[Workflow] Turn UI-bearing canonical specs into reviewed, interactive multi-view HTML mockups; stop before planned work or production code.
The English summary is being prepared. Showing the original description.
[Utilities] Use when asking what the .claude framework does for THIS project: configuration, skills/agents/workflows, reference docs, key tech/architecture/structure facts. Command keyword search: framework-config --mode=help.
The English summary is being prepared. Showing the original description.
[opencode] Use when running the opencode sync and verify pipeline: opencode.json reconcile, skill policy, hidden-skill commands, hooks bridge, sub-agent mirror, drift check.
The English summary is being prepared. Showing the original description.
[Workflow] Write and verify spec-traced integration tests, or diagnose and fix failing suites to repeatable green. --mode={write|green}.
The English summary is being prepared. Showing the original description.
[Planning] Use when a workflow step or the user asks for adversarial scenarios for failure, data integrity, access, replay and recovery risks before planning.
The English summary is being prepared. Showing the original description.
[Git] Use when asked to create, open, finish, update or mark ready a pull request. Runs in the main session with risk-based test/review choices and automatic checks for routine CI repairs: branch, commit, open PR, CI to green.
The English summary is being prepared. Showing the original description.
[Planning] Use when the user asks to plan work too big for one session whose route is unclear: chart a map of decision tickets, then resolve one ticket per session until the way is clear.
The English summary is being prepared. Showing the original description.
[Design] Use when a workflow step or the user asks for UI creation, exploration or description from briefs, screenshots or videos for product/marketing interfaces. --mode=review checks layout, styling, accessibility and async states.
The English summary is being prepared. Showing the original description.
[Project Management] Use when a workflow step or the user asks for task refinement, story slicing, HTML mockups, draft challenges, artifact review or readiness checks via --mode={refine|story|mockup|challenge|review|dor}.
The English summary is being prepared. Showing the original description.
[Workflow] Turn an idea or existing canonical specs into a reviewed provisional spec or reviewed, readiness-checked, prioritized planned tasks and stories; stop before implementation. --from=idea|spec --to=spec|tasks.
The English summary is being prepared. Showing the original description.
[Research] Use when a workflow step or the user asks for deep analysis of a prior source map: fetch, extract and cross-validate findings into a cited evidence base.
The English summary is being prepared. Showing the original description.
[Workflow] Implement behavior already captured in a canonical spec or test-case set, with scope held, reviewed changes and verified tests. Spec gaps use workflow-feature.
The English summary is being prepared. Showing the original description.
[Project Management] Use for explicit project-owned tracker guidance (--mode=guide), or portable-engine work records, placement, linked concerns, lifecycle, evidence, acceptance and local status. Existing engine modes and bare inspect remain supported.
The English summary is being prepared. Showing the original description.
[Code Quality] Use when a workflow step or the user asks for security audits: OWASP, secrets, supply chain, infrastructure, CI/CD and AI-agent risks.
The English summary is being prepared. Showing the original description.
[Architecture] Use when a workflow step or the user asks for architecture design, compliance review, scalability grading or whole-project audit via --mode={design|review|scalability|full}.
The English summary is being prepared. Showing the original description.
[Documentation] Use when a workflow step or the user asks for documentation sync after code/spec/test changes (--mode=update), or explicit reference-doc initialization and reconciliation (--mode=init).
The English summary is being prepared. Showing the original description.
[Code Quality] Use when a workflow step or the user asks for AI code or plan review: LLM calls, prompts, agents, RAG, evals and guardrails. --mode={code|plan}; --report-only is read-only.
The English summary is being prepared. Showing the original description.
[Decision Support] Use when the user wants a plan, design, decision or idea stress-tested by interview before anything is written or built, or says "grill me".
The English summary is being prepared. Showing the original description.
[Document Processing] Use when converting between Word DOCX and Markdown (GFM, math rendering). --to={markdown|docx}.
The English summary is being prepared. Showing the original description.
[Document Processing] Use when a workflow step or the user asks for HTML page, deck, mockup or animation export to PNG, vector PDF, MP4 or GIF. --to={png|pdf|mp4|gif}.
The English summary is being prepared. Showing the original description.
[Testing] Use when initializing, writing, reviewing or verifying performance/load/soak/capacity tests. --mode=verify --fix-loop (or --mode=green) diagnoses, fixes and remeasures with performance-review. Static bottleneck audits use performance-review.
The English summary is being prepared. Showing the original description.
[Utilities] Use when asking about or configuring the .claude/.codex/.agents/.opencode skills framework: command discovery/help, runtime modes, scoped settings, commit reviews, hooks, workflows or skill visibility. Explains options; changes only requested settings.
The English summary is being prepared. Showing the original description.
[Code Quality] Use when evaluating received review feedback, reviewing named code on request, or verifying a completion claim. Current diffs: changes-review; rationale: why-review.
The English summary is being prepared. Showing the original description.
[Planning] Use ONLY when the user explicitly requests a product roadmap, roadmap update or milestone selection: outcome milestones, MVP scope, non-goals, risks, evidence gates.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)