(self) -> str: if not self.skills: return "(no skills)" diff --git a/docs/en/s05-skill-loading.md b/docs/en/s05-skill-loading.md index 4107a25..311de72 100644 --- a/docs/en/s05-skill-loading.md +++ b/docs/en/s05-skill-loading.md @@ -33,24 +33,27 @@ Layer 1: skill *names* in system prompt (cheap). Layer 2: full *body* via tool_r ## How It Works -1. Skill files live in `.skills/` as Markdown with YAML frontmatter. +1. Each skill is a directory containing a `SKILL.md` with YAML frontmatter. ``` -.skills/ - git.md # ---\n description: Git workflow\n ---\n ... - test.md # ---\n description: Testing patterns\n ---\n ... +skills/ + pdf/ + SKILL.md # ---\n name: pdf\n description: Process PDF files\n ---\n ... + code-review/ + SKILL.md # ---\n name: code-review\n description: Review code\n ---\n ... ``` -2. SkillLoader parses frontmatter, separates metadata from body. +2. SkillLoader scans for `SKILL.md` files, uses the directory name as the skill identifier. ```python class SkillLoader: def __init__(self, skills_dir: Path): self.skills = {} - for f in sorted(skills_dir.glob("*.md")): + for f in sorted(skills_dir.rglob("SKILL.md")): text = f.read_text() meta, body = self._parse_frontmatter(text) - self.skills[f.stem] = {"meta": meta, "body": body} + name = meta.get("name", f.parent.name) + self.skills[name] = {"meta": meta, "body": body} def get_descriptions(self) -> str: lines = [] @@ -87,7 +90,7 @@ The model learns what skills exist (cheap) and loads them when relevant (expensi |----------------|------------------|----------------------------| | Tools | 5 (base + task) | 5 (base + load_skill) | | System prompt | Static string | + skill descriptions | -| Knowledge | None | .skills/*.md files | +| Knowledge | None | skills/\*/SKILL.md files | | Injection | None | Two-layer (system + result)| ## Try It diff --git a/docs/ja/s05-skill-loading.md b/docs/ja/s05-skill-loading.md index 8aa6319..5fb8140 100644 --- a/docs/ja/s05-skill-loading.md +++ b/docs/ja/s05-skill-loading.md @@ -33,24 +33,27 @@ When model calls load_skill("git"): ## 仕組み -1. スキルファイルは`.skills/`にYAMLフロントマター付きMarkdownとして配置される。 +1. 各スキルは `SKILL.md` ファイルを含むディレクトリとして配置される。 ``` -.skills/ - git.md # ---\n description: Git workflow\n ---\n ... - test.md # ---\n description: Testing patterns\n ---\n ... +skills/ + pdf/ + SKILL.md # ---\n name: pdf\n description: Process PDF files\n ---\n ... + code-review/ + SKILL.md # ---\n name: code-review\n description: Review code\n ---\n ... ``` -2. SkillLoaderがフロントマターを解析し、メタデータと本体を分離する。 +2. SkillLoaderが `SKILL.md` を再帰的に探索し、ディレクトリ名をスキル識別子として使用する。 ```python class SkillLoader: def __init__(self, skills_dir: Path): self.skills = {} - for f in sorted(skills_dir.glob("*.md")): + for f in sorted(skills_dir.rglob("SKILL.md")): text = f.read_text() meta, body = self._parse_frontmatter(text) - self.skills[f.stem] = {"meta": meta, "body": body} + name = meta.get("name", f.parent.name) + self.skills[name] = {"meta": meta, "body": body} def get_descriptions(self) -> str: lines = [] @@ -87,7 +90,7 @@ TOOL_HANDLERS = { |----------------|------------------|----------------------------| | Tools | 5 (base + task) | 5 (base + load_skill) | | System prompt | Static string | + skill descriptions | -| Knowledge | None | .skills/*.md files | +| Knowledge | None | skills/\*/SKILL.md files | | Injection | None | Two-layer (system + result)| ## 試してみる diff --git a/docs/zh/s05-skill-loading.md b/docs/zh/s05-skill-loading.md index 9ebc601..fc62d1b 100644 --- a/docs/zh/s05-skill-loading.md +++ b/docs/zh/s05-skill-loading.md @@ -33,24 +33,27 @@ When model calls load_skill("git"): ## 工作原理 -1. 技能文件以 Markdown 格式存放在 `.skills/`, 带 YAML frontmatter。 +1. 每个技能是一个目录, 包含 `SKILL.md` 文件和 YAML frontmatter。 ``` -.skills/ - git.md # ---\n description: Git workflow\n ---\n ... - test.md # ---\n description: Testing patterns\n ---\n ... +skills/ + pdf/ + SKILL.md # ---\n name: pdf\n description: Process PDF files\n ---\n ... + code-review/ + SKILL.md # ---\n name: code-review\n description: Review code\n ---\n ... ``` -2. SkillLoader 解析 frontmatter, 分离元数据和正文。 +2. SkillLoader 递归扫描 `SKILL.md` 文件, 用目录名作为技能标识。 ```python class SkillLoader: def __init__(self, skills_dir: Path): self.skills = {} - for f in sorted(skills_dir.glob("*.md")): + for f in sorted(skills_dir.rglob("SKILL.md")): text = f.read_text() meta, body = self._parse_frontmatter(text) - self.skills[f.stem] = {"meta": meta, "body": body} + name = meta.get("name", f.parent.name) + self.skills[name] = {"meta": meta, "body": body} def get_descriptions(self) -> str: lines = [] @@ -87,7 +90,7 @@ TOOL_HANDLERS = { |----------------|------------------|--------------------------------| | Tools | 5 (基础 + task) | 5 (基础 + load_skill) | | 系统提示 | 静态字符串 | + 技能描述列表 | -| 知识库 | 无 | .skills/*.md 文件 | +| 知识库 | 无 | skills/\*/SKILL.md 文件 | | 注入方式 | 无 | 两层 (系统提示 + result) | ## 试一试 diff --git a/web/src/data/generated/docs.json b/web/src/data/generated/docs.json index 876e8e9..12d520c 100644 --- a/web/src/data/generated/docs.json +++ b/web/src/data/generated/docs.json @@ -27,7 +27,7 @@ "version": "s05", "locale": "en", "title": "s05: Skills", - "content": "# s05: Skills\n\n`s01 > s02 > s03 > s04 > [ s05 ] s06 | s07 > s08 > s09 > s10 > s11 > s12`\n\n> *\"Load knowledge when you need it, not upfront\"* -- inject via tool_result, not the system prompt.\n\n## Problem\n\nYou want the agent to follow domain-specific workflows: git conventions, testing patterns, code review checklists. Putting everything in the system prompt wastes tokens on unused skills. 10 skills at 2000 tokens each = 20,000 tokens, most of which are irrelevant to any given task.\n\n## Solution\n\n```\nSystem prompt (Layer 1 -- always present):\n+--------------------------------------+\n| You are a coding agent. |\n| Skills available: |\n| - git: Git workflow helpers | ~100 tokens/skill\n| - test: Testing best practices |\n+--------------------------------------+\n\nWhen model calls load_skill(\"git\"):\n+--------------------------------------+\n| tool_result (Layer 2 -- on demand): |\n| |\n| Full git workflow instructions... | ~2000 tokens\n| Step 1: ... |\n| |\n+--------------------------------------+\n```\n\nLayer 1: skill *names* in system prompt (cheap). Layer 2: full *body* via tool_result (on demand).\n\n## How It Works\n\n1. Skill files live in `.skills/` as Markdown with YAML frontmatter.\n\n```\n.skills/\n git.md # ---\\n description: Git workflow\\n ---\\n ...\n test.md # ---\\n description: Testing patterns\\n ---\\n ...\n```\n\n2. SkillLoader parses frontmatter, separates metadata from body.