Skillmgmnt — AI skill for Claude Code
Read-only observability for AI-agent skills: catalog, load topology across 47+ tools, real usage, governance findings, and a deterministic safety review.
How to install Skillmgmnt
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open hcodestack/skillhub and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Skillmgmnt does
Read-only observability for AI-agent skills: catalog, load topology across 47+ tools, real usage, governance findings, and a deterministic safety review. Also discovers skills served over MCP (SEP-2640) that no filesystem scan can see. English/中文, installable by your own agent.
Alternatives in AI
- Axonhub — ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs 3.2k ★
- Gentle AI — Agent Skills Index — When working on this project, load the relevant skill(s) BEFORE writing any code 1.9k ★
- Lumenx Model Onboarding — LumenX 模型接入与文档更新流程 - 厂商文档抓取、model_catalog 更新、运行时范围判断、端到端验证 1.2k ★
README
Skillmgmnt
**The read-only observability dashboard for your AI-agent skills.** See every skill you own, every tool that loads it, what actually gets used — and what's silently broken.
[](LICENSE) [](https://www.python.org) [](web/) [](AGENTS.md)
**English** · [简体中文](README.zh-CN.md)
Renamed from `hcodestack/skillhub` on 2026-09-18. Old links redirect and nothing needs changing — see the [changelog](CHANGELOG.md) for what kept the old name on purpose, and for the `SKILLHUB_*` environment variables that still work but are deprecated.
Skills (`SKILL.md` folders) are how AI coding tools learn your workflows — and they multiply fast: one library, a dozen tools, symlinks here, copies there, leftovers everywhere. Skillmgmnt answers the four questions nobody can answer by hand anymore:
- What do I have? — a searchable catalog of your whole skills library
- Where is it loaded? — which of 47+ AI tools (Claude Code, Codex, Cursor, Gemini CLI, Copilot, Cline, …) load each skill, globally or per-project, as a symlink or a copy
- Is it used? — invocation events parsed from the tools' own session logs
- What's broken? — broken symlinks, stray copies, drifted duplicates, oversized bodies, descriptions too thin to ever trigger, and a deterministic safety review of what each skill's code actually does
✨ Features
| 🗺 **Load to |
Related Skills
Sourceant
Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP t
Bodyboot
Self-bootstrapping embodiment compiler for physical AI: a coding agent discovers an unfamiliar robot SDK, infe
Pinpoint Apm MCP
Description: Pinpoint APM MCP server — read-only, guardrailed access to Pinpoint traces, metrics, transactions
Skim Master Rules
Skim Master — output governance for AI agents. Nothing load-bearing is only in the middle: the first line alon
LLM Kernel
Rust foundation library for AI-native apps — 16-provider catalog, async LLM client, MCP server, knowledge grap
UX Lint
Deterministic regex-based linter for AI fingerprints. No LLM, no API, no network. CI-friendly — exits non-zero
Related Agents
Gads Placements
Display and YouTube placement safety auditor. Scans every placement that served impressions, classifies agains
Multi Agent Systems Architect Agent
Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — cover
Cloud Manager
Owns cloud architecture across AWS/Azure/GCP — account/subscription/project structure, landing zones, networki