review-maintainability
Audit code for DRY violations, dead code, complexity, and consistency issues.
发现 文档写作 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Audit code for DRY violations, dead code, complexity, and consistency issues.
Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.
Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.
Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from a session, or review workflow effectiveness.
Audit TypeScript code for type safety issues—any/unknown abuse, invalid states, missing narrowing.
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
Audit code for logical bugs, race conditions, edge cases, and error handling issues.
Update main/master from origin, rebase current branch on it, resolve conflicts, and push.
Create a comprehensive SEO_STRATEGY.md covering both traditional SEO and Generative Engine Optimization (GEO) for AI platforms. Requires CUSTOMER.md to exist first. Includes platform-specific tactics for Google...
Manifest builder with verification criteria. Converts known requirements into Deliverables + Invariants. Use when you need done criteria, acceptance tests, quality gates—not for requirements discovery. Outputs...
Audit code for testability design patterns. Identifies business logic entangled with IO and suggests functional core / imperative shell separation.
Deep code analysis using consultant agent. Identifies technical debt, risks, and improvement opportunities.
Create implementation plans from spec via iterative codebase research and strategic questions. Produces mini-PR plans optimized for iterative development.
Research external topics via web search with structured hypothesis tracking and source evaluation.
Requirements discovery through structured interview. Use when WHAT is unclear—scope needs definition, requirements need gathering, or starting from scratch. Outputs spec document, not executable manifest.
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.
Verify code changes comply with CLAUDE.md instructions and project standards.
Audit documentation accuracy against code changes. Reports discrepancies without modifying files.
Executes implementation plans via subagents with automated verification and fix loops. Use after /plan for complex features. Each chunk gets dedicated Implementor + Verifier agents with up to 5 fix attempts.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven...
This skill should be used when the user asks to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", "SKILL.md format", "skill frontmatter", "sk...
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command w...
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomou...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。