\n\n```python\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills = {}\n for f in sorted(skills_dir.glob(\"*.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n self.skills[f.stem] = {\"meta\": meta, \"body\": body}\n\n def get_descriptions(self) -> str:\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"\")\n lines.append(f\" - {name}: {desc}\")\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'.\"\n return f\"\\n{skill['body']}\\n\"\n```\n\n3. Layer 1 goes into the system prompt. Layer 2 is just another tool handler.\n\n```python\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\nTOOL_HANDLERS = {\n # ...base tools...\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n```\n\nThe model learns what skills exist (cheap) and loads them when relevant (expensive).\n\n## What Changed From s04\n\n| Component | Before (s04) | After (s05) |\n|----------------|------------------|----------------------------|\n| Tools | 5 (base + task) | 5 (base + load_skill) |\n| System prompt | Static string | + skill descriptions |\n| Knowledge | None | .skills/*.md files |\n| Injection | None | Two-layer (system + result)|\n\n## Try It\n\n```sh\ncd learn-claude-code\npython agents/s05_skill_loading.py\n```\n\n1. `What skills are available?`\n2. `Load the agent-builder skill and follow its instructions`\n3. `I need to do a code review -- load the relevant skill first`\n4. `Build an MCP server using the mcp-builder skill`\n" + "content": "# s05: Skills\n\n`s01 > s02 > s03 > s04 > [ s05 ] s06 | s07 > s08 > s09 > s10 > s11 > s12`\n\n> *\"Load knowledge when you need it, not upfront\"* -- inject via tool_result, not the system prompt.\n\n## Problem\n\nYou want the agent to follow domain-specific workflows: git conventions, testing patterns, code review checklists. Putting everything in the system prompt wastes tokens on unused skills. 10 skills at 2000 tokens each = 20,000 tokens, most of which are irrelevant to any given task.\n\n## Solution\n\n```\nSystem prompt (Layer 1 -- always present):\n+--------------------------------------+\n| You are a coding agent. |\n| Skills available: |\n| - git: Git workflow helpers | ~100 tokens/skill\n| - test: Testing best practices |\n+--------------------------------------+\n\nWhen model calls load_skill(\"git\"):\n+--------------------------------------+\n| tool_result (Layer 2 -- on demand): |\n| |\n| Full git workflow instructions... | ~2000 tokens\n| Step 1: ... |\n| |\n+--------------------------------------+\n```\n\nLayer 1: skill *names* in system prompt (cheap). Layer 2: full *body* via tool_result (on demand).\n\n## How It Works\n\n1. Each skill is a directory containing a `SKILL.md` with YAML frontmatter.\n\n```\nskills/\n pdf/\n SKILL.md # ---\\n name: pdf\\n description: Process PDF files\\n ---\\n ...\n code-review/\n SKILL.md # ---\\n name: code-review\\n description: Review code\\n ---\\n ...\n```\n\n2. SkillLoader scans for `SKILL.md` files, uses the directory name as the skill identifier.\n\n```python\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills = {}\n for f in sorted(skills_dir.rglob(\"SKILL.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n name = meta.get(\"name\", f.parent.name)\n self.skills[name] = {\"meta\": meta, \"body\": body}\n\n def get_descriptions(self) -> str:\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"\")\n lines.append(f\" - {name}: {desc}\")\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'.\"\n return f\"\\n{skill['body']}\\n\"\n```\n\n3. Layer 1 goes into the system prompt. Layer 2 is just another tool handler.\n\n```python\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\nTOOL_HANDLERS = {\n # ...base tools...\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n```\n\nThe model learns what skills exist (cheap) and loads them when relevant (expensive).\n\n## What Changed From s04\n\n| Component | Before (s04) | After (s05) |\n|----------------|------------------|----------------------------|\n| Tools | 5 (base + task) | 5 (base + load_skill) |\n| System prompt | Static string | + skill descriptions |\n| Knowledge | None | skills/\\*/SKILL.md files |\n| Injection | None | Two-layer (system + result)|\n\n## Try It\n\n```sh\ncd learn-claude-code\npython agents/s05_skill_loading.py\n```\n\n1. `What skills are available?`\n2. `Load the agent-builder skill and follow its instructions`\n3. `I need to do a code review -- load the relevant skill first`\n4. `Build an MCP server using the mcp-builder skill`\n" }, { "version": "s06", @@ -99,7 +99,7 @@ "version": "s05", "locale": "zh", "title": "s05: Skills (技能加载)", - "content": "# s05: Skills (技能加载)\n\n`s01 > s02 > s03 > s04 > [ s05 ] s06 | s07 > s08 > s09 > s10 > s11 > s12`\n\n> *\"用到什么知识, 临时加载什么知识\"* -- 通过 tool_result 注入, 不塞 system prompt。\n\n## 问题\n\n你希望智能体遵循特定领域的工作流: git 约定、测试模式、代码审查清单。全塞进系统提示太浪费 -- 10 个技能, 每个 2000 token, 就是 20,000 token, 大部分跟当前任务毫无关系。\n\n## 解决方案\n\n```\nSystem prompt (Layer 1 -- always present):\n+--------------------------------------+\n| You are a coding agent. |\n| Skills available: |\n| - git: Git workflow helpers | ~100 tokens/skill\n| - test: Testing best practices |\n+--------------------------------------+\n\nWhen model calls load_skill(\"git\"):\n+--------------------------------------+\n| tool_result (Layer 2 -- on demand): |\n| |\n| Full git workflow instructions... | ~2000 tokens\n| Step 1: ... |\n| |\n+--------------------------------------+\n```\n\n第一层: 系统提示中放技能名称 (低成本)。第二层: tool_result 中按需放完整内容。\n\n## 工作原理\n\n1. 技能文件以 Markdown 格式存放在 `.skills/`, 带 YAML frontmatter。\n\n```\n.skills/\n git.md # ---\\n description: Git workflow\\n ---\\n ...\n test.md # ---\\n description: Testing patterns\\n ---\\n ...\n```\n\n2. SkillLoader 解析 frontmatter, 分离元数据和正文。\n\n```python\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills = {}\n for f in sorted(skills_dir.glob(\"*.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n self.skills[f.stem] = {\"meta\": meta, \"body\": body}\n\n def get_descriptions(self) -> str:\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"\")\n lines.append(f\" - {name}: {desc}\")\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'.\"\n return f\"\\n{skill['body']}\\n\"\n```\n\n3. 第一层写入系统提示。第二层不过是 dispatch map 中的又一个工具。\n\n```python\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\nTOOL_HANDLERS = {\n # ...base tools...\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n```\n\n模型知道有哪些技能 (便宜), 需要时再加载完整内容 (贵)。