Agent skill

skill-extractor

Extract reusable skills from conversation patterns. Use when asked to "turn this into a skill," "extract a skill," or "I keep doing this task repeatedly."

Stars 25
Forks 5

Install this agent skill to your Project

npx add-skill https://github.com/leegonzales/AISkills/tree/main/SkillExtractor/skill-extractor

SKILL.md

Skill Extractor

Transform repeated conversation patterns into reusable SKILL.md files.

Workflow

1. Gather Evidence

Ask: "Share a conversation excerpt where Claude did this task well, or describe a task you do repeatedly."

Accept:

  • Pasted conversation excerpts
  • Task descriptions with examples
  • Multiple examples to find common patterns

2. Identify the Pattern

Analyze for these elements:

Element Find This
Trigger What phrase starts this workflow?
Input What does user provide?
Transform What does Claude do with it?
Output What format/structure results?
Quality What separates good from bad?

3. Validate

Confirm: "It sounds like you want to [workflow]. Is that right?"

Refine: "What would you change? What context made it work?"

4. Generate SKILL.md

Output a complete skill file following the format in references/skill-template.md.

5. Test

Run the extracted skill on fresh input. Iterate until it works reliably.

Skill Archetypes

Type Pattern Example
Transformer Format A → Format B Notes → Email
Analyzer Input → Assessment Code → Review
Generator Parameters → Content Topic → Blog
Synthesizer Many → One Feedback → Themes

Viability Check

Strong candidates:

  • Done 3+ times with similar structure
  • Clear input → output transformation
  • Required specific prompting to work
  • Explainable to a colleague

Weak candidates:

  • One-off creative tasks
  • Simple Q&A (no workflow)
  • Requires external data
  • Too vague to define success

Output Deliverables

Provide:

  1. SKILL.md — Complete, ready to use
  2. Test prompt — Verify it works
  3. Usage examples — How to invoke
  4. Refinement notes — Next iteration

Example Extraction

User says: "I keep asking Claude to turn meeting notes into weekly updates."

Extracted pattern:

  • Trigger: "write weekly update" / "summarize this week"
  • Input: Bullet points from meetings
  • Transform: Organize by Accomplishments/In Progress/Blockers
  • Output: Professional email format
  • Quality: Outcome-focused, not activity-focused

Result: See references/example-extractions.md for the full weekly-update-writer skill.

References

  • references/skill-template.md — Standard skill format
  • references/example-extractions.md — Before/after examples

Expand your agent's capabilities with these related and highly-rated skills.

leegonzales/AISkills

context-continuity

High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "handoff," "continue this in another chat," or needs to work around context window limits. Produces structured artifacts (Minimal ~200 words, Full ~1000 words). DO NOT trigger on simple "summarize our conversation" requests—only when transfer intent is explicit.

25 5
Explore
leegonzales/AISkills

codex-peer-review

25 5
Explore
leegonzales/AISkills

silicon-doppelganger

Build psychometrically accurate personal proxy agents for the PAIRL Conductor system. Extracts personality, decision heuristics, and values into portable schemas that enable AI agents to negotiate, filter, and act on a principal's behalf.

25 5
Explore
leegonzales/AISkills

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches three independent reviewers in parallel.

25 5
Explore
leegonzales/AISkills

fabric-patterns

Run danielmiessler/fabric CLI patterns for content analysis, extraction, summarization, writing, security analysis, and more. Use when user asks to "use fabric," "run a pattern," "extract wisdom," "summarize with fabric," or when piping content through AI patterns would be more effective than inline processing. Triggers include "fabric," "pattern," "extract wisdom," "summarize this article," "analyze this threat report," or any reference to a specific fabric pattern name.

25 5
Explore
leegonzales/AISkills

moltbook-enclave

Secure, air-gapped interface for Moltbook (social network for AI agents). Isolates untrusted external content from your main agent's memory and context.

25 5
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results