skill-management
Discover, activate, and manage agent skills following the Skill Protocol
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Discover, activate, and manage agent skills following the Skill Protocol
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Create an Architectural Decision Record (ADR) to document a significant design or technology choice
Audit VS Code extensions against the current project stack and recommend keep/add/remove actions
Diagnose and fix a failing CI pipeline or GitHub Actions workflow
Triage a GitHub issue by classifying severity, labelling waste category, proposing next action, and drafting a structured response
Create a new MCP server — clarify purpose, choose transport, scaffold, implement, test, and register
Configure and manage Model Context Protocol servers for external tool access
| name | skill-management |
| description | Discover, activate, and manage agent skills following the Skill Protocol |
| compatibility | >=1.4 |
Skill metadata: version "1.0"; license MIT; tags [skills, workflow, discovery, management]; compatibility ">=1.4"; recommended tools [codebase, editFiles, fetch].
Skills are reusable markdown-based behavioural instructions that teach the agent how to perform a specific workflow. Unlike tools (§11) which are executable scripts, skills are declarative — they shape the agent's approach rather than running code.
Skills follow the Agent Skills open standard. Each skill is a SKILL.md file with minimal YAML frontmatter (name, description) plus a markdown body that includes a Skill metadata note and step-by-step workflow instructions.
Skills are loaded on demand — the agent reads a skill's SKILL.md only when the description field matches the current task context. Do not pre-load all skills.
Task requires a workflow
│
├─ 1. SCAN — check .github/skills/*/SKILL.md descriptions
│ ├─ Match found → READ the full SKILL.md, follow its instructions
│ └─ No match → ↓
│
├─ 2. SEARCH (if enabled by skill search preference setting)
│ ├─ Search official repos (anthropics/skills, github/awesome-copilot) THEN:
│ │ community sources (GitHub search, awesome-agent-skills)
│ │ ├─ Found → evaluate fit, quality-check, adapt, save locally
│ │ └─ Not found → ↓
│
└─ 3. CREATE — author a new skill from scratch
- Save to .github/skills/<kebab-name>/SKILL.md
| Priority | Location | Scope |
|---|---|---|
| 1 (highest) | .github/skills/<name>/SKILL.md | Project — checked into version control |
| 2 | ~/.copilot/skills/<name>/SKILL.md | Personal — shared across all projects for one user |
| 3 | Agent plugins (@agentPlugins) | Plugin — installed via Extensions view (VS Code 1.110+) |
| 4 | Organization-level agents | Org — published at GitHub org level for all members |
Agent file discovery: Use the
chat.agentFilesLocationsVS Code setting to add custom directories for skill/agent discovery beyond the default locations.
Subagents inherit this protocol fully. A subagent may read and follow any project or personal skill. To create a new skill, the subagent must flag the proposal to the parent agent, which confirms before any write to .github/skills/.