\n\n## 相对 s04 的变更\n\n| 组件 | 之前 (s04) | 之后 (s05) |\n|----------------|------------------|--------------------------------|\n| Tools | 5 (基础 + task) | 5 (基础 + load_skill) |\n| 系统提示 | 静态字符串 | + 技能描述列表 |\n| 知识库 | 无 | .skills/*.md 文件 |\n| 注入方式 | 无 | 两层 (系统提示 + result) |\n\n## 试一试\n\n```sh\ncd learn-claude-code\npython agents/s05_skill_loading.py\n```\n\n试试这些 prompt (英文 prompt 对 LLM 效果更好, 也可以用中文):\n\n1. `What skills are available?`\n2. `Load the agent-builder skill and follow its instructions`\n3. `I need to do a code review -- load the relevant skill first`\n4. `Build an MCP server using the mcp-builder skill`\n" + "content": "# s05: Skills (技能加载)\n\n`s01 > s02 > s03 > s04 > [ s05 ] s06 | s07 > s08 > s09 > s10 > s11 > s12`\n\n> *\"用到什么知识, 临时加载什么知识\"* -- 通过 tool_result 注入, 不塞 system prompt。\n\n## 问题\n\n你希望智能体遵循特定领域的工作流: git 约定、测试模式、代码审查清单。全塞进系统提示太浪费 -- 10 个技能, 每个 2000 token, 就是 20,000 token, 大部分跟当前任务毫无关系。\n\n## 解决方案\n\n```\nSystem prompt (Layer 1 -- always present):\n+--------------------------------------+\n| You are a coding agent. |\n| Skills available: |\n| - git: Git workflow helpers | ~100 tokens/skill\n| - test: Testing best practices |\n+--------------------------------------+\n\nWhen model calls load_skill(\"git\"):\n+--------------------------------------+\n| tool_result (Layer 2 -- on demand): |\n| |\n| Full git workflow instructions... | ~2000 tokens\n| Step 1: ... |\n| |\n+--------------------------------------+\n```\n\n第一层: 系统提示中放技能名称 (低成本)。第二层: tool_result 中按需放完整内容。\n\n## 工作原理\n\n1. 每个技能是一个目录, 包含 `SKILL.md` 文件和 YAML frontmatter。\n\n```\nskills/\n pdf/\n SKILL.md # ---\\n name: pdf\\n description: Process PDF files\\n ---\\n ...\n code-review/\n SKILL.md # ---\\n name: code-review\\n description: Review code\\n ---\\n ...\n```\n\n2. SkillLoader 递归扫描 `SKILL.md` 文件, 用目录名作为技能标识。\n\n```python\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills = {}\n for f in sorted(skills_dir.rglob(\"SKILL.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n name = meta.get(\"name\", f.parent.name)\n self.skills[name] = {\"meta\": meta, \"body\": body}\n\n def get_descriptions(self) -> str:\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"\")\n lines.append(f\" - {name}: {desc}\")\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'.\"\n return f\"\\n{skill['body']}\\n\"\n```\n\n3. 第一层写入系统提示。第二层不过是 dispatch map 中的又一个工具。\n\n```python\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\nTOOL_HANDLERS = {\n # ...base tools...\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n```\n\n模型知道有哪些技能 (便宜), 需要时再加载完整内容 (贵)。\n\n## 相对 s04 的变更\n\n| 组件 | 之前 (s04) | 之后 (s05) |\n|----------------|------------------|--------------------------------|\n| Tools | 5 (基础 + task) | 5 (基础 + load_skill) |\n| 系统提示 | 静态字符串 | + 技能描述列表 |\n| 知识库 | 无 | skills/\\*/SKILL.md 文件 |\n| 注入方式 | 无 | 两层 (系统提示 + result) |\n\n## 试一试\n\n```sh\ncd learn-claude-code\npython agents/s05_skill_loading.py\n```\n\n试试这些 prompt (英文 prompt 对 LLM 效果更好, 也可以用中文):\n\n1. `What skills are available?`\n2. `Load the agent-builder skill and follow its instructions`\n3. `I need to do a code review -- load the relevant skill first`\n4. `Build an MCP server using the mcp-builder skill`\n" }, { "version": "s06", @@ -171,7 +171,7 @@ "version": "s05", "locale": "ja", "title": "s05: Skills", - "content": "# s05: Skills\n\n`s01 > s02 > s03 > s04 > [ s05 ] s06 | s07 > s08 > s09 > s10 > s11 > s12`\n\n> *\"必要な知識を、必要な時に読み込む\"* -- system prompt ではなく tool_result で注入。\n\n## 問題\n\nエージェントにドメイン固有のワークフローを遵守させたい: gitの規約、テストパターン、コードレビューチェックリスト。すべてをシステムプロンプトに入れると、使われないスキルにトークンを浪費する。10スキル x 2000トークン = 20,000トークン、ほとんどが任意のタスクに無関係だ。\n\n## 解決策\n\n```\nSystem prompt (Layer 1 -- always present):\n+--------------------------------------+\n| You are a coding agent. |\n| Skills available: |\n| - git: Git workflow helpers | ~100 tokens/skill\n| - test: Testing best practices |\n+--------------------------------------+\n\nWhen model calls load_skill(\"git\"):\n+--------------------------------------+\n| tool_result (Layer 2 -- on demand): |\n| |\n| Full git workflow instructions... | ~2000 tokens\n| Step 1: ... |\n| |\n+--------------------------------------+\n```\n\n第1層: スキル*名*をシステムプロンプトに(低コスト)。第2層: スキル*本体*をtool_resultに(オンデマンド)。\n\n## 仕組み\n\n1. スキルファイルは`.skills/`にYAMLフロントマター付きMarkdownとして配置される。\n\n```\n.skills/\n git.md # ---\\n description: Git workflow\\n ---\\n ...\n test.md # ---\\n description: Testing patterns\\n ---\\n ...\n```\n\n2. SkillLoaderがフロントマターを解析し、メタデータと本体を分離する。\n\n```python\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills = {}\n for f in sorted(skills_dir.glob(\"*.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n self.skills[f.stem] = {\"meta\": meta, \"body\": body}\n\n def get_descriptions(self) -> str:\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"\")\n lines.append(f\" - {name}: {desc}\")\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'.\"\n return f\"\\n{skill['body']}\\n\"\n```\n\n3. 第1層はシステムプロンプトに配置。第2層は通常のツールハンドラ。\n\n```python\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\nTOOL_HANDLERS = {\n # ...base tools...\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n```\n\nモデルはどのスキルが存在するかを知り(低コスト)、関連する時にだけ読み込む(高コスト)。\n\n## s04からの変更点\n\n| Component | Before (s04) | After (s05) |\n|----------------|------------------|----------------------------|\n| Tools | 5 (base + task) | 5 (base + load_skill) |\n| System prompt | Static string | + skill descriptions |\n| Knowledge | None | .skills/*.md files |\n| Injection | None | Two-layer (system + result)|\n\n## 試してみる\n\n```sh\ncd learn-claude-code\npython agents/s05_skill_loading.py\n```\n\n1. `What skills are available?`\n2. `Load the agent-builder skill and follow its instructions`\n3. `I need to do a code review -- load the relevant skill first`\n4. `Build an MCP server using the mcp-builder skill`\n" + "content": "# s05: Skills\n\n`s01 > s02 > s03 > s04 > [ s05 ] s06 | s07 > s08 > s09 > s10 > s11 > s12`\n\n> *\"必要な知識を、必要な時に読み込む\"* -- system prompt ではなく tool_result で注入。\n\n## 問題\n\nエージェントにドメイン固有のワークフローを遵守させたい: gitの規約、テストパターン、コードレビューチェックリスト。すべてをシステムプロンプトに入れると、使われないスキルにトークンを浪費する。10スキル x 2000トークン = 20,000トークン、ほとんどが任意のタスクに無関係だ。\n\n## 解決策\n\n```\nSystem prompt (Layer 1 -- always present):\n+--------------------------------------+\n| You are a coding agent. |\n| Skills available: |\n| - git: Git workflow helpers | ~100 tokens/skill\n| - test: Testing best practices |\n+--------------------------------------+\n\nWhen model calls load_skill(\"git\"):\n+--------------------------------------+\n| tool_result (Layer 2 -- on demand): |\n| |\n| Full git workflow instructions... | ~2000 tokens\n| Step 1: ... |\n| |\n+--------------------------------------+\n```\n\n第1層: スキル*名*をシステムプロンプトに(低コスト)。