浏览 doodledood 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
69收录技能的仓库 Stars 合计
446仓库 Forks
0平均每个技能的仓库 Stars
6同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Audit code compliance with AGENTS.md project guidelines. Checks adherence to project conventions, naming, patterns, and standards. Read-only analysis. Use before PR. Triggers: review agents.md adherence, check...
Comprehensive code review orchestrator. Runs multiple focused review analyses (bugs, types, maintainability, simplicity, coverage, docs, AGENTS.md) and consolidates findings. Use before PR or after implementati...
Orchestrate fixing issues found by $review. Handles issue discovery, user confirmation, plan creation, and execution via $implement. Triggers: fix review issues, fix findings, address review feedback.
Conduct structured web research with hypothesis tracking. Synthesizes information from multiple sources into actionable findings. Use for technical research, API docs, best practices. Triggers: web research, lo...
Context-gathering for finding files to read. Maps codebase structure, returns overview + prioritized file list with line ranges. Thoroughness: quick for lookups, medium for bugs/features, thorough for multi-are...
Audit code for bugs, logic errors, race conditions, and edge cases. Read-only analysis producing actionable report. Use before PR, after implementation, or when debugging. Triggers: review bugs, find bugs, chec...
Create implementation plans from spec via iterative codebase research and strategic questions. Produces mini-PR plans optimized for iterative development. Use after $spec or when you have clear requirements. Tr...
Audit code for DRY violations, dead code, complexity, and consistency issues. Read-only analysis with actionable recommendations. Use before PR or for code quality review. Triggers: review maintainability, code...
Audit test coverage for code changes. Identifies untested logic and provides specific test recommendations. Read-only analysis. Use before PR or after implementation. Triggers: review coverage, check tests, tes...
Audit code for testability design patterns. Identifies business logic entangled with IO, hard-coded dependencies, and mocking friction. Suggests functional core / imperative shell separation. Read-only analysis...
Execute implementation plans in-place with verification loops. Implements chunks sequentially, runs quality gates, auto-fixes failures. Use after $plan or with inline tasks. Triggers: implement, build, code, ex...
Comprehensive multi-wave web research with strategic source selection. Gathers information from official docs, community resources, and advanced sources. Use for deep technical research, API documentation, best...
Audit code for over-engineering, premature optimization, and cognitive complexity. Identifies unnecessary abstractions, YAGNI violations, and overly complex solutions. Read-only analysis. Triggers: review simpl...
Sync skills from claude-code-plugins vibe-workflow to this codex-workflow repo. Adapts Claude Code features to Codex equivalents. Use when vibe-workflow has updates to sync.
Audit TypeScript/typed code for type safety issues. Identifies any abuse, missing type guards, and opportunities to make invalid states unrepresentable. Read-only. Triggers: review types, type safety, check typ...
Audit documentation accuracy against code changes. Identifies stale docs, incorrect examples, and missing documentation. Read-only analysis. Use before PR or after implementation. Triggers: review docs, check d...
Build requirements specification through structured discovery interview. Use when defining scope, gathering requirements, or specifying WHAT work should accomplish - features, bugs, refactors, infrastructure, m...
Completion marker. Outputs hierarchical execution summary showing Global Invariants respected and all Deliverables completed.
Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.
Fetch claude-code-plugins repo and convert plugins to OpenCode format. Usage: /sync-from-claude-plugins [plugin-names...] (default: all available plugins)
Manifest verification runner. Spawns parallel verifiers for Global Invariants and Acceptance Criteria. Called by /do, not directly by users.
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。