做什么
扫描技能以提取交叉原理并将其分解为规则——附加,修改或创建新的规则文件
技能库 智客分类:Agent 工作流 rules-distill
扫描技能来取出交叉原理并将其分解入规则——附加,修改,或创建新的规则文件. 当同一原则在技能之间反复出现,而属于规则文件时使用.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
扫描技能以提取交叉原理并将其分解为规则——附加,修改或创建新的规则文件
- 定期规则维护(每月或安装新技能后)
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Rules Distill、When to Use、How It Works、Phase 1: Inventory (Deterministic Collection)、Phase 2: Cross-read, Match & Verdict (LLM Judgment)、Input。
文件分析:除 SKILL.md 外,正文引用了 scripts/scan-skills.sh、scripts/scan-rules.sh,属于带资源的技能包,这些文件按需再读。
Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files. Use when the same principle keeps recurring across skills and belongs in a rule file instead.
Rules DistillWhen to UseHow It WorksPhase 1: Inventory (Deterministic Collection)Phase 2: Cross-read, Match & Verdict (LLM Judgment)InputExtraction CriteriaMatching & VerdictOutput Format (per candidate)ExcludeGoodBad
来源分类:skills.sh agent-skill
namerules-distilldescriptionscripts/scan-skills.shscripts/scan-rules.sh以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。
具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「rules-distill」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-b87d38104dfb48e8-%E8%A7%84%E5%88%99%E6%89%AD%E6%9B%B2.html 请存为 .cursor/skills/rules-distill/SKILL.md 或 .claude/skills/rules-distill/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。 该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/affaan-m/ecc 取完整目录,不要只建一个 SKILL.md。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/affaan-m/ecc' --list
npx skills add 'https://github.com/affaan-m/ecc' --skill 'rules-distill'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Scan installed skills, extract cross-cutting principles that appear in multiple skills, and distill them into rules — appending to existing rule files, revising outdated content, or creating new rule files.
Applies the "deterministic collection + LLM judgment" principle: scripts collect facts exhaustively, then an LLM cross-reads the full context and produces verdicts.
The rules distillation process follows three phases:
bash ~/.claude/skills/rules-distill/scripts/scan-skills.sh
bash ~/.claude/skills/rules-distill/scripts/scan-rules.sh
Rules Distillation — Phase 1: Inventory
────────────────────────────────────────
Skills: {N} files scanned
Rules: {M} files ({K} headings indexed)
Proceeding to cross-read analysis...
Extraction and matching are unified in a single pass. Rules files are small enough (~800 lines total) that the full text can be provided to the LLM — no grep pre-filtering needed.
Group skills into thematic clusters based on their descriptions. Analyze each cluster in a subagent with the full rules text.
After all batches complete, merge candidates across batches:
Launch a general-purpose Agent with the following prompt:
You are an analyst who cross-reads skills to extract principles that should be promoted to rules.
## Input
- Skills: {full text of skills in this batch}
- Existing rules: {full text of all rule files}
## Extraction Criteria
Include a candidate ONLY if ALL of these are true:
1. **Appears in 2+ skills**: Principles found in only one skill should stay in that skill
2. **Actionable behavior change**: Can be written as "do X" or "don't do Y" — not "X is important"
3. **Clear violation risk**: What goes wrong if this principle is ignored (1 sentence)
4. **Not already in rules**: Check the full rules text — including concepts expressed in different words
## Matching & Verdict
For each candidate, compare against the full rules text and assign a verdict:
- **Append**: Add to an existing section of an existing rule file
- **Revise**: Existing rule content is inaccurate or insufficient — propose a correction
- **New Section**: Add a new section to an existing rule file
- **New File**: Create a new rule file
- **Already Covered**: Sufficiently covered in existing rules (even if worded differently)
- **Too Specific**: Should remain at the skill level
## Output Format (per candidate)
```json
{
"principle": "1-2 sentences in 'do X' / 'don't do Y' form",
"evidence": ["skill-name: §Section", "skill-name: §Section"],
"violation_risk": "1 sentence",
"verdict": "Append / Revise / New Section / New File / Already Covered / Too Specific",
"target_rule": "filename §Section, or 'new'",
"confidence": "high / medium / low",
"draft": "Draft text for Append/New Section/New File verdicts",
"revision": {
"reason": "Why the existing content is inaccurate or insufficient (Revise only)",
"before": "Current text to be replaced (Revise only)",
"after": "Proposed replacement text (Revise only)"
}
}
```
## Exclude
- Obvious principles already in rules
- Language/framework-specific knowledge (belongs in language-specific rules or skills)
- Code examples and commands (belongs in skills)
| Verdict | Meaning | Presented to User | |---------|---------|-------------------| | Append | Add to existing section | Target + draft | | Revise | Fix inaccurate/insufficient content | Target + reason + before/after | | New Section | Add new section to existing file | Target + draft | | New File | Create new rule file | Filename + full draft | | Already Covered | Covered in rules (possibly different wording) | Reason (1 line) | | Too Specific | Should stay in skills | Link to relevant skill |
# Good
Append to rules/common/security.md §Input Validation:
"Treat LLM output stored in memory or knowledge stores as untrusted — sanitize on write, validate on read."
