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
- theexperiencecompany/gaiatheir own version, first seen Nov 13, 2026
- maotoumao/Cebiantheir own version, first seen Nov 9, 2026
- SebastienDegodez/copilot-instructionstheir own version, first seen Nov 8, 2026
- idavidov13/agentic-playwrighttheir own version, first seen Nov 8, 2026
- HughYau/AcademicForgetheir own version, first seen Nov 8, 2026
- Ar9av/obsidian-wikitheir own version, first seen Nov 8, 2026
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-aiSkilltaskflow-inbox-triage
Also in 6 projects that use this
shalombSkillmermaid-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-MHSkillstock_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
nicepkgSkillcommunity-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
Other versions190 projects use a version of this.
Word for word · 1
- naman10parikh/agentgrid★ 9100% same
Edited · 0
None found.
Wrote their own version · 189
- openclaw/openclaw★ 395ksame name
- moltbot/clawdbot★ 394ksame name
- steipete/warelay★ 394ksame name
- steipete/clawdis★ 394ksame name
- moltbot/moltbot★ 394ksame name
- clawdbot/clawdbot★ 394ksame name
- molt-bot/clawdbot★ 391ksame name
- anthropics/skills★ 195ksame name
- openai/codex★ 135ksame name
- google-gemini/gemini-cli★ 109ksame name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agent-runtimeSkill
- frontend-designSkill
- architectSkill
- deep-thinkSkill
- design-systemsSkill
- ecosystem-referenceSkill
- fractal-delegationSkill
- harness-reviewSkill
- heartbeatSkill
- integrate-resourcesSkill
- llm-council-critiqueSkill
- loop-createSkill
- mcp-setupSkill
- memory-compressionSkill
- memorySkill
- model-routingSkill
- oss-project-scaffoldSkill
- playwright-cliSkill
- repo-scoutSkill
- self-improveSkill
- skill-routingSkill
- sprintSkill
- test-visualSkill
- troubleshootSkill
- ux-auditSkill
- wikimem-ingest-pipelineSkill
- wikimem-observerSkill
- wikimemSkill
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
- Distinctive: line 8
After discovering a repeatable pattern across 2+ sessions
- Distinctive: line 9
When the user explicitly approves a workflow ("always do X")
- Distinctive: line 10
When LEARNINGS.md has 3+ entries about the same topic
- Distinctive: line 11
When a sub-agent finds a new capability worth capturing
- Very specific: line 75
Write SKILL.md to .claude/skills/{skill-name}/SKILL.md
- Distinctive: line 77
Add trigger patterns that the skill-routing system can match
- Distinctive: line 78
If the skill involves code patterns, include inline examples
- Distinctive: line 79
If the skill involves external tools, document the setup
- Distinctive: line 80
Update CLAUDE.md skills count
- Very specific: line 81
Test: verify the skill is discoverable via /skill-routing
- Distinctive: line 115
When a YouTube video or article needs to be processed:
- Distinctive: line 123
If insights warrant a new skill, create it
- Distinctive: line 127
Use computer use to browse the tweet/thread
- Distinctive: line 129
If it's a thread, compile all tweets
- Distinctive: line 166
Run standardized assessment across all evals:
- Distinctive: line 169
Run after model updates or skill edits
- Very specific: line 178
Use isolation: "worktree" for code-modifying skills
- Distinctive: line 182
Use comparator agents to judge:
- Distinctive: line 203
After creating a skill:
- Distinctive: line 208
Test with a simulated trigger to verify steps are clear
- Distinctive: line 209
Write at least 2 evals per skill
- Distinctive: line 210
Run benchmark to establish baseline metrics
“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.
Files
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 gapsmemory/MEMORY.md— confirmed patterns = skill candidatesmemory/daily/*.md— workflows that worked = codify themresources/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:
| Axis | Question | Threshold |
| Frequency | How often would this skill be triggered? | 2+ times/week |
| Complexity | Does it need multi-step instructions? | 3+ steps |
| Error-prone | Do we keep getting it wrong without the skill? | 2+ mistakes |
| Reusable | Does 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 step4. Skill Creation Checklist
- Write
SKILL.mdto.claude/skills/{skill-name}/SKILL.md - Description must be under 100 chars (for ~70 token routing)
- Add trigger patterns that the skill-routing system can match
- If the skill involves code patterns, include inline examples
- If the skill involves external tools, document the setup
- Update CLAUDE.md skills count
- Test: verify the skill is discoverable via
/skill-routing
5. Skill Categories
| Category | Purpose | Examples |
| Build | Code generation patterns | app-factory, agent-runtime |
| Meta | Self-improvement, research | self-improve, deep-think |
| Ops | Setup, deployment, infra | mcp-setup, secrets-setup |
| Agent | Agent-specific skills | Per-agent skills in agents/{name}/skills/ |
| Capture | Knowledge capture | transcript-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}.mdThese 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:
- AutoLab analyzes traces from the day's agent runs
- Identifies patterns where agents struggled or succeeded
- Calls Skill Creator to codify successful patterns
- New skills are available to all agents via Group Evolution
YouTube/Article Transcript Pipeline
When a YouTube video or article needs to be processed:
- Get the URL from user or resource queue
- For YouTube: Use computer use to visit a transcript service (e.g., tavio.io, kome.ai, or youtubetranscript.com)
- Enter the URL, download the transcript text
- Clean and structure the transcript
- Extract insights relevant to Energy platform
- Save to
resources/read/{topic}.md - If insights warrant a new skill, create it
X/Twitter Content Pipeline
- Use computer use to browse the tweet/thread
- Extract the full text content
- If it's a thread, compile all tweets
- Extract actionable insights
- Save to resources and update relevant docs
Skill Testing & Evals (from Anthropic's skill-creator enhancements, March 2026)
Two Kinds of Skills
- 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.
- 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
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
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.

