agentleFS
naman10parikhnaman10parikh/wikimem/.claude/skills/skill-creator/SKILL.md

skill-creator

Skill8 starsChanged 27 days agoMITView on GitHub

Auto-generate new skills from learnings, approved patterns, and repeated user preferences. The meta-skill that makes the harness self-improving. Core to AutoLab.

190 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use taskflow-inbox-triage, mermaid-diagram-generator and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • shalombSkill

    mermaid-diagram-generator

    Guide on creating and editing Mermaid charts safely. Use when asked to draw a diagram, flowchart, or architecture chart. Triggers on: 'mermaid', 'diagram', 'flowchart', 'visualize'.

    Also in 5 projects that use this

  • Liang-MHSkill

    stock_analysis

    获取 A 股、基金和港股的实时行情和技术分析数据

    Also in 5 projects that use this

  • nicepkgSkill

    community-led-growth

    Expert in community-led growth (CLG) - leveraging user communities to drive acquisition, retention, and expansion. Covers building developer communities, user groups, ambassador programs, and turning customers into advocates. Knows the difference between community as a feature vs community as a growth engine, and how to measure community ROI. Use when "community-led, CLG, ambassador program, champion program, user community, developer community, word of mouth, user group, " mentioned.

    Also in 5 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

22 rules. 0 are common, 19 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 185 edited versions we read keep these.

  • 19

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After discovering a repeatable pattern across 2+ sessions

    line 8
  2. Distinctive:

    When the user explicitly approves a workflow ("always do X")

    line 9
  3. Distinctive:

    When LEARNINGS.md has 3+ entries about the same topic

    line 10
  4. Distinctive:

    When a sub-agent finds a new capability worth capturing

    line 11
  5. Very specific:

    Write SKILL.md to .claude/skills/{skill-name}/SKILL.md

    line 75
  6. Distinctive:

    Add trigger patterns that the skill-routing system can match

    line 77
  7. Distinctive:

    If the skill involves code patterns, include inline examples

    line 78
  8. Distinctive:

    If the skill involves external tools, document the setup

    line 79
  9. Distinctive:

    Update CLAUDE.md skills count

    line 80
  10. Very specific:

    Test: verify the skill is discoverable via /skill-routing

    line 81
  11. Distinctive:

    When a YouTube video or article needs to be processed:

    line 115
  12. Distinctive:

    If insights warrant a new skill, create it

    line 123
  13. Distinctive:

    Use computer use to browse the tweet/thread

    line 127
  14. Distinctive:

    If it's a thread, compile all tweets

    line 129
  15. Distinctive:

    Run standardized assessment across all evals:

    line 166
  16. Distinctive:

    Run after model updates or skill edits

    line 169
  17. Very specific:

    Use isolation: "worktree" for code-modifying skills

    line 178
  18. Distinctive:

    Use comparator agents to judge:

    line 182
  19. Distinctive:

    After creating a skill:

    line 203
  20. Distinctive:

    Test with a simulated trigger to verify steps are clear

    line 208
  21. Distinctive:

    Write at least 2 evals per skill

    line 209
  22. Distinctive:

    Run benchmark to establish baseline metrics

    line 210

“Common” is measured: kept by at least 6 in 10 of the 185 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

When to Use

  • After discovering a repeatable pattern across 2+ sessions
  • When the user explicitly approves a workflow ("always do X")
  • When LEARNINGS.md has 3+ entries about the same topic
  • When a sub-agent finds a new capability worth capturing
  • During AutoLab nightly improvement cycles

Process

1. Source Mining

Scan these sources for skill candidates:

  • memory/LEARNINGS.md — repeated corrections = skill gaps
  • memory/MEMORY.md — confirmed patterns = skill candidates
  • memory/daily/*.md — workflows that worked = codify them
  • resources/read/*.md — external techniques worth internalizing
  • Session transcript — what did the user approve? correct? praise?
  • packages/web/features.json — feature patterns that recur

2. Skill Candidate Evaluation

For each candidate, score on 4 axes:

AxisQuestionThreshold
FrequencyHow often would this skill be triggered?2+ times/week
ComplexityDoes it need multi-step instructions?3+ steps
Error-proneDo we keep getting it wrong without the skill?2+ mistakes
ReusableDoes it apply across agents, not just one?Cross-agent preferred

Score >= 3/4 axes → create the skill.