第2層: スキル*本体*をtool_resultに(オンデマンド)。\n\n## 仕組み\n\n1. 各スキルは `SKILL.md` ファイルを含むディレクトリとして配置される。\n\n```\nskills/\n pdf/\n SKILL.md # ---\\n name: pdf\\n description: Process PDF files\\n ---\\n ...\n code-review/\n SKILL.md # ---\\n name: code-review\\n description: Review code\\n ---\\n ...\n```\n\n2. SkillLoaderが `SKILL.md` を再帰的に探索し、ディレクトリ名をスキル識別子として使用する。\n\n```python\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills = {}\n for f in sorted(skills_dir.rglob(\"SKILL.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n name = meta.get(\"name\", f.parent.name)\n self.skills[name] = {\"meta\": meta, \"body\": body}\n\n def get_descriptions(self) -> str:\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"\")\n lines.append(f\" - {name}: {desc}\")\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'.\"\n return f\"\\n{skill['body']}\\n\"\n```\n\n3. 第1層はシステムプロンプトに配置。第2層は通常のツールハンドラ。\n\n```python\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\nTOOL_HANDLERS = {\n # ...base tools...\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n```\n\nモデルはどのスキルが存在するかを知り(低コスト)、関連する時にだけ読み込む(高コスト)。\n\n## s04からの変更点\n\n| Component | Before (s04) | After (s05) |\n|----------------|------------------|----------------------------|\n| Tools | 5 (base + task) | 5 (base + load_skill) |\n| System prompt | Static string | + skill descriptions |\n| Knowledge | None | skills/\\*/SKILL.md files |\n| Injection | None | Two-layer (system + result)|\n\n## 試してみる\n\n```sh\ncd learn-claude-code\npython agents/s05_skill_loading.py\n```\n\n1. `What skills are available?`\n2. `Load the agent-builder skill and follow its instructions`\n3. `I need to do a code review -- load the relevant skill first`\n4. `Build an MCP server using the mcp-builder skill`\n" }, { "version": "s06", diff --git a/web/src/data/generated/versions.json b/web/src/data/generated/versions.json index 3655df0..40b6afe 100644 --- a/web/src/data/generated/versions.json +++ b/web/src/data/generated/versions.json @@ -90,7 +90,7 @@ "filename": "s03_todo_write.py", "title": "TodoWrite", "subtitle": "Plan Before You Act", - "loc": 173, + "loc": 171, "tools": [ "bash", "read_file", @@ -143,7 +143,7 @@ } ], "layer": "planning", - "source": "#!/usr/bin/env python3\n\"\"\"\ns03_todo_write.py - TodoWrite\n\nThe model tracks its own progress via a TodoManager. A nag reminder\nforces it to keep updating when it forgets.\n\n +----------+ +-------+ +---------+\n | User | ---> | LLM | ---> | Tools |\n | prompt | | | | + todo |\n +----------+ +---+---+ +----+----+\n ^ |\n | tool_result |\n +---------------+\n |\n +-----------+-----------+\n | TodoManager state |\n | [ ] task A |\n | [>] task B <- doing |\n | [x] task C |\n +-----------------------+\n |\n if rounds_since_todo >= 3:\n inject \n\nKey insight: \"The agent can track its own progress -- and I can see it.\"\n\"\"\"\n\nimport os\nimport subprocess\nfrom pathlib import Path\n\nfrom anthropic import Anthropic\nfrom dotenv import load_dotenv\n\nload_dotenv(override=True)\n\nif os.getenv(\"ANTHROPIC_BASE_URL\"):\n os.environ.pop(\"ANTHROPIC_AUTH_TOKEN\", None)\n\nWORKDIR = Path.cwd()\nclient = Anthropic(base_url=os.getenv(\"ANTHROPIC_BASE_URL\"))\nMODEL = os.environ[\"MODEL_ID\"]\n\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nUse the todo tool to plan multi-step tasks. Mark in_progress before starting, completed when done.\nPrefer tools over prose.\"\"\"\n\n\n# -- TodoManager: structured state the LLM writes to --\nclass TodoManager:\n def __init__(self):\n self.items = []\n\n def update(self, items: list) -> str:\n if len(items) > 20:\n raise ValueError(\"Max 20 todos allowed\")\n validated = []\n in_progress_count = 0\n for i, item in enumerate(items):\n text = str(item.get(\"text\", \"\")).strip()\n status = str(item.get(\"status\", \"pending\")).lower()\n item_id = str(item.get(\"id\", str(i + 1)))\n if not text:\n raise ValueError(f\"Item {item_id}: text required\")\n if status not in (\"pending\", \"in_progress\", \"completed\"):\n raise ValueError(f\"Item {item_id}: invalid status '{status}'\")\n if status == \"in_progress\":\n in_progress_count += 1\n validated.append({\"id\": item_id, \"text\": text, \"status\": status})\n if in_progress_count > 1:\n raise ValueError(\"Only one task can be in_progress at a time\")\n self.items = validated\n return self.render()\n\n def render(self) -> str:\n if not self.items:\n return \"No todos.\"\n lines = []\n for item in self.items:\n marker = {\"pending\": \"[ ]\", \"in_progress\": \"[>]\", \"completed\": \"[x]\"}[item[\"status\"]]\n lines.append(f\"{marker} #{item['id']}: {item['text']}\")\n done = sum(1 for t in self.items if t[\"status\"] == \"completed\")\n lines.append(f\"\\n({done}/{len(self.items)} completed)\")\n return \"\\n\".join(lines)\n\n\nTODO = TodoManager()\n\n\n# -- Tool implementations --\ndef safe_path(p: str) -> Path:\n path = (WORKDIR / p).resolve()\n if not path.is_relative_to(WORKDIR):\n raise ValueError(f\"Path escapes workspace: {p}\")\n return path\n\ndef run_bash(command: str) -> str:\n dangerous = [\"rm -rf /\", \"sudo\", \"shutdown\", \"reboot\", \"> /dev/\"]\n if any(d in command for d in dangerous):\n return \"Error: Dangerous command blocked\"\n try:\n r = subprocess.run(command, shell=True, cwd=WORKDIR,\n capture_output=True, text=True, timeout=120)\n out = (r.stdout + r.stderr).strip()\n return out[:50000] if out else \"(no output)\"\n except subprocess.TimeoutExpired:\n return \"Error: Timeout (120s)\"\n\ndef run_read(path: str, limit: int = None) -> str:\n try:\n lines = safe_path(path).read_text().splitlines()\n if limit and limit < len(lines):\n lines = lines[:limit] + [f\"... ({len(lines) - limit} more)\"]\n return \"\\n\".join(lines)[:50000]\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_write(path: str, content: str) -> str:\n try:\n fp = safe_path(path)\n fp.parent.mkdir(parents=True, exist_ok=True)\n fp.write_text(content)\n return f\"Wrote {len(content)} bytes\"\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_edit(path: str, old_text: str, new_text: str) -> str:\n try:\n fp = safe_path(path)\n content = fp.read_text()\n if old_text not in content:\n return f\"Error: Text not found in {path}\"\n fp.write_text(content.replace(old_text, new_text, 1))\n return f\"Edited {path}\"\n except Exception as e:\n return f\"Error: {e}\"\n\n\nTOOL_HANDLERS = {\n \"bash\": lambda **kw: run_bash(kw[\"command\"]),\n \"read_file\": lambda **kw: run_read(kw[\"path\"], kw.get(\"limit\")),\n \"write_file\": lambda **kw: run_write(kw[\"path\"], kw[\"content\"]),\n \"edit_file\": lambda **kw: run_edit(kw[\"path\"], kw[\"old_text\"], kw[\"new_text\"]),\n \"todo\": lambda **kw: TODO.update(kw[\"items\"]),\n}\n\nTOOLS = [\n {\"name\": \"bash\", \"description\": \"Run a shell command.