Reference note for the Claude Code adapter surface; the active Claude bootstrap now lives in `/.claude-plugin`, `/hooks`, and the repository `skills/` directory.
PR 변경 내용을 분석하여 .claude/context/ 문서를 자동 생성하는 규칙
Cross-platform persistent memory for coding agents. Provides session continuity, progressive retrieval, and unified memory across Claude Code, Codex, OpenCode, and Cursor.
Use when preparing Claude Code prompts or workflows that should leverage the CMC CLI skill.
Join AgentTavern from the current AI runtime. Use when the user gives a `/join/<token>` room invite URL or a private assistant invite URL and wants the current thread attached to AgentTavern. Works with Codex, Claude Code, and OpenCode.
Integrate AI capabilities like LLM calls, RAG pipelines, and prompt engineering. Use this skill when an AI-powered feature needs to be built or refined.
Configure claude-cast settings including API keys, default layout, volume, and pane width.
Multi-LLM peer review — send plans, ideas, or code to GPT (via OpenAI Codex CLI) and Gemini (via Gemini CLI) for structured peer review with cross-examination, then cherry-pick feedback. Decision Packet v2 with tiered output (Ship Blocker / Before Next Sprint / Backlog), dependency arrows, effort estimates, conflict flags, and JSON export. Tie-breaker model resolves HIGH CONFIDENCE deadlocks. Supports review, idea, redteam, debate, premortem, advocate, refactor, deploy, api, perf, diff, quick, help, and history modes. Supports parallel multi-mode dispatch (--modes redteam,deploy,perf) with collision detection. Use this skill whenever the user wants a second opinion from other AI models, wants to brainstorm with multiple perspectives, needs adversarial analysis, wants to stress-test a plan, review a code diff, get deployment readiness feedback, API design review, performance analysis, or mentions peer review, brainstorm, or multi-LLM feedback. Supports --rounds N, --verbose, --quiet, --gpt-model, --gemini-model, --steelman, --iterate, --json, and --modes flags. Falls back to GitHub Copilot CLI if Codex CLI is unavailable.
Demo skill showing Claude Code compatible SKILL.md format
Use when investigating Claude CLI protocol behavior — stream-json event mismatches, permission handling, control_request/response fields, or any question about what the CLI actually does internally. Covers live event debugging, JSONL history comparison, and binary reverse-engineering.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
