菜单
Use when a feature implementation, refactor, or bugfix is complete and code changes need quality review before committing
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。
Use when producing, editing, or reviewing Traditional Chinese technical writing, including comments, documentation, explanations, and Chinese answers that must avoid translationese, casual phrasing, template language, and weak logic.
Audit NixOS impermanence state — find files still on the current filesystem device. Use when the user wants to check for untracked files, audit impermanence, or runs /impermanence-audit.
去除文字中的 AI 生成痕跡。適用於編輯或審閱文字，使其聽起來更自然、更像人類書寫。 基於維基百科的「AI 寫作特徵」綜合指南。偵測並修復以下模式：誇大的象徵意義、 宣傳性語言、以 -ing 結尾的膚淺分析、模糊的歸因、破折號過度使用、三段式法則、 AI 詞彙、否定式排比、過多的連接性短語。
Universal coding standards, best practices, and patterns. Use when developing in any language — triggers on TypeScript, JavaScript, React, Node.js, Python, Nix, ruff, pyright, pytest, uv, flake.nix, justfile, just, recipes, and general code quality topics.
Use when writing git commit messages, reviewing commits, or setting up commit conventions. Triggers on commit, git commit, commit message, changelog, semantic versioning.
A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.
基于 SOC 职业分类
| name | post-implementation-review |
| description | Use when a feature implementation, refactor, or bugfix is complete and code changes need quality review before committing |
Structured quality review for completed code changes. Run BEFORE committing or creating PRs.
Core principle: Simplify -> Verify -> Audit -> Learn.
Announce at start: "I'm using the post-implementation-review skill to review these changes."
When NOT to use:
Dispatch code-simplifier:code-simplifier agent on recently modified production files.
Run the project's verification suite. Must be green before proceeding.
flake.nix exists, wrap all commands with nix develop -c (see coding-standards Nix Dev Shell section)just lint + just test if justfile existsruff format --check + ruff check + pyright + pytesteslint + tsc + jest/vitestInvoke /security-review skill. Read changed files and audit against checklist:
secrets, input validation, SQL injection, auth, XSS, error handling, rate limiting, sensitive data exposure.
Invoke /continuous-learning to extract reusable patterns.
Important: If a learned pattern is a language-specific coding standard (e.g., Python mocking pattern, async best practice), add it to the appropriate coding-standards/references/ file (python.md, typescript.md, or nix.md) — NOT as a standalone learned skill. Standalone learned skills are for cross-cutting patterns (e.g., LangGraph interrupt pattern, SQLAlchemy migration gotcha).
| Step | Tool/Skill | Blocks Next? |
|---|---|---|
| 1. Simplify | code-simplifier:code-simplifier | Yes |
| 2. Verify | just lint + just test | Yes |
| 3. Security | /security-review | No |
| 4. Learn | /continuous-learning | No |
| Mistake | Fix |
|---|---|
| Skipping verification after simplification | Always run lint+test — simplifier can introduce issues |
| Running security review on failing code | Fix lint/test first |
| Simplifying test files | Only simplify production code |
| Saving language-specific patterns as standalone skills | Add to coding-standards references instead |
Comes after: Implementation complete, all original tests passing Comes before: superpowers:finishing-a-development-branch, /commit Pairs with: superpowers:requesting-code-review (complementary)
When committing after review: Invoke /conventional-commits skill for commit message format. For nixpkgs contributions, use nixpkgs-specific format instead (see coding-standards/references/nix.md).