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"command\": {\"type\": \"string\"}}, \"required\": [\"command\"]}},\n {\"name\": \"read_file\", \"description\": \"Read file contents.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"limit\": {\"type\": \"integer\"}}, \"required\": [\"path\"]}},\n {\"name\": \"write_file\", \"description\": \"Write content to file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"content\": {\"type\": \"string\"}}, \"required\": [\"path\", \"content\"]}},\n {\"name\": \"edit_file\", \"description\": \"Replace exact text in file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"old_text\": {\"type\": \"string\"}, \"new_text\": {\"type\": \"string\"}}, \"required\": [\"path\", \"old_text\", \"new_text\"]}},\n {\"name\": \"todo\", \"description\": \"Update task list. Track progress on multi-step tasks.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"items\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"id\": {\"type\": \"string\"}, \"text\": {\"type\": \"string\"}, \"status\": {\"type\": \"string\", \"enum\": [\"pending\", \"in_progress\", \"completed\"]}}, \"required\": [\"id\", \"text\", \"status\"]}}}, \"required\": [\"items\"]}},\n]\n\n\n# -- Agent loop with nag reminder injection --\ndef agent_loop(messages: list):\n rounds_since_todo = 0\n while True:\n # Nag reminder: if 3+ rounds without a todo update, inject reminder\n if rounds_since_todo >= 3 and messages:\n last = messages[-1]\n if last[\"role\"] == \"user\" and isinstance(last.get(\"content\"), list):\n last[\"content\"].insert(0, {\"type\": \"text\", \"text\": \"Update your todos.\"})\n response = client.messages.create(\n model=MODEL, system=SYSTEM, messages=messages,\n tools=TOOLS, max_tokens=8000,\n )\n messages.append({\"role\": \"assistant\", \"content\": response.content})\n if response.stop_reason != \"tool_use\":\n return\n results = []\n used_todo = False\n for block in response.content:\n if block.type == \"tool_use\":\n handler = TOOL_HANDLERS.get(block.name)\n try:\n output = handler(**block.input) if handler else f\"Unknown tool: {block.name}\"\n except Exception as e:\n output = f\"Error: {e}\"\n print(f\"> {block.name}: {str(output)[:200]}\")\n results.append({\"type\": \"tool_result\", \"tool_use_id\": block.id, \"content\": str(output)})\n if block.name == \"todo\":\n used_todo = True\n rounds_since_todo = 0 if used_todo else rounds_since_todo + 1\n messages.append({\"role\": \"user\", \"content\": results})\n\n\nif __name__ == \"__main__\":\n history = []\n while True:\n try:\n query = input(\"\\033[36ms03 >> \\033[0m\")\n except (EOFError, KeyboardInterrupt):\n break\n if query.strip().lower() in (\"q\", \"exit\", \"\"):\n break\n history.append({\"role\": \"user\", \"content\": query})\n agent_loop(history)\n print()\n" + "source": "#!/usr/bin/env python3\n\"\"\"\ns03_todo_write.py - TodoWrite\n\nThe model tracks its own progress via a TodoManager. A nag reminder\nforces it to keep updating when it forgets.\n\n +----------+ +-------+ +---------+\n | User | ---> | LLM | ---> | Tools |\n | prompt | | | | + todo |\n +----------+ +---+---+ +----+----+\n ^ |\n | tool_result |\n +---------------+\n |\n +-----------+-----------+\n | TodoManager state |\n | [ ] task A |\n | [>] task B <- doing |\n | [x] task C |\n +-----------------------+\n |\n if rounds_since_todo >= 3:\n inject \n\nKey insight: \"The agent can track its own progress -- and I can see it.\"\n\"\"\"\n\nimport os\nimport subprocess\nfrom pathlib import Path\n\nfrom anthropic import Anthropic\nfrom dotenv import load_dotenv\n\nload_dotenv(override=True)\n\nif os.getenv(\"ANTHROPIC_BASE_URL\"):\n os.environ.pop(\"ANTHROPIC_AUTH_TOKEN\", None)\n\nWORKDIR = Path.cwd()\nclient = Anthropic(base_url=os.getenv(\"ANTHROPIC_BASE_URL\"))\nMODEL = os.environ[\"MODEL_ID\"]\n\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nUse the todo tool to plan multi-step tasks. Mark in_progress before starting, completed when done.\nPrefer tools over prose.\"\"\"\n\n\n# -- TodoManager: structured state the LLM writes to --\nclass TodoManager:\n def __init__(self):\n self.items = []\n\n def update(self, items: list) -> str:\n if len(items) > 20:\n raise ValueError(\"Max 20 todos allowed\")\n validated = []\n in_progress_count = 0\n for i, item in enumerate(items):\n text = str(item.get(\"text\", \"\")).strip()\n status = str(item.get(\"status\", \"pending\")).lower()\n item_id = str(item.get(\"id\", str(i + 1)))\n if not text:\n raise ValueError(f\"Item {item_id}: text required\")\n if status not in (\"pending\", \"in_progress\", \"completed\"):\n raise ValueError(f\"Item {item_id}: invalid status '{status}'\")\n if status == \"in_progress\":\n in_progress_count += 1\n validated.append({\"id\": item_id, \"text\": text, \"status\": status})\n if in_progress_count > 1:\n raise ValueError(\"Only one task can be in_progress at a time\")\n self.items = validated\n return self.render()\n\n def render(self) -> str:\n if not self.items:\n return \"No todos.\"\n lines = []\n for item in self.items:\n marker = {\"pending\": \"[ ]\", \"in_progress\": \"[>]\", \"completed\": \"[x]\"}[item[\"status\"]]\n lines.append(f\"{marker} #{item['id']}: {item['text']}\")\n done = sum(1 for t in self.items if t[\"status\"] == \"completed\")\n lines.append(f\"\\n({done}/{len(self.items)} completed)\")\n return \"\\n\".join(lines)\n\n\nTODO = TodoManager()\n\n\n# -- Tool implementations --\ndef safe_path(p: str) -> Path:\n path = (WORKDIR / p).resolve()\n if not path.is_relative_to(WORKDIR):\n raise ValueError(f\"Path escapes workspace: {p}\")\n return path\n\ndef run_bash(command: str) -> str:\n dangerous = [\"rm -rf /\", \"sudo\", \"shutdown\", \"reboot\", \"> /dev/\"]\n if any(d in command for d in dangerous):\n return \"Error: Dangerous command blocked\"\n try:\n r = subprocess.run(command, shell=True, cwd=WORKDIR,\n capture_output=True, text=True, timeout=120)\n out = (r.stdout + r.stderr).strip()\n return out[:50000] if out else \"(no output)\"\n except subprocess.TimeoutExpired:\n return \"Error: Timeout (120s)\"\n\ndef run_read(path: str, limit: int = None) -> str:\n try:\n lines = safe_path(path).read_text().splitlines()\n if limit and limit < len(lines):\n lines = lines[:limit] + [f\"... ({len(lines) - limit} more)\"]\n return \"\\n\".join(lines)[:50000]\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_write(path: