Run any Skill in Manus with one click

skill-graveyard

Stars7

Forks2

UpdatedMay 7, 2026 at 06:23

Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs locally; reads ~/.claude session JSONL logs. No network calls.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

sfrangulov

sfrangulov/skill-graveyard

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

File ClerksOffice and Administrative Support Occupations·SOC 43-4071

SKILL.md

readonly

name	skill-graveyard
description	Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs locally; reads ~/.claude session JSONL logs. No network calls.
license	MIT
metadata	{"author":"sfrangulov","version":"1.0.0"}

skill-graveyard

CLI that audits Claude Code skill usage. Two signals from one parser:

Dead installs — installed but never invoked → safe to remove.
Hallucinated invocations — invoked but not installed → typos, external-framework registrations, or model tool/skill confusion.

How to invoke

Run via npx skill-graveyard@latest <subcommand> [flags] — no install needed.

Subcommands

audit (default) — classify into active / dead / missing / hallucinated. Flags: --days N, --only <bucket>, --json, --claude-dir <path>.
prune — print removal commands for dead skills. --apply to execute (user/agents only; plugin removals always print only).
suggest — triage hallucinated/missing into actionable buckets.
projects — per-project usage breakdown (cwd from sessions).
cost — token cost estimate of installed metadata vs invocations.
outdated — check installed plugins / git skills for upstream updates (network).

Decision flow

"are there skills I don't use?" → npx skill-graveyard@latest
"clean up unused skills" → prune, then prune --apply
"skill X didn't work" → suggest (look for hallucinated/missing entry)
per-project view → projects
token cost → cost
check updates → outdated

After running, print binary output as-is. Do not summarize unless the user asks.

More from this repository

same repository

mcp-graveyard

sfrangulov/skill-graveyard

Audit which MCP server tools your Claude Code sessions actually invoke. Use when the user wants to find dead MCP servers (configured but never called), hallucinated MCP tool calls, or per-project MCP usage. Triggers on "which MCP servers don't I use?", "clean up MCP config", "remove unused MCP servers", "audit MCP tools". Runs locally; reads ~/.claude session JSONL logs and ~/.claude.json. No network calls.

2026-05-077

memory-graveyard

sfrangulov/skill-graveyard

Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory pointers", "memory hygiene", "unused memory", "memory truncation". Runs locally; reads ~/.claude/projects session JSONL logs and memory directories. No network calls.

2026-05-077

name	skill-graveyard
description	Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs locally; reads ~/.claude session JSONL logs. No network calls.
license	MIT
metadata	{"author":"sfrangulov","version":"1.0.0"}

skill-graveyard

CLI that audits Claude Code skill usage. Two signals from one parser:

Dead installs — installed but never invoked → safe to remove.
Hallucinated invocations — invoked but not installed → typos, external-framework registrations, or model tool/skill confusion.

How to invoke

Run via npx skill-graveyard@latest <subcommand> [flags] — no install needed.

Subcommands

audit (default) — classify into active / dead / missing / hallucinated. Flags: --days N, --only <bucket>, --json, --claude-dir <path>.
prune — print removal commands for dead skills. --apply to execute (user/agents only; plugin removals always print only).
suggest — triage hallucinated/missing into actionable buckets.
projects — per-project usage breakdown (cwd from sessions).
cost — token cost estimate of installed metadata vs invocations.
outdated — check installed plugins / git skills for upstream updates (network).

Decision flow

"are there skills I don't use?" → npx skill-graveyard@latest
"clean up unused skills" → prune, then prune --apply
"skill X didn't work" → suggest (look for hallucinated/missing entry)
per-project view → projects
token cost → cost
check updates → outdated

After running, print binary output as-is. Do not summarize unless the user asks.