菜单
Implement code incrementally with quality gates. Use when the user says 'build', 'implement', or when starting the implementation phase of an approved plan.
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。
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "is this over-engineered", or invokes /prune. Complements correctness-focused review; this one only hunts complexity.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Structured production-incident investigation. Forces evidence-first hypothesis ranking before any code change. Use when given an error message, Sentry alert, failing log, or 'investigate <X>' request.
Fetch and digest Sentry issue data (issue summary, tags, stack trace, breadcrumbs, latest event) by short ID, numeric issue ID, or sentry.io URL. Org-agnostic - works for any Sentry org the local token can access. Use when the user mentions a Sentry issue or short ID (e.g. MY-PROJECT-4X2), pastes a sentry.io issue URL, or asks to investigate/debug a Sentry error.
Create or update a diagram. Picks mermaid vs drawio per rules/diagrams.md, writes the source file, previews via MCP. Use when the user says 'diagram', '/diagram', or asks for a flowchart/architecture/sequence/state diagram.
Create or refresh technical engineering docs in the current repo's /docs/ tree. Diataxis layout, mermaid diagrams, ADR support, drift audit. Use when the user says 'write docs', 'document this', 'audit the docs', or '/document'.
基于 SOC 职业分类
| name | build |
| description | Implement code incrementally with quality gates. Use when the user says 'build', 'implement', or when starting the implementation phase of an approved plan. |
Implement the approved plan incrementally: $ARGUMENTS
Follow these disciplines:
why-not-mechanizable: skill workflow guidance; each step requires understanding the surrounding context (repo, task shape, prior state).
.claude/state/plans/ or the current conversation) (review-time: see section note)(review-time: see section note)(review-time: see section note)rules/agent-routing.md) - their guardrails apply to every increment (review-time: see section note)rules/parallel-agents.md); single-lane plans stay in this session (review-time: lane-vs-single judgment from the plan shape)For each task in the plan:
(review-time: see section note)(review-time: see section note)rules/engineering-principles.md: vertical slicing, change sizing (~100 lines per commit, max 300, split at 1000+), and anti-rationalization rules all apply (review-time: see section note)(review-time: see section note)(review-time: see section note)(review-time: see section note)
/verify-done (typecheck + lint + tests + build) - do not rely on post-edit hooks alone (review-time: see section note)(review-time: see section note)(review-time: see section note)If the feature is large and will take multiple sessions:
(review-time: see section note)(review-time: see section note)(review-time: see section note)After all tasks are done:
/verify-done one final time (review-time: see section note)(review-time: see section note)(review-time: see section note)