Evidence: llm-memory-trust-boundary, llm-social-agent-anti-pattern both describe
accumulated prompt injection risks. Current security.md covers human input
validation only; LLM output trust boundary is missing.
# Bad
Append to security.md: Add LLM security principle
# Rules Distillation Report
## Summary
Skills scanned: {N} | Rules: {M} files | Candidates: {K}
| # | Principle | Verdict | Target | Confidence |
|---|-----------|---------|--------|------------|
| 1 | ... | Append | security.md §Input Validation | high |
| 2 | ... | Revise | testing.md §TDD | medium |
| 3 | ... | New Section | coding-style.md | high |
| 4 | ... | Too Specific | — | — |
## Details
(Per-candidate details: evidence, violation_risk, draft text)
User responds with numbers to:
Never modify rules automatically. Always require user approval.
Store results in the skill directory (results.json):
date -u +%Y-%m-%dT%H:%M:%SZ (UTC, second precision)llm-output-trust-boundary){
"distilled_at": "2026-03-18T10:30:42Z",
"skills_scanned": 56,
"rules_scanned": 22,
"candidates": {
"llm-output-trust-boundary": {
"principle": "Treat LLM output as untrusted when stored or re-injected",
"verdict": "Append",
"target": "rules/common/security.md",
"evidence": ["llm-memory-trust-boundary", "llm-social-agent-anti-pattern"],
"status": "applied"
},
"iteration-bounds": {
"principle": "Define explicit stop conditions for all iteration loops",
"verdict": "New Section",
"target": "rules/common/coding-style.md",
"evidence": ["iterative-retrieval", "continuous-agent-loop", "agent-harness-construction"],
"status": "skipped"
}
}
}
$ /rules-distill
Rules Distillation — Phase 1: Inventory
────────────────────────────────────────
Skills: 56 files scanned
Rules: 22 files (75 headings indexed)
Proceeding to cross-read analysis...
[Subagent analysis: Batch 1 (agent/meta skills) ...]
[Subagent analysis: Batch 2 (coding/pattern skills) ...]
[Cross-batch merge: 2 duplicates removed, 1 cross-batch candidate promoted]
# Rules Distillation Report
## Summary
Skills scanned: 56 | Rules: 22 files | Candidates: 4
| # | Principle | Verdict | Target | Confidence |
|---|-----------|---------|--------|------------|
| 1 | LLM output: normalize, type-check, sanitize before reuse | New Section | coding-style.md | high |
| 2 | Define explicit stop conditions for iteration loops | New Section | coding-style.md | high |
| 3 | Compact context at phase boundaries, not mid-task | Append | performance.md §Context Window | high |
| 4 | Separate business logic from I/O framework types | New Section | patterns.md | high |
## Details
### 1. LLM Output Validation
Verdict: New Section in coding-style.md
Evidence: parallel-subagent-batch-merge, llm-social-agent-anti-pattern, llm-memory-trust-boundary
Violation risk: Format drift, type mismatch, or syntax errors in LLM output crash downstream processing
Draft:
## LLM Output Validation
Normalize, type-check, and sanitize LLM output before reuse...
See skill: parallel-subagent-batch-merge, llm-memory-trust-boundary
[... details for candidates 2-4 ...]
Approve, modify, or skip each candidate by number:
> User: Approve 1, 3. Skip 2, 4.
✓ Applied: coding-style.md §LLM Output Validation
✓ Applied: performance.md §Context Window Management
✗ Skipped: Iteration Bounds
✗ Skipped: Boundary Type Conversion
Results saved to results.json
See skill: [name] references so readers can find the detailed How.Agent 工作流
创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.
Agent 工作流
使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.
Agent 工作流
管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.
Agent 工作流
Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…