str, content: str) -> str:\n try:\n fp = safe_path(path)\n fp.parent.mkdir(parents=True, exist_ok=True)\n fp.write_text(content)\n return f\"Wrote {len(content)} bytes\"\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_edit(path: str, old_text: str, new_text: str) -> str:\n try:\n fp = safe_path(path)\n content = fp.read_text()\n if old_text not in content:\n return f\"Error: Text not found in {path}\"\n fp.write_text(content.replace(old_text, new_text, 1))\n return f\"Edited {path}\"\n except Exception as e:\n return f\"Error: {e}\"\n\n\nTOOL_HANDLERS = {\n \"bash\": lambda **kw: run_bash(kw[\"command\"]),\n \"read_file\": lambda **kw: run_read(kw[\"path\"], kw.get(\"limit\")),\n \"write_file\": lambda **kw: run_write(kw[\"path\"], kw[\"content\"]),\n \"edit_file\": lambda **kw: run_edit(kw[\"path\"], kw[\"old_text\"], kw[\"new_text\"]),\n \"todo\": lambda **kw: TODO.update(kw[\"items\"]),\n}\n\nTOOLS = [\n {\"name\": \"bash\", \"description\": \"Run a shell command.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"command\": {\"type\": \"string\"}}, \"required\": [\"command\"]}},\n {\"name\": \"read_file\", \"description\": \"Read file contents.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"limit\": {\"type\": \"integer\"}}, \"required\": [\"path\"]}},\n {\"name\": \"write_file\", \"description\": \"Write content to file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"content\": {\"type\": \"string\"}}, \"required\": [\"path\", \"content\"]}},\n {\"name\": \"edit_file\", \"description\": \"Replace exact text in file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"old_text\": {\"type\": \"string\"}, \"new_text\": {\"type\": \"string\"}}, \"required\": [\"path\", \"old_text\", \"new_text\"]}},\n {\"name\": \"todo\", \"description\": \"Update task list. Track progress on multi-step tasks.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"items\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"id\": {\"type\": \"string\"}, \"text\": {\"type\": \"string\"}, \"status\": {\"type\": \"string\", \"enum\": [\"pending\", \"in_progress\", \"completed\"]}}, \"required\": [\"id\", \"text\", \"status\"]}}}, \"required\": [\"items\"]}},\n]\n\n\n# -- Agent loop with nag reminder injection --\ndef agent_loop(messages: list):\n rounds_since_todo = 0\n while True:\n # Nag reminder is injected below, alongside tool results\n response = client.messages.create(\n model=MODEL, system=SYSTEM, messages=messages,\n tools=TOOLS, max_tokens=8000,\n )\n messages.append({\"role\": \"assistant\", \"content\": response.content})\n if response.stop_reason != \"tool_use\":\n return\n results = []\n used_todo = False\n for block in response.content:\n if block.type == \"tool_use\":\n handler = TOOL_HANDLERS.get(block.name)\n try:\n output = handler(**block.input) if handler else f\"Unknown tool: {block.name}\"\n except Exception as e:\n output = f\"Error: {e}\"\n print(f\"> {block.name}: {str(output)[:200]}\")\n results.append({\"type\": \"tool_result\", \"tool_use_id\": block.id, \"content\": str(output)})\n if block.name == \"todo\":\n used_todo = True\n rounds_since_todo = 0 if used_todo else rounds_since_todo + 1\n if rounds_since_todo >= 3:\n results.insert(0, {\"type\": \"text\", \"text\": \"Update your todos.\"})\n messages.append({\"role\": \"user\", \"content\": results})\n\n\nif __name__ == \"__main__\":\n history = []\n while True:\n try:\n query = input(\"\\033[36ms03 >> \\033[0m\")\n except (EOFError, KeyboardInterrupt):\n break\n if query.strip().lower() in (\"q\", \"exit\", \"\"):\n break\n history.append({\"role\": \"user\", \"content\": query})\n agent_loop(history)\n print()\n" }, { "id": "s04", @@ -209,7 +209,7 @@ "filename": "s05_skill_loading.py", "title": "Skills", "subtitle": "Load on Demand", - "loc": 177, + "loc": 182, "tools": [ "bash", "read_file", @@ -225,44 +225,44 @@ "classes": [ { "name": "SkillLoader", - "startLine": 51, - "endLine": 99 + "startLine": 57, + "endLine": 105 } ], "functions": [ { "name": "safe_path", "signature": "def safe_path(p: str)", - "startLine": 111 + "startLine": 117 }, { "name": "run_bash", "signature": "def run_bash(command: str)", - "startLine": 117 + "startLine": 123 }, { "name": "run_read", "signature": "def run_read(path: str, limit: int = None)", - "startLine": 129 + "startLine": 135 }, { "name": "run_write", "signature": "def run_write(path: str, content: str)", - "startLine": 138 + "startLine": 144 }, { "name": "run_edit", "signature": "def run_edit(path: str, old_text: str, new_text: str)", - "startLine": 147 + "startLine": 153 }, { "name": "agent_loop", "signature": "def agent_loop(messages: list)", - "startLine": 181 + "startLine": 187 } ], "layer": "planning", - "source": "#!/usr/bin/env python3\n\"\"\"\ns05_skill_loading.py - Skills\n\nTwo-layer skill injection that avoids bloating the system prompt:\n\n Layer 1 (cheap): skill names in system prompt (~100 tokens/skill)\n Layer 2 (on demand): full skill body in tool_result\n\n System prompt:\n +--------------------------------------+\n | You are a coding agent. |\n | Skills available: |\n | - git: Git workflow helpers | <-- Layer 1: metadata only\n | - test: Testing best practices |\n +--------------------------------------+\n\n When model calls load_skill(\"git\"):\n +--------------------------------------+\n | tool_result: |\n | |\n | Full git workflow instructions... | <-- Layer 2: full body\n | Step 1: ... |\n | Step 2: ... |\n | |\n +--------------------------------------+\n\nKey insight: \"Don't put everything in the system prompt. Load on demand.\"\n\"\"\"\n\nimport os\nimport re\nimport subprocess\nfrom pathlib import Path\n\nfrom anthropic import Anthropic\nfrom dotenv import load_dotenv\n\nload_dotenv(override=True)\n\nif os.getenv(\"ANTHROPIC_BASE_URL\"):\n os.environ.pop(\"ANTHROPIC_AUTH_TOKEN\", None)\n\nWORKDIR = Path.cwd()\nclient = Anthropic(base_url=os.getenv(\"ANTHROPIC_BASE_URL\"))\nMODEL = os.environ[\"MODEL_ID\"]\nSKILLS_DIR = WORKDIR / \".skills\"\n\n\n# -- SkillLoader: parse .skills/*.md files with YAML frontmatter --\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills_dir = skills_dir\n self.skills = {}\n self._load_all()\n\n def _load_all(self):\n if not self.skills_dir.exists():\n return\n for f in sorted(self.skills_dir.glob(\"*.md\")):\n name = f.stem\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n self.skills[name] = {\"meta\": meta, \"body\": body, \"path\": str(f)}\n\n def _parse_frontmatter(self, text: str) -> tuple:\n \"\"\"Parse YAML frontmatter between --- delimiters.