菜单
Report Claude Code skill-usage telemetry — top used, recently active, dormant skills, plus on-disk size. USE WHEN: skill stats, skill usage, dormant skills, which skills do I use, prune skills, skill telemetry, what skills are dormant, most popular skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Security-inspect an AI agent skill (your own or a third party's) with the skillspector CLI, then deliver a plain-English verdict report in chat (safe / caution / do-not-install, threat breakdown, top findings to check, file hotspots). Use whenever you want to vet, scan, audit, or sanity-check a skill before installing or trusting it, point at a skill repo/folder/zip and ask "is this safe?", say "inspect this skill", "scan this skill", "check this skill for malware", "skillspector", or share a GitHub link to a skill/agent and want to know the risk. Also use to re-read confusing skillspector output.
Security-inspect an AI agent skill (your own or a third party's) with the skillspector CLI, then deliver a plain-English verdict report in chat (safe / caution / do-not-install, threat breakdown, top findings to check, file hotspots). Use whenever Ossie wants to vet, scan, audit, or sanity-check a skill before installing or trusting it, points at a skill repo/folder/zip and asks "is this safe?", says "inspect this skill", "scan this skill", "check this skill for malware", "skillspector", or shares a GitHub link to a skill/agent and wants to know the risk. Also use to re-read confusing skillspector output.
Execute GitHub issues one at a time as vertical slices — fetch, branch, TDD, verify, PR, then the next. Use when the user says "ship issue", "resolve
Unified 3D printing pipeline for Bambu Lab printers. USE WHEN user says: print, 3d print, slice, slice this, make me, design a part, model this, STL, 3MF, MakerWorld, browse models, find me a model, printer status, check printer, what's printing, prepare for printing, generate 3MF, fit on one plate, multi-object plate, storage, organizer, mount, holder, bracket, gridfinity, or provides STL files, photos of things to design, or MakerWorld links. Covers design with OpenSCAD MCP, browsing MakerWorld with agent-browser, slicing STL to 3MF with the bundled OrcaSlicer-backed CLI, multi-plate arrangement, and printer control with Bambu MCP. This is the only skill for 3D-printing related work.
USE WHEN: dogfood, QA, exploratory test, find issues, bug hunt, test this app/site/platform, or review the quality of a web application. Systematically explores a web app in a real browser, finds bugs and UX issues, and produces a structured report with full reproduction evidence (step-by-step screenshots, repro GIFs when available, and detailed repro steps) so findings can be handed straight to the responsible team.
USE WHEN: check/audit/update/improve/fix CLAUDE.md or AGENTS.md, CLAUDE.md maintenance, AGENTS.md review, project memory optimization, agent documentation. Audits agent instruction files against modern harness engineering principles (leanness, discoverability, anti-staleness), then applies targeted improvements after approval.
| name | skill-stats |
| description | Report Claude Code skill-usage telemetry — top used, recently active, dormant skills, plus on-disk size. USE WHEN: skill stats, skill usage, dormant skills, which skills do I use, prune skills, skill telemetry, what skills are dormant, most popular skills. |
Aggregates skill-invocation telemetry written by this plugin's bundled PreToolUse hook (${CLAUDE_PLUGIN_ROOT}/scripts/log-skill.ts) and cross-references against the on-disk skill catalog at ~/.claude/skills/ and ~/.claude/plugins/marketplaces/.
Skill tool invocation and appends one JSONL event to the plugin's telemetry file (${CLAUDE_PLUGIN_DATA}/events.jsonl, falling back to ~/.claude/plugins/data/skill-stats/events.jsonl). The hook is non-blocking — any failure exits silently and never interferes with skill execution.First-run note: Right after install, telemetry is empty. Use the plugin for a few days/sessions to accumulate data, then run the report.
Run the underlying script directly:
bun ${CLAUDE_PLUGIN_ROOT}/scripts/report.ts # full text report
bun ${CLAUDE_PLUGIN_ROOT}/scripts/report.ts --json # machine-readable JSON
bun ${CLAUDE_PLUGIN_ROOT}/scripts/report.ts --days=7 # restrict to last N days
bun ${CLAUDE_PLUGIN_ROOT}/scripts/report.ts --stale=14 # custom stale threshold
bun ${CLAUDE_PLUGIN_ROOT}/scripts/report.ts --author=NAME # filter by SKILL.md frontmatter `authors:`
The --author=NAME view reads the authors: field from each SKILL.md frontmatter and lists matching skills with their usage counts, session counts, last-used age, and on-disk size. Dormant authored skills surface with count = 0 for easy pruning decisions.
When invoking this skill in chat, run the JSON form, parse it, and present a clean markdown table with these sections:
codex:rescue show as phantom because they are slash-commands, not standalone SKILL.md files. They are real and used, just stored differently.Snapshots are useful for trend comparison. To save one:
mkdir -p "${CLAUDE_PLUGIN_DATA}/snapshots"
bun ${CLAUDE_PLUGIN_ROOT}/scripts/report.ts --json > "${CLAUDE_PLUGIN_DATA}/snapshots/skill-stats-$(date +%Y%m%d).json"
If ${CLAUDE_PLUGIN_DATA} is not set in your shell, fall back to ~/.claude/plugins/data/skill-stats/snapshots/.
Each line of events.jsonl is a self-contained JSON object:
{"event":"skill_invocation","skill":"deep-dive","session_id":"abc123","timestamp":"2026-05-01T20:00:00.000Z"}
The hook never logs tool inputs, file paths, or user prompts — only the skill name, session ID, and timestamp. Sessions named smoke or test are excluded.