All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 14,948
- 623
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 14,041–14,064 of 14,948 skills
- Aeon Skill EvalsValidate the output of any installed skill against an assertion manifest — word counts, required patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing vs prior runs (NEW_FAIL / NEW_PASS / CHRONIC / STABLE_FAIL). Bootstrap mode generates a starter manifest from a skill's recent successful runs so manifests aren't written speculatively. Triggers: "evaluate this skill's output", "check skill X for regressions", "bootstrap evals for Y", "did this skill ou...Votes: 0GitHub stars: 1,203
- Poteto Modepoteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.Votes: 0GitHub stars: 9,086
- Workflow From ChatsExtract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.Votes: 0GitHub stars: 9,086
- Weekly ReviewProduce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new workVotes: 0GitHub stars: 9,086
- New Branch And PrCreate a fresh branch, complete work, and open a pull requestVotes: 0GitHub stars: 9,086
- Ww AnalyzeDeep analysis workflows for World Weaver memory systems, code, and architectureVotes: 0GitHub stars: 3
- Vllm Ascend Model AdapterAdapt and debug existing or new models for vLLM on Ascend NPU. Implement in /vllm-workspace/vllm and /vllm-workspace/vllm-ascend, validate via direct vllm serve from /workspace, and deliver one signed commit in the current repo.Votes: 0GitHub stars: 5
- Skill ReviewerReview skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo conventions. WHEN: \"review skill\", \"review skill PR\", \"review skill changes\", \"check skill quality\", \"skill PR feedback\".Votes: 0GitHub stars: 253
- Staff Engineer ModePrincipal-engineer operating mode for non-trivial coding (implement, debug, refactor, design, review). Enforces a 5-phase loop — read before write, state contracts, pre-mortem failure modes, small reversible steps (Two Hats), verify end-to-end. Includes 22-item red-flag catalog with restart actions, the 3-strike rule, and paste-able templates per phase. Grounded chapter-by-chapter in 10 canonical books (Pragmatic Programmer, Clean Code, Code Complete, A Philosophy of Software Design, Refactor...Votes: 0GitHub stars: 2
- review-buddyChunked interactive PR review — walks you through PRs chunk by chunk, surfaces existing reviewer feedback, and helps post thoughtful comments without cognitive overload. Use when the user wants to review a pull request, examine PR changes, or post review comments to GitHub. Also trigger when the user mentions a PR number or GitHub PR URL and wants feedback, asks to self-review their own PR, wants a sanity check or quick look at PR changes, needs to resume a paused review session, wants to pos...Votes: 0GitHub stars: 4
- UltraworkDecompose multi-step tasks into parallel sub-agent workloads, route each sub-task to the cheapest capable model tier (Haiku/Sonnet/Opus), run long-running commands in the background, and verify all deliverables before stopping. Use when the user asks to 'go fast', 'parallelize', 'ultrawork', or when a request contains 3+ independent sub-tasks that benefit from concurrent execution.Votes: 0GitHub stars: 28
- RalphSelf-referential loop until task completion with architect verificationVotes: 0GitHub stars: 28
- PlanStrategic planning with optional interview workflowVotes: 0GitHub stars: 28
- PipelineChain agents together in sequential or branching workflows with data passingVotes: 0GitHub stars: 28
- OrchestrateCoordinate multi-agent task execution by delegating to specialist subagents, managing parallel workflows, and verifying completion through architect review. Handles investigation-to-PR cycles, codebase assessment, todo-driven progress tracking, and failure recovery. Use when a task requires breaking work across multiple agents, delegating frontend/backend/research to specialists, or managing a full GitHub issue-to-PR workflow.Votes: 0GitHub stars: 28
- Learn About OmdAnalyze your OMC usage patterns and get personalized recommendationsVotes: 0GitHub stars: 28
- EcomodeToken-efficient parallel execution mode using Haiku and Sonnet agentsVotes: 0GitHub stars: 28
- Code ReviewRun a comprehensive code reviewVotes: 0GitHub stars: 28
- AnalyzeDeep analysis and investigationVotes: 0GitHub stars: 28
- Code ReviewerReview actual code implementations (Python, JavaScript, TypeScript, React) for correctness, maintainability, security hygiene, and adherence to project patterns. Use when reviewing pull requests to ensure code quality, proper error handling, adequate test coverage mapped to acceptance criteria, and alignment with architecture boundaries and review standards.Votes: 0GitHub stars: 37
- Ci Code ReviewerAutomated CI code review for GitHub PRs using OpenAI Codex. Validates PR descriptions, checks implementation alignment, enforces Quest architecture boundaries, and maps test coverage to acceptance criteria when PRs move to ready-for-review.Votes: 0GitHub stars: 37
- Prd WriterWrite PRD, 写产品需求文档。Use when: 需要写新功能 PRD（有UI/无UI）、第三方集成、功能重构、性能/安全优化需求。Votes: 0GitHub stars: 82
- ReviewRead the changeset yourself, review it with one Claude reviewer and one codex reviewer on the same target at once, triage their findings with /triage, and iterate until a round returns no breaking finding. TRIGGER on "review the changes", "code review", on the Review before a changeset is presented to the Architect, and when a /orchestrate or /verify-changes step names it. DO NOT TRIGGER for N identical reviewers on one Task (that is /independent-review).Votes: 0GitHub stars: 22
- Independent ReviewRun N identical parallel Subagents on the same Task for independent Verification. Use when the Architect wants consensus through redundancy — multiple Subagents independently analyze, review, or test the same thing, then the combined returns are triaged with /triage. Invocation /independent-review [count] "task"Votes: 0GitHub stars: 22