菜单
Orchestrates the full idea-to-ship workflow. Use when the user has a new idea, feature, or project and wants guided step-by-step progress. Triggers on "I have an idea", "let's build", "new feature", "start a project", or when the user wants to follow the complete workflow from concept to code.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | idea |
| description | Orchestrates the full idea-to-ship workflow. Use when the user has a new idea, feature, or project and wants guided step-by-step progress. Triggers on "I have an idea", "let's build", "new feature", "start a project", or when the user wants to follow the complete workflow from concept to code. |
| disable-model-invocation | true |
Leading words: anchor (the idea paragraph), gate (transition criteria), legwork (each step's work).
Pass auto as the first argument to use self-driving grilling mode (auto-selects recommended options without asking).
Step 1: Anchor the idea
Step 2: Grill (interactive or auto)
Step 3: Requirements
Step 4: Prototype (if needed)
Step 5: PRD
Step 6: Types
Step 7: Issues
Step 8: Implement
Resuming: If you've already completed steps, say "I'm at step X" to skip ahead.
Write a one-paragraph description of your idea. This anchor holds the entire workflow together.
Gate: You can state the idea in one paragraph that a non-technical stakeholder would understand.
If auto was passed: Run /grill-with-docs-auto.
Otherwise: Run /grill-with-docs.
Gate: Every major question has been answered or explicitly deferred. You have a CONTEXT.md and at least one ADR. If you're uncertain about domain terms or architectural choices, you're not done.
Next: Say "ready for requirements" when the gate is met.
Run /make-requirements-great in Author mode.
Gate: Requirements pass the 18 characteristics. Open questions are resolved or explicitly deferred with owner assignment.
Next: Say "ready for PRD" when the gate is met.
Can you settle every question in conversation? If yes, skip to Step 5.
If a question needs a runnable answer, run /prototype and use /handoff to bridge context.
Gate: All design questions that needed code answers have been answered.
Next: Say "ready for PRD" when the gate is met.
Run /to-prd.
Gate: PRD is complete with all sections filled. Scope is clear. Success criteria are measurable.
Next: Say "ready for types" when the gate is met.
Run /docs-to-types to build the typed skeleton (domain types, seams, adapters, error families, dependency rules). Does not implement business behavior.
Gate: Typed architecture compiles. Domain types reflect CONTEXT.md glossary. Seams match ADRs.
Next: Say "ready for issues" when the gate is met.
Run /to-issues.
Gate: Every issue is small enough to implement in one session. Acceptance criteria are clear. Dependencies are mapped.
Next: For each issue, start a fresh session and run /implement with the PRD and the single issue.
For each issue:
/implement (drives /tdd internally, closes with /code-review)Gate: All issues are implemented. Tests pass. Code review is clean. PRD is fully delivered.
/to-issues/implement (Step 8) starts fresh, working from the issue/to-issues, use /handoff to continue in a fresh threadSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
Self-driving version of grill-with-docs. Runs an auto-grill loop (auto-selects recommended options without asking) while creating ADRs and glossary entries via domain-modeling as decisions resolve. Use when the user says "auto-grill with docs", "grill and decide with docs", or invokes /grill-with-docs-auto.
Long-running iterative development loops with pacing control and verifiable progress. Uses .scratch/<plan>/ structure where each plan has a PRD.md and issues/. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.