\"\"\"\n match = re.match(r\"^---\\n(.*?)\\n---\\n(.*)\", text, re.DOTALL)\n if not match:\n return {}, text\n meta = {}\n for line in match.group(1).strip().splitlines():\n if \":\" in line:\n key, val = line.split(\":\", 1)\n meta[key.strip()] = val.strip()\n return meta, match.group(2).strip()\n\n def get_descriptions(self) -> str:\n \"\"\"Layer 1: short descriptions for the system prompt.\"\"\"\n if not self.skills:\n return \"(no skills available)\"\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"No description\")\n tags = skill[\"meta\"].get(\"tags\", \"\")\n line = f\" - {name}: {desc}\"\n if tags:\n line += f\" [{tags}]\"\n lines.append(line)\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n \"\"\"Layer 2: full skill body returned in tool_result.\"\"\"\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'. Available: {', '.join(self.skills.keys())}\"\n return f\"\\n{skill['body']}\\n\"\n\n\nSKILL_LOADER = SkillLoader(SKILLS_DIR)\n\n# Layer 1: skill metadata injected into system prompt\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nUse load_skill to access specialized knowledge before tackling unfamiliar topics.\n\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\n\n# -- Tool implementations --\ndef safe_path(p: str) -> Path:\n path = (WORKDIR / p).resolve()\n if not path.is_relative_to(WORKDIR):\n raise ValueError(f\"Path escapes workspace: {p}\")\n return path\n\ndef run_bash(command: str) -> str:\n dangerous = [\"rm -rf /\", \"sudo\", \"shutdown\", \"reboot\", \"> /dev/\"]\n if any(d in command for d in dangerous):\n return \"Error: Dangerous command blocked\"\n try:\n r = subprocess.run(command, shell=True, cwd=WORKDIR,\n capture_output=True, text=True, timeout=120)\n out = (r.stdout + r.stderr).strip()\n return out[:50000] if out else \"(no output)\"\n except subprocess.TimeoutExpired:\n return \"Error: Timeout (120s)\"\n\ndef run_read(path: str, limit: int = None) -> str:\n try:\n lines = safe_path(path).read_text().splitlines()\n if limit and limit < len(lines):\n lines = lines[:limit] + [f\"... ({len(lines) - limit} more)\"]\n return \"\\n\".join(lines)[:50000]\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_write(path: str, content: str) -> str:\n try:\n fp = safe_path(path)\n fp.parent.mkdir(parents=True, exist_ok=True)\n fp.write_text(content)\n return f\"Wrote {len(content)} bytes\"\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_edit(path: str, old_text: str, new_text: str) -> str:\n try:\n fp = safe_path(path)\n content = fp.read_text()\n if old_text not in content:\n return f\"Error: Text not found in {path}\"\n fp.write_text(content.replace(old_text, new_text, 1))\n return f\"Edited {path}\"\n except Exception as e:\n return f\"Error: {e}\"\n\n\nTOOL_HANDLERS = {\n \"bash\": lambda **kw: run_bash(kw[\"command\"]),\n \"read_file\": lambda **kw: run_read(kw[\"path\"], kw.get(\"limit\")),\n \"write_file\": lambda **kw: run_write(kw[\"path\"], kw[\"content\"]),\n \"edit_file\": lambda **kw: run_edit(kw[\"path\"], kw[\"old_text\"], kw[\"new_text\"]),\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n\nTOOLS = [\n {\"name\": \"bash\", \"description\": \"Run a shell command.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"command\": {\"type\": \"string\"}}, \"required\": [\"command\"]}},\n {\"name\": \"read_file\", \"description\": \"Read file contents.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"limit\": {\"type\": \"integer\"}}, \"required\": [\"path\"]}},\n {\"name\": \"write_file\", \"description\": \"Write content to file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"content\": {\"type\": \"string\"}}, \"required\": [\"path\", \"content\"]}},\n {\"name\": \"edit_file\", \"description\": \"Replace exact text in file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"old_text\": {\"type\": \"string\"}, \"new_text\": {\"type\": \"string\"}}, \"required\": [\"path\", \"old_text\", \"new_text\"]}},\n {\"name\": \"load_skill\", \"description\": \"Load specialized knowledge by name.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\", \"description\": \"Skill name to load\"}}, \"required\": [\"name\"]}},\n]\n\n\ndef agent_loop(messages: list):\n while True:\n response = client.messages.create(\n model=MODEL, system=SYSTEM, messages=messages,\n tools=TOOLS, max_tokens=8000,\n )\n messages.append({\"role\": \"assistant\", \"content\": response.content})\n if response.stop_reason != \"tool_use\":\n return\n results = []\n for block in response.content:\n if block.type == \"tool_use\":\n handler = TOOL_HANDLERS.get(block.name)\n try:\n output = handler(**block.input) if handler else f\"Unknown tool: {block.name}\"\n except Exception as e:\n output = f\"Error: {e}\"\n print(f\"> {block.name}: {str(output)[:200]}\")\n results.append({\"type\": \"tool_result\", \"tool_use_id\": block.id, \"content\": str(output)})\n messages.append({\"role\": \"user\", \"content\": results})\n\n\nif __name__ == \"__main__\":\n history = []\n while True:\n try:\n query = input(\"\\033[36ms05 >> \\033[0m\")\n except (EOFError, KeyboardInterrupt):\n break\n if query.strip().lower() in (\"q\", \"exit\", \"\"):\n break\n history.append({\"role\": \"user\", \"content\": query})\n agent_loop(history)\n print()\n" + "source": "#!/usr/bin/env python3\n\"\"\"\ns05_skill_loading.py - Skills\n\nTwo-layer skill injection that avoids bloating the system prompt:\n\n Layer 1 (cheap): skill names in system prompt (~100 tokens/skill)\n Layer 2 (on demand): full skill body in tool_result\n\n skills/\n pdf/\n SKILL.md <-- frontmatter (name, description) + body\n code-review/\n SKILL.md\n\n System prompt:\n +--------------------------------------+\n | You are a coding agent. |\n | Skills available: |\n | - pdf: Process PDF files... | <-- Layer 1: metadata only\n | - code-review: Review code... |\n +--------------------------------------+\n\n When model calls load_skill(\"pdf\"):\n +--------------------------------------+\n | tool_result: |\n | |\n | Full PDF processing instructions | <-- Layer 2: full body\n | Step 1: ... |\n | Step 2: ... |\n | |\n +--------------------------------------+\n\nKey insight: \"Don't put everything in the system prompt. Load on demand.