메뉴
Use when a user asks to use OpenArc generally, initialize governance, improve repository continuity, audit governance drift, migrate an existing workspace, or choose which OpenArc skill should handle a request.
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
Use when a new goal, feature request, migration, or non-trivial change needs focused clarification before PRD, spec, plan, or implementation work begins.
Use when implementing repository changes through the smallest safe path, from direct routine fixes to risk-driven clarification, specs, plans, task coordination, validation, and documentation updates.
Use when producing a lightweight implementation plan before coding, including scope, affected systems, migration, rollback, tests, reuse, and architecture impact.
Use when auditing repository governance read-only, or when explicitly initializing or repairing governance and patching an agent guide without destructive rewrites.
Use when creating or updating OpenArc feature specs with acceptance criteria, compatibility decisions, and technical direction.
Use when a user proposes changes that may require patch, minor, or major version changes, release notes, changelog updates, or version confirmation.
| name | openarc |
| description | Use when a user asks to use OpenArc generally, initialize governance, improve repository continuity, audit governance drift, migrate an existing workspace, or choose which OpenArc skill should handle a request. |
Use this as the first stop when the user says "use OpenArc" or asks for repository governance without naming a specific skill.
Map the user's request to the narrowest skill:
| User Intent | Use |
|---|---|
| "Set up OpenArc here" | repository-governance, then profile-specific governance skills as needed |
| "What is missing?" / "Audit this repo" | repository-governance in read-only audit mode, then run the scan helper if available |
| "Clarify this request" / "New feature" / "New goal" | clarification-gate, then route to PRD, spec, plan, or implementation |
| "Fix this bug" / routine implementation | Implement directly when scope, constraints, and validation are clear |
| "Write PRD" | product-governance |
| "Write spec" | spec-workflow |
| "Plan implementation" | planning-engine |
| "Define design system" | design-governance |
| "Define brand" | brand-governance |
| "Organize assets" | assets-governance |
| "Migrate existing workspace" | workspace-migration |
| "Version this change" | version-governance |
| "Branch, commit, or PR" | release-workflow; stop after the requested git/PR work |
| "Release or publish" | release-workflow; require an explicit release request and confirmation |
| "Prepare for open source" | open-source-maintenance |
For a new or unfamiliar repository:
repo_profile to separate required, relevant, and optional governance.unknown profile, use only a README and one agent guide as the minimum baseline; report missing files, but create them only when setup is explicitly requested. Do not infer product, design, brand, spec, plan, task, or archive needs from the profile alone.docs/TASKS.md only for work spanning multiple stages, people, or agentsIf this plugin's scripts/openarc.py is available, prefer:
python3 plugins/openarc/scripts/openarc.py scan .
python3 plugins/openarc/scripts/openarc.py doctor plugins/openarc
Use script output as evidence, not as a replacement for judgment.
clarification-gate before PRD, spec, plan, or implementation work only when material product, behavior, compatibility, migration, or risk decisions remain unresolved.docs/specs/* as the canonical spec location and docs/TASKS.md as the canonical active task source.docs/DESIGN.md, docs/BRAND.md, or docs/assets/* for script, CLI, automation, library, or docs-only repositories unless the repo already has UI or brand signals.