3. Skill Template

---
name: { skill-name }
description: { one-line description, under 100 chars }
---

## When to Use

- {trigger condition 1}
- {trigger condition 2}

## Process

### Step 1: {Action}

{What to do, what to check}

### Step 2: {Action}

{What to do, what to check}

## Output

- {What the skill produces}
- {How to verify it worked}

## Model Tier

- {Haiku | Sonnet | Opus} for each step

4. Skill Creation Checklist

  1. Write SKILL.md to .claude/skills/{skill-name}/SKILL.md
  2. Description must be under 100 chars (for ~70 token routing)
  3. Add trigger patterns that the skill-routing system can match
  4. If the skill involves code patterns, include inline examples
  5. If the skill involves external tools, document the setup
  6. Update CLAUDE.md skills count
  7. Test: verify the skill is discoverable via /skill-routing

5. Skill Categories

CategoryPurposeExamples
BuildCode generation patternsapp-factory, agent-runtime
MetaSelf-improvement, researchself-improve, deep-think
OpsSetup, deployment, inframcp-setup, secrets-setup
AgentAgent-specific skillsPer-agent skills in agents/{name}/skills/
CaptureKnowledge capturetranscript-to-insight, resource-digest

6. For Agent-Level Skills

Skills can also be created for individual agents (not just the harness):

agents/{agent-name}/skills/{skill-name}.md

These are loaded into the agent's system prompt via the memory-loader. They follow the same template but are scoped to that agent's domain.

Integration with AutoLab

The Skill Creator is a key component of the AutoLab nightly cycle:

  1. AutoLab analyzes traces from the day's agent runs
  2. Identifies patterns where agents struggled or succeeded
  3. Calls Skill Creator to codify successful patterns
  4. New skills are available to all agents via Group Evolution

YouTube/Article Transcript Pipeline

When a YouTube video or article needs to be processed:

  1. Get the URL from user or resource queue
  2. For YouTube: Use computer use to visit a transcript service (e.g., tavio.io, kome.ai, or youtubetranscript.com)
  3. Enter the URL, download the transcript text
  4. Clean and structure the transcript
  5. Extract insights relevant to Energy platform
  6. Save to resources/read/{topic}.md
  7. If insights warrant a new skill, create it

X/Twitter Content Pipeline

  1. Use computer use to browse the tweet/thread
  2. Extract the full text content
  3. If it's a thread, compile all tweets
  4. Extract actionable insights
  5. Save to resources and update relevant docs

Skill Testing & Evals (from Anthropic's skill-creator enhancements, March 2026)

Two Kinds of Skills

  1. Capability uplift — helps Claude do something the base model can't do consistently (e.g., document creation, complex workflows). May become unnecessary as models improve.
  2. Encoded preference — sequences steps according to your team's process (e.g., NDA review, weekly updates). Durable, value depends on fidelity to actual workflow.

Writing Evals

For each skill, define test cases:

## Evals

### Test 1: {scenario}

- **Prompt:** "{test input that should trigger the skill}"
- **Expected:** {description of correct output}
- **Files:** {any test files needed}

### Test 2: {scenario}

...

Evals check that:

  • The skill triggers when it should (no false negatives)
  • The skill doesn't trigger when it shouldn't (no false positives)
  • Output quality meets the bar defined in "Expected"

Benchmark Mode

Run standardized assessment across all evals:

  • Track eval pass rate, elapsed time, token usage
  • Run after model updates or skill edits
  • Store results locally or integrate with CI

Multi-Agent Eval Execution

Spin up independent agents to run evals in parallel:

  • Each eval in a clean context (no cross-contamination)
  • Own token and timing metrics per eval
  • Use isolation: "worktree" for code-modifying skills

A/B Comparisons

Use comparator agents to judge:

  • Skill v1 vs v2 (after edits)
  • Skill vs no skill (is it still needed?)
  • Judges don't know which output is which → unbiased

Description Tuning

As skill count grows, description precision is critical:

  • Too broad → false triggers on unrelated prompts
  • Too narrow → never fires when needed
  • Analyze description against sample prompts
  • Suggest edits that cut both false positives and false negatives

The Future: Skills → Specifications

As models improve, skills evolve from "how to do X" (implementation) to "what X should produce" (specification). Evals already describe the "what" — eventually the eval IS the skill.

Verification

After creating a skill:

  • Confirm it appears in skill count
  • Confirm skill-routing can find it with relevant keywords
  • Confirm the description fits in ~70 tokens
  • Test with a simulated trigger to verify steps are clear
  • Write at least 2 evals per skill
  • Run benchmark to establish baseline metrics

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.