\"\n\"\"\"\n\nimport os\nimport re\nimport subprocess\nfrom pathlib import Path\n\nfrom anthropic import Anthropic\nfrom dotenv import load_dotenv\n\nload_dotenv(override=True)\n\nif os.getenv(\"ANTHROPIC_BASE_URL\"):\n os.environ.pop(\"ANTHROPIC_AUTH_TOKEN\", None)\n\nWORKDIR = Path.cwd()\nclient = Anthropic(base_url=os.getenv(\"ANTHROPIC_BASE_URL\"))\nMODEL = os.environ[\"MODEL_ID\"]\nSKILLS_DIR = WORKDIR / \"skills\"\n\n\n# -- SkillLoader: scan skills//SKILL.md with YAML frontmatter --\nclass SkillLoader:\n def __init__(self, skills_dir: Path):\n self.skills_dir = skills_dir\n self.skills = {}\n self._load_all()\n\n def _load_all(self):\n if not self.skills_dir.exists():\n return\n for f in sorted(self.skills_dir.rglob(\"SKILL.md\")):\n text = f.read_text()\n meta, body = self._parse_frontmatter(text)\n name = meta.get(\"name\", f.parent.name)\n self.skills[name] = {\"meta\": meta, \"body\": body, \"path\": str(f)}\n\n def _parse_frontmatter(self, text: str) -> tuple:\n \"\"\"Parse YAML frontmatter between --- delimiters.\"\"\"\n match = re.match(r\"^---\\n(.*?)\\n---\\n(.*)\", text, re.DOTALL)\n if not match:\n return {}, text\n meta = {}\n for line in match.group(1).strip().splitlines():\n if \":\" in line:\n key, val = line.split(\":\", 1)\n meta[key.strip()] = val.strip()\n return meta, match.group(2).strip()\n\n def get_descriptions(self) -> str:\n \"\"\"Layer 1: short descriptions for the system prompt.\"\"\"\n if not self.skills:\n return \"(no skills available)\"\n lines = []\n for name, skill in self.skills.items():\n desc = skill[\"meta\"].get(\"description\", \"No description\")\n tags = skill[\"meta\"].get(\"tags\", \"\")\n line = f\" - {name}: {desc}\"\n if tags:\n line += f\" [{tags}]\"\n lines.append(line)\n return \"\\n\".join(lines)\n\n def get_content(self, name: str) -> str:\n \"\"\"Layer 2: full skill body returned in tool_result.\"\"\"\n skill = self.skills.get(name)\n if not skill:\n return f\"Error: Unknown skill '{name}'. Available: {', '.join(self.skills.keys())}\"\n return f\"\\n{skill['body']}\\n\"\n\n\nSKILL_LOADER = SkillLoader(SKILLS_DIR)\n\n# Layer 1: skill metadata injected into system prompt\nSYSTEM = f\"\"\"You are a coding agent at {WORKDIR}.\nUse load_skill to access specialized knowledge before tackling unfamiliar topics.\n\nSkills available:\n{SKILL_LOADER.get_descriptions()}\"\"\"\n\n\n# -- Tool implementations --\ndef safe_path(p: str) -> Path:\n path = (WORKDIR / p).resolve()\n if not path.is_relative_to(WORKDIR):\n raise ValueError(f\"Path escapes workspace: {p}\")\n return path\n\ndef run_bash(command: str) -> str:\n dangerous = [\"rm -rf /\", \"sudo\", \"shutdown\", \"reboot\", \"> /dev/\"]\n if any(d in command for d in dangerous):\n return \"Error: Dangerous command blocked\"\n try:\n r = subprocess.run(command, shell=True, cwd=WORKDIR,\n capture_output=True, text=True, timeout=120)\n out = (r.stdout + r.stderr).strip()\n return out[:50000] if out else \"(no output)\"\n except subprocess.TimeoutExpired:\n return \"Error: Timeout (120s)\"\n\ndef run_read(path: str, limit: int = None) -> str:\n try:\n lines = safe_path(path).read_text().splitlines()\n if limit and limit < len(lines):\n lines = lines[:limit] + [f\"... ({len(lines) - limit} more)\"]\n return \"\\n\".join(lines)[:50000]\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_write(path: str, content: str) -> str:\n try:\n fp = safe_path(path)\n fp.parent.mkdir(parents=True, exist_ok=True)\n fp.write_text(content)\n return f\"Wrote {len(content)} bytes\"\n except Exception as e:\n return f\"Error: {e}\"\n\ndef run_edit(path: str, old_text: str, new_text: str) -> str:\n try:\n fp = safe_path(path)\n content = fp.read_text()\n if old_text not in content:\n return f\"Error: Text not found in {path}\"\n fp.write_text(content.replace(old_text, new_text, 1))\n return f\"Edited {path}\"\n except Exception as e:\n return f\"Error: {e}\"\n\n\nTOOL_HANDLERS = {\n \"bash\": lambda **kw: run_bash(kw[\"command\"]),\n \"read_file\": lambda **kw: run_read(kw[\"path\"], kw.get(\"limit\")),\n \"write_file\": lambda **kw: run_write(kw[\"path\"], kw[\"content\"]),\n \"edit_file\": lambda **kw: run_edit(kw[\"path\"], kw[\"old_text\"], kw[\"new_text\"]),\n \"load_skill\": lambda **kw: SKILL_LOADER.get_content(kw[\"name\"]),\n}\n\nTOOLS = [\n {\"name\": \"bash\", \"description\": \"Run a shell command.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"command\": {\"type\": \"string\"}}, \"required\": [\"command\"]}},\n {\"name\": \"read_file\", \"description\": \"Read file contents.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"limit\": {\"type\": \"integer\"}}, \"required\": [\"path\"]}},\n {\"name\": \"write_file\", \"description\": \"Write content to file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"content\": {\"type\": \"string\"}}, \"required\": [\"path\", \"content\"]}},\n {\"name\": \"edit_file\", \"description\": \"Replace exact text in file.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"path\": {\"type\": \"string\"}, \"old_text\": {\"type\": \"string\"}, \"new_text\": {\"type\": \"string\"}}, \"required\": [\"path\", \"old_text\", \"new_text\"]}},\n {\"name\": \"load_skill\", \"description\": \"Load specialized knowledge by name.\",\n \"input_schema\": {\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\", \"description\": \"Skill name to load\"}}, \"required\": [\"name\"]}},\n]\n\n\ndef agent_loop(messages: list):\n while True:\n response = client.messages.create(\n model=MODEL, system=SYSTEM, messages=messages,\n tools=TOOLS, max_tokens=8000,\n )\n messages.append({\"role\": \"assistant\", \"content\": response.content})\n if response.stop_reason != \"tool_use\":\n return\n results = []\n for block in response.content:\n if block.type == \"tool_use\":\n handler = TOOL_HANDLERS.get(block.name)\n try:\n output = handler(**block.input) if handler else f\"Unknown tool: {block.name}\"\n except Exception as e:\n output = f\"Error: {e}\"\n print(f\"> {block.name}: {str(output)[:200]}\")\n results.append({\"type\": \"tool_result\", \"tool_use_id\": block.id, \"content\": str(output)})\n messages.append({\"role\": \"user\", \"content\": results})\n\n\nif __name__ == \"__main__\":\n history = []\n while True:\n try:\n query = input(\"\\033[36ms05 >> \\033[0m\")\n except (EOFError, KeyboardInterrupt):\n break\n if query.strip().lower() in (\"q\", \"exit\", \"\"):\n break\n history.append({\"role\": \"user\", \"content\": query})\n agent_loop(history)\n print()\n" }, { "id": "s06", @@ -856,7 +856,7 @@ "newTools": [ "todo" ], - "locDelta": 58 + "locDelta": 56 }, { "from": "s03", @@ -868,7 +868,7 @@ "newTools": [ "task" ], - "locDelta": -27 + "locDelta": -25 }, { "from": "s04", @@ -880,7 +880,7 @@ "newTools": [ "load_skill" ], - "locDelta": 31 + "locDelta": 36 }, { "from": "s05", @@ -894,7 +894,7 @@ "newTools": [ "compact" ], - "locDelta": 23 + "locDelta": 18 }, { "from": "s06",