Search, install, and manage Agent Skills locally and from GitHub, then help decide whether the task really needs a skill or another customization primitive. Use when looking for skills, installing skills, managing a skill collection, or choosing between a skill, prompt, instruction, or agent.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Full-featured Agent Skills management tool.
Before searching, check whether the ask really calls for a skill rather than a prompt, instruction, agent, or hook. If not, explain that first instead of forcing a skill recommendation.
→ references/customization-routing.md for routing patterns.
| Feature | Description |
|---|---|
| Search | Local index + GitHub API + Web fallback |
| Tags | Filter by category (#azure #bicep) |
| Install | Download to local directory |
| Star | Mark and manage favorites |
| Update | Sync all sources from GitHub |
# Search
python scripts/search_skills.py "pdf"
python scripts/search_skills.py "#azure #development"
# Management
python scripts/search_skills.py --info skill-name
python scripts/search_skills.py --install skill-name
python scripts/search_skills.py --star skill-name
# Index
python scripts/search_skills.py --update
python scripts/search_skills.py --add-source https://github.com/owner/repo
| Command | Description |
|---|---|
<query> | Search skills by keyword |
#tag | Filter by category |
--info SKILL | Show skill details |
--install SKILL | Download skill locally |
--star SKILL | Add to favorites |
--list-starred | Show favorites |
--similar SKILL | Find similar skills |
--update | Update index from sources |
--add-source URL | Add new source repository |
--stats | Show index statistics |
--check | Verify dependencies |
| File | Description |
|---|---|
scripts/search_skills.py | Python script |
scripts/Search-Skills.ps1 | PowerShell script |
references/skill-index.json | Skill index (220+ skills) |
references/starred-skills.json | Your starred skills |
→ references/setup-guide.md for installation
| Tool | Required |
|---|---|
GitHub CLI (gh) | 2.0+ |
| curl | Any |
| Python or PowerShell | One of them |
→ references/agent-instructions.md for complete guide
{N} repos, {M} skills searched (last updated: {date})
| Skill | Description | Source | Trust |
| ----- | ----------- | ------ | ----- |
| ... | ... | ... | ... |
**Next?**
1. Install?
2. Details?
3. Update index? (last: {date})
4. Web search?
| Type | Badge | Description |
|---|---|---|
official | Official | Anthropic / GitHub 公式 |
awesome-list | Curated | キュレーションリスト |
community | Community | コミュニティ製（自己責任） |
Source policy:
github.com, raw.githubusercontent.com, or gist.github.com by default. Any other host needs explicit user approval scoped to the current session.SKILL.md requires, then wait for explicit approval.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.
Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow behavior, and external quality evidence, or safely prune workspace-scoped local chat history by age. Use for session analysis, repeated-task retrospectives, model evaluation, cost/performance analysis, and old session cleanup.
日本語の概要は準備中です。原文の説明を表示しています。
Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels, explicit timing semantics, representative-frame QA, and a static fallback. Use when asked for GIF生成, animated infographic, 動的インフォグラフィック, 結果が流れる図, animated benchmark, or a blog/SNS animation whose displayed metrics must remain traceable to source data.
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.
Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー, アスキーアート, or a decorative header for a script/README.