菜单
Implement a feature from a PRD. Activated when the user asks to implement, build, or construct from a product document.
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。
基于 SOC 职业分类
Legacy code archaeology — multi-phase discovery that reads the codebase, git history, and optionally Jira to reconstruct WHY code exists. Produces discovery notes, ADR candidates, and PRD candidates for human review. Activated when user says 'descobrir módulo', 'arqueologia de código', 'entender legado', 'contexto do módulo', 'por que esse código', 'legacy context', '/discover', or when starting work on an unfamiliar legacy module.
Legacy code archaeology and context bootstrap. Activated when the user mentions "legacy code", "código legado", "sistema antigo", "código sem documentação", "discover module", "entender módulo", "arqueologia de código", "código que ninguém entende", or runs /discover. Populates the empty upper layers of tiered lookup (memory and docs) before context-engineering techniques can be effective. Read-only for source code: outputs discovery notes, ADR candidates, and suggested intent markers. Remote discovery supports GitHub (via gh CLI) and Azure DevOps (via az CLI plus REST).
Context engineering — proactive context window management. Activated when working on large tasks, long sessions, multi-file changes, or when context is getting bloated. Keywords: "context", "too much code", "split this task", "focus", "scope down", "token budget", "keep it small". Complements the reactive context-guard hook with proactive techniques.
Reconcile a Claude Design handoff bundle (PROMPT.md) with the project's PRD and conventions. Activated when the PRD references a Claude Design handoff, when a PROMPT.md exists in docs/design/, or when the user mentions "Claude Design", "design handoff", or "PROMPT.md".
Pattern learner. Activated when the user says "learn from this", "what patterns", "improve skills", "retrospective", "session review", or wants to extract reusable patterns from recent work to improve the project's skills and conventions.
Long-term memory via vector DB. Activated when the user asks about past decisions, previous solutions, project history, "how did we do X", "last time", "we already solved", or when the agent needs historical context before planning an implementation.
| name | implement-prd |
| description | Implement a feature from a PRD. Activated when the user asks to implement, build, or construct from a product document. |
| allowed tools | Read, Write, Edit, Grep, Glob, Bash |
docs/product/docs/architecture/docs/specs/ (design, compliance, etc.).claude/skills/frontend-agent/SKILL.md → load design tokens from docs/specs/design-system/README.md → scan existing components → generate UI from tokens + component library + PRD requirementsCLAUDE.md conventions.claude/skills/testing/SKILL.mdCheck the PRD for these patterns to determine the flow:
figma.com URL or ## Design section with link → Figma flow## Design with "see design-system tokens" or no link → Agent flow| Racionalização | Realidade |
|---|---|
| "O código tá simples, não precisa de testes" | Código simples hoje vira complexo amanhã. Testes documentam intenção. |
| "Já sei o que o PRD quer, não preciso ler tudo" | PRDs têm restrições e edge cases nas entrelinhas. Leia completo. |
| "Esse ADR não se aplica aqui" | Se o ADR existe, alguém já enfrentou esse problema. Verifique antes de ignorar. |
| "Vou commitar tudo junto, é mais rápido" | Commits atômicos permitem revert cirúrgico. Commit grande = revert impossível. |
| "Design tokens são exagero pra esse componente" | Hardcode hoje, inconsistência amanhã. Sempre use tokens. |
src/ sem atualizar docs/