Skills Manager
Operate the skills-manager CLI — manage a local skill hub (install, import, distribute to agents/projects, update) and backfill provenance for source-less skills (adopt lockfile evidence, search the ecosystem for candidates, verify, get the user's approval, write sources). Use this skill whenever the user mentions skills-manager, the skill home / hub (~/.skills-manager), importing skills from agent runtime directories, distributing or undistributing skills, updating skills from their sources, tagging skills with domain categories (类别 / 分类 / categories), applying / inspecting a category set (类别
Install
npx skills add shenysun/skills-manager --skill skills-managergit clone --depth 1 https://github.com/shenysun/skills-manager.git /tmp/skills-manager
mkdir -p ~/.claude/skills
cp -r /tmp/skills-manager/skills/skills-manager ~/.claude/skills/skills-managerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skills Manager
The user's skills live in a single **hub** (`~/.skills-manager` by default; override with `--home <path>` or `SKILL_HOME`). The hub is the only content authority: `skills/<name>/` directories plus a `registry.yaml` of metadata. Skills flow in two directions — **install/import** into the hub, **distribute** out to agent runtime directories (`~/.claude/skills`, `~/.cursor/skills`, …) as symlinks (user scope) or copies (project scope).
Key vocabulary you will need when reading output:
- **Source**: where a skill came from — `{type: git|local, url, subpath, ref, …}` on the registry entry. A skill with a `url` (+ `subpath`) is **updatable`; without one it is a *snapshot*.
- **Update detection**: the freshness engine behind `update --check` and the dashboard's 可更新 check. GitHub sources compare the skill sub-directory's tree SHA (`source.upstream_tree`) against the GitHub Trees API — one call per repo (shared by all its skills), TTL-cached, through the logged-in `gh` CLI when present (5000 req/h) or anonymous HTTPS otherwise (60 req/h). A row reading **检测失败 / detection failed** means the check did not complete — that is *not* "no update"; every failure appends a JSON line to `<home>/.skills/dashboard.log`.
- **`imported: true`**: how the skill *entered* the hub (via `init`), orthogonal to whether it has a source.
- **Detected agents**: the agent set `npx skills` would target on this machine, resolved locally from the bundled catalog snapshot.Details
- Skill name
skills-manager- Repository
- shenysun/skills-manager
- Path
skills/skills-manager/SKILL.md- License
- MIT
- Repo updated
- 4 November 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Skills Manager skill do?
Operate the skills-manager CLI — manage a local skill hub (install, import, distribute to agents/projects, update) and backfill provenance for source-less skills (adopt lockfile evidence, search the ecosystem for candidates, verify, get the user's approval, write sources). Use this skill whenever the user mentions skills-manager, the skill home / hub (~/.skills-manager), importing skills from agent runtime directories, distributing or undistributing skills, updating skills from their sources, tagging skills with domain categories (类别 / 分类 / categories), applying / inspecting a category set (类别
How do I install the Skills Manager skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add shenysun/skills-manager --skill skills-manager. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Skills Manager popular?
It lives in shenysun/skills-manager, which has 243 GitHub stars and 6 forks, and is included in 1 curated skill list.
Related skills
Team
243shenysun/skills-manager
Run the four-role Herdr team (pm, po, dev, qa panes) that ships one feature of this repo. In the main session the user runs /team as the orchestrator (up, status, go, down); in a role pane the orchestrator prompts /team role: pm|po|dev|qa. Requires HERDR_ENV=1.
AI Agent Builder
581claude-office-skills/skills
Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns
Generate Prompt Request
192agent37-platform/agent37-skills-collection
This skill should be used to generate a "prompt request" one-pager that summarizes the current session for a pull request. It produces one consolidated User block folding together every ask and decision from the session, plus one Assistant block summarizing what was built. Use it when the user asks to "generate a prompt request", recap or summarize the session for a PR, or capture what was requested. Also use it automatically when opening a pull request or writing a PR description, so the PR body includes the asks and decisions behind the change. Works on the current session only and outputs i
Dcf Valuation
581claude-office-skills/skills
Build Discounted Cash Flow (DCF) valuation models. Calculate intrinsic value with customizable assumptions. Generate professional valuation reports.
Ue Project Context
468quodsoler/unreal-engine-skills
Use when creating, refreshing or repairing `.agents/ue-project-context.md`, the project document every other UE skill reads first. Also use when the user says 'project context', 'set up context', 'UE context', 'scan my project', 'onboard the agent to my project', 'update project context', 'configure project', 'what engine version is this project on', 'which plugins do we have enabled', or complains that UE advice keeps coming out generic. For Build.cs and Target.cs mechanics, see ue-module-build-system; for naming and API-macro conventions, see ue-cpp-foundations; for GAS specifics, see ue-gam
Discord Bot
581claude-office-skills/skills
Discord bot development - community management, moderation, notifications, and AI integration
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.