skill-prune — Claude Code skill: what it does, how to install
skill-prune reviews skill content for orphans, duplicates, and outdated task-specific notes. Use it during maintenance or after the linter finds issues.
MIT 163 installs ★ 632 updated 2026-07-29
npx skills add transilienceai/communitytools --skill skill-prune -a claude-codeWhat skill-prune does
skill-prune reviews a skill collection for content that no longer earns its place. It flags unlinked files, material seen only in blocked engagements, entries superseded by newer techniques, and repeated coverage. The skill uses these four signals to separate removal candidates from content worth keeping.
It starts with scripts/skill_linter.py --check-orphans, then prepares a deletion plan that names files or lines and gives a short reason for each item. Nothing is deleted during the invocation: the plan needs approval first. Files marked with <!-- KEEP: <reason> -->, content cited by an active engagement, and canonical single-owner files are protected.
Run scripts/skill_linter.py again after the approved changes to catch broken links or duplicates. The skill is available for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.
What it helps with
- find orphaned files in a skill collection
- remove duplicate technique notes
- drop lore from retired engagements
- review candidates flagged by the linter
- prepare an approved deletion plan
Example prompts for the agent
- Review this skill collection and identify content that should be pruned.
- Run
scripts/skill_linter.py --check-orphans, apply the four signals, and prepare a deletion plan without deleting anything. - Check whether any candidate is protected by
<!-- KEEP: <reason> -->or an active engagement reference.
How to install skill-prune
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill skill-prune -a claude-code2Manually: put the files in place
~/.claude/skills/skill-prune/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill-prune/
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill skill-prune -a codex2Manually: put the files in place
.agents/skills/skill-prune/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill skill-prune -a cursor2Manually: put the files in place
.cursor/skills/skill-prune/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install transilienceai/communitytools skills/skill-prune2Manually: put the files in place
.github/skills/skill-prune/SKILL.md1Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill skill-prune -a gemini-cli2Platform CLI
gemini skills install https://github.com/transilienceai/communitytools --path skills/skill-pruneManually: put the files in place
.devin/skills/skill-prune/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add transilienceai/communitytools --skill skill-prune -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about skill-prune
How do I install skill-prune in Claude Code?
Run npx skills add transilienceai/communitytools --skill skill-prune -a claude-code, then check ~/.claude/skills/skill-prune/SKILL.md.
What does skill-prune do?
It reviews skill content for orphaned files, duplicates, blocked-run-only references, and older entries replaced by newer material. It produces a removal plan rather than deleting content immediately.
Does skill-prune delete files automatically?
No. It lists candidates with reasons and waits for plan approval; after the change, it can run scripts/skill_linter.py again to verify links and duplicates.
Source text
SKILL.md · MIT
--- name: skill-prune description: Identify and remove negative-ROI skill content — orphan files, never-read entries, duplicates, content reintroducing challenge-specific lore. Inverse of /skill-update. Use during quarterly maintenance or after the linter flags issues. --- # Skill Prune Inverse of `/skill-update`. Removes content rather than adding it. Run during quarterly maintenance, after engagements, or when `scripts/skill_linter.py` reports orphans / duplicates. ## When to invoke - Quarterly cadence. - After `scripts/skill_linter.py --check-orphans` reports orphan reference files. - After a SKILL.md or reference file grows past its cap and needs trimming. - After a de-specialization sweep, to drop content tied to retired challenges. ## Prune criteria (the four signals — same shape as /skill-update, inverted) A reference / scenario / line is a **prune candidate** when it satisfies any of: 1. **Orphan** — not linked from any SKILL.md or other reference file in the last 60 days. 2. **Referenced only by failed engagements** — appeared in `attack-chain.md` of runs that ended `status=BLOCKED`, never in a successful chain. 3. **Contradicted by newer content** — a later scenario / pattern supersedes it; the older entry no longer reflects current technique. 4. **Redundant with newer content** — same technique covered more clearly elsewhere. Removing content fails any of these → keep it. ## Safety rules - **Never** prune a file with `<!-- KEEP: <reason> -->` annotation. - **Never** prune content cited in a still-open engagement's `OUTPUT_DIR/attack-chain.md`. - **Never** prune the canonical-home file for a single-owner rule (brute-force, output-discipline, env-reader, skill-update). - Bias toward keeping technique-rich content over operational lore. ## Procedure 1. Run `scripts/skill_linter.py --check-orphans` to surface orphans. 2. For each candidate file or block, evaluate the four signals. 3. Build a deletion plan — show files / lines to remove with one-line rationale per item. 4. Apply deletions only after the plan is approved (skill-prune does not auto-delete during invocation). 5. Re-run `scripts/skill_linter.py` to confirm the change broke no other links and didn't reintroduce duplicates. ## Output Concise change report: - **Removed.** File or block + one-line rationale per item. - **Kept (flagged for follow-up).** Items that failed all four signals but are worth revisiting next quarter. - **No prunes.** State explicitly when nothing warranted removal. ## Anti-Patterns - Pruning content because it's old — age alone is not a signal; relevance is. - Pruning a reference because its parent SKILL.md is bloated — fix the SKILL.md instead. - Removing a single-owner canonical file (brute-force / output-discipline / env-reader). - Pruning during an active engagement that may still cite the content.
© transilienceai · MIT · transilienceai/communitytools