JPeetz/agent-skills / skills/skill-development/skill-miner
skill-miner
VerifiedUse this skill when mining agent history for repeated, skill-worthy workflows that deserve to become reusable skills.
Skill Miner
Overview
Mine real agent usage for new skill opportunities. The goal is to find repeated workflows, extract the reusable technique, and turn strong candidates into draft skills with evidence.
When To Use
- A user wants to scan past coding-agent sessions for repeated workflows.
- The user suspects they keep asking agents to do similar tasks manually.
- A team wants a backlog of candidate skills based on actual work rather than brainstorming.
- Existing memories, session logs, or project notes contain recurring procedures that have not been packaged.
Do not use to tune an existing skill; use skill-personalizer. Do not use to publish a private skill publicly; use skill-generalizer.
Workflow
- Locate real evidence: session JSONL, memory summaries, repo notes, repeated scripts, and recent project folders. Use Hermes tools like
search_filesto find session logs andsession_searchto query past conversation context for recurring patterns. - Run
scripts/scan_sessions.pyfor a first-pass sanitized cluster report when local session files or exported transcripts are available. - Cluster repeated work by intent, trigger phrasing, tools used, files touched, and verification pattern.
- Filter out one-off tasks, ordinary coding knowledge, and project-specific instructions better suited for
AGENTS.md. - Score candidates by recurrence, friction, risk, portability, and future value.
- For each strong candidate, draft a concise skill name, trigger description, workflow outline, bundled-resource needs, and validation prompts.
- Recommend whether each candidate should stay personal, become a public skill (see
skill-lifecycle-foundryfor generalization), or be skipped. - If the user asks to proceed, create the selected skill folders and verify frontmatter/layout.
Evidence Rules
- Quote or summarize enough source evidence to justify each candidate.
- Do not expose sensitive transcript content unless the user explicitly asks for raw evidence.
- Avoid turning every repeated task into a skill; prefer workflows where guidance changes future behavior.
- Treat broad intent clusters as navigation hints, not skill drafts.
- Check sampled positives and near misses before trusting a regex-based workflow candidate.
- If session access is incomplete, label findings as partial and list what was scanned.
Prerequisites
- Access to agent session history or archives
- For automated scanning: a recent Hermes, Claude Code, or Codex session archive
- Familiarity with the skill-lifecycle-foundry skill for generalization and publication workflows
Pitfalls
- Session logs can contain sensitive data. Always sanitize before sharing mining results.
- One repeated task does not make a skill — look for 3+ occurrences before drafting.
- Mining without domain context can produce overly generic skill candidates.
- The automated scanner (
scan_sessions.py) is a first-pass tool. Always review its output manually before creating skills.
Verification
- Run
search_fileson session archives with recurring action patterns. - Verify that extracted candidates show 3+ repeat instances.
- Cross-check candidate against the existing
skill-lifecycle-foundryto confirm it's a genuine gap. - Draft a test workload and verify the agent follows the new skill correctly.
References
See skill-lifecycle-foundry for the full skill lifecycle: personalize, generalize, and publish skills from this miner's output.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |