AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Skill Menu

skill-254095728-bit-agent-skill-menu-skill-menu · by 254095728-bit

Discover, search, understand, organize, and inspect locally installed Agent Skills across Codex, Claude Code, GitHub Copilot, Cursor, Gemini CLI, OpenClaw, and custom roots. Use when the user asks what skills are installed, which skill fits a task, wants relevant skill options from the current conversation, searches by capability or keyword, manages skill favorites or custom tags, checks skill he…

↗ Repository
— No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-254095728-bit-agent-skill-menu-skill-menu

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Skill Menu? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Agent Skill Menu

Help the user discover relevant installed skills without executing them.

Workflow

  1. Infer the user's task, domain, objects, tools, file types, and desired outcome from the current conversation.
  2. Translate or expand those concepts into concise search terms when useful.
  3. Run the bundled CLI with JSON output:
node scripts/skill-menu.mjs search "" --json
  1. Present every relevant result in ranked order. Show only:
  • Skill name
  • One-sentence purpose
  1. Always copy the CLI result into the assistant response in the current Agent conversation. A tool call or terminal result alone is not a user-visible answer.
  2. Do not merely say that results were generated or that a menu was displayed. Include the actual complete result list in the response.
  3. Never show internal numeric scores.
  4. Never invoke, install, remove, move, repair, or modify a recommended skill.
  5. If no task is clear, run list --json and show favorites followed by frequently viewed skills.
  6. If no reliable match exists, say so. Only broaden the search when the user asks.

Commands

Run commands relative to this skill directory:

node scripts/skill-menu.mjs list [--json]
node scripts/skill-menu.mjs search "" [--json] [--broad]
node scripts/skill-menu.mjs show  [--json]
node scripts/skill-menu.mjs favorite add|remove|list [skill-name] [--json]
node scripts/skill-menu.mjs tag add|remove   [--json]
node scripts/skill-menu.mjs tag rename   [--json]
node scripts/skill-menu.mjs tag list [--json]
node scripts/skill-menu.mjs tag export [file]
node scripts/skill-menu.mjs tag import  [--replace]
node scripts/skill-menu.mjs root add|remove|list [path] [--json]
node scripts/skill-menu.mjs doctor [--json] [--report]
node scripts/skill-menu.mjs index rebuild [--json]

Use --root to add one or more roots for a single command.

Presentation

  • Respond in the user's language.
  • Keep the default results compact and scrollable in the Agent interface.
  • Render every returned result in the assistant message as a numbered list. Do not leave results only in tool output.
  • Do not group results unless the user asks for grouping.
  • Explain details, source paths, platforms, dependencies, tags, or health issues only when the user asks about a specific skill.
  • Recommend ordered multi-skill workflows when the task clearly has multiple stages, but do not execute any step.
  • Do not interrupt a skill the user already chose unless they ask for alternatives or the chosen skill cannot fit the task.

Privacy And Safety

  • Do not read Agent conversation histories.
  • Do not send telemetry or make background network requests.
  • Treat original skill directories as read-only.
  • Only write index cache, preferences, custom tags, favorites, and Skill Menu usage statistics under ~/.agent-skill-menu/.
  • Read [references/search-behavior.md](references/search-behavior.md) when explaining ranking, privacy, or supported platforms.

Source & license

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

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

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Developer Tools