Skill Manager

skill-manager

Meta-skill that keeps the installed skill/agent ecosystem small, deduplicated, and correctly routed. Deterministic work is done by stdlib-only Python scripts in scripts/; judgment (clustering, merging, scoring) is done by Claude using the scripts' JSON output.

Subcommands

| Subcommand | What it does | Read first | Key scripts | |---|---|---|---| | audit | Inventory everything, cluster by job, propose merge/archive/keep | [references/audit.md](references/audit.md) | inventory.py, refcheck.py, usagereport.py | | merge | Consolidate one approved cluster into one skill | [references/merge.md](references/merge.md) | archive.py | | registry | Generate/verify registry, inject routing into CLAUDE.md | [references/registry.md](references/registry.md) | registry.py | | health | Drift check, never-used flags, description bloat | [references/health.md](references/health.md) | registry.py --verify, usagereport.py, intakescan.py | | intake | Judge newly installed items vs registry: accept/replace/reject | [references/intake.md](references/intake.md) | intakescan.py | | compare | Analyze an external GitHub repo of skills: better than mine? missing? viable/safe to add? | [references/repo-compare.md](references/repo-compare.md) | reposcan.py | | apply | Plain-English invocation: resolve the right skill/agent/command from the registry and run it (chaining multi-step asks) | [references/apply.md](references/apply.md) | — | | new | Gap-check before creating a skill; delegate to skill-creator | [references/gap-check.md](references/gap-check.md) | inventory.py | | propose | Proactively suggest a new skill from recurring uncovered work (reuses CL-v2 instincts, registry-gated) | [references/propose.md](references/propose.md) | proposescan.py | | restore | Un-archive an item via the manifest | — | archive.py --restore |

If the user's request doesn't name a subcommand, infer it: "too many skills" → audit; "just installed X" → intake; "I need a skill that does Y" → new.

Ground rules (always apply)

1. Never delete — archive only. All removals go through archive.py, which

writes an undo manifest. Archives are kept indefinitely.

1. Never touch plugin files. Plugins are inventoried and may be recommended

for disabling (claude plugin disable / config edit by the user) — nothing more.

1. Never archive a referenced item. refcheck.py output blocks archiving;

review its match contexts (short names false-positive) and fix real references first.

1. Every merge/archive/replace requires explicit user approval, presented

per cluster or per item — never batch-approve silently.

1. Delegate, don't duplicate: quality verdicts → /skill-stocktake (reuse

its results.json if under 30 days old); new-skill authoring → skill-creator; instinct promotion → evolve/prune (out of scope).

1. After any state change (merge, archive, restore, intake accept), update

registry.json and refresh the snapshot: python scripts/intake_scan.py --update-snapshot.

1. External skills are untrusted code. Clone repos only into the session

scratchpad, never execute their scripts during analysis, read every flagged executable file before recommending install, and never register third-party hooks into settings.json automatically.

Running scripts

All scripts live in ~/.claude/skills/skill-manager/scripts/ and are stdlib-only Python 3. Run with absolute paths; use a scratch directory for the JSON outputs:

python "%USERPROFILE%\.claude\skills\skill-manager\scripts\inventory.py" --out inventory.json
python "%USERPROFILE%\.claude\skills\skill-manager\scripts\refcheck.py" --inventory inventory.json --out refcheck.json
python "%USERPROFILE%\.claude\skills\skill-manager\scripts\usage_report.py" --inventory inventory.json --out usage.json
python "%USERPROFILE%\.claude\skills\skill-manager\scripts\intake_scan.py"            # diff vs snapshot
python "%USERPROFILE%\.claude\skills\skill-manager\scripts\registry.py" --verify --inventory inventory.json
python "%USERPROFILE%\.claude\skills\skill-manager\scripts\archive.py" --list

Data files

| File | Purpose | |---|---| | ~/.claude/skills/skill-manager/registry.json | Category-keyed source of truth: canonical item per job | | ~/.claude/skills/skill-manager/inventory_snapshot.json | Baseline for new-install detection | | ~/.claude/skills-archived/ + manifest.json | Archived items + undo manifest | | ~/.claude/observations.jsonl | Usage log (written by hooks/logskillusage.py; also read by skill-stocktake) | | CLAUDE.md between `` markers | The always-loaded routing table (≤50 lines) |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: potocibi
• Source: potocibi/skills-manager
• License: MIT

Install and usage instructions live in the source repository linked above.