All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,941
- 665
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 13,225–13,248 of 15,941 skills
- Resolve Pr CommentsTriage unresolved PR review comments, produce a severity-ordered fix plan, then resolve or fix each issue with subagents. Use when addressing PR feedback before merge.Votes: 0GitHub stars: 12
- Vertically Sliced Feature ModulesFeature-first module architecture for cohesive ownership, composition, and promotion boundaries. Use when designing, moving, or reviewing feature and package structure.Votes: 0GitHub stars: 12
- Code StyleLanguage-agnostic code-design rules for explicit state, failure, ownership, and I/O boundaries. Use when implementing, refactoring, or reviewing code.Votes: 0GitHub stars: 12
- Pull Request Fix PlanCreate a fix plan from the given code review comments and CI results.Votes: 0GitHub stars: 2
- Code ReviewUse when reviewing a pull request, diff, or branch. Produces severity-ranked findings covering correctness, security, performance, and maintainability, with concrete fixes rather than opinions.Votes: 0GitHub stars: 26
- Context CompressionThis skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.Votes: 0GitHub stars: 17,900
- Go FxUse this skill to build, refactor, or review Go applications using the Uber Fx dependency injection framework. It ensures idiomatic use of Fx for lifecycle management, module-based architecture, and boilerplate reduction.Votes: 0GitHub stars: 24
- Static AnalysisUse static analysis (SAST) to detect defects and nonconformities (MISRA, CERT) early, with triage and traceability appropriate to safety class.Votes: 0GitHub stars: 8
- State MachinesDefine explicit, testable state machines with safe states, controlled transitions, and error handling suited to medical device safety classes.Votes: 0GitHub stars: 8
- Separation Of ConcernsDefine architectural partitioning to contain failures, simplify verification, and align safety classes with appropriate isolation.Votes: 0GitHub stars: 8
- Psychology Permanent Notes> [!definition] **Non-Recurrent Constituent Skill** > A non-recurrent constituent skill is a component of complex cognitive performance that requires adaptation to specific problem contexts, involving reasoning and decision-making rather than automated rule-following. It falls under [[cognitive-architecture]], where it is distinguished from recurrent skills by the variability in its execution across different situations. > [!attention] **Boundary** > This concept excludes skills that are exec...Votes: 0GitHub stars: 6
- Thermo Nuclear Code Quality ReviewRun an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.Votes: 0GitHub stars: 72
- Plan WritingGenerate structured implementation plans with task breakdowns, dependencies, and verification criteria.Votes: 0GitHub stars: 72
- Domain ModelingDomain entity definition, value objects, aggregate boundaries, state transition modeling, and business invariant contracts.Votes: 0GitHub stars: 72
- Pr ReviewReview someone else's GitHub PR - checkout locally, deep read-only review, output copyable findings. Never posts, approves, or merges. Invoke when Josh says things like 'review this PR', 'can you look at Dave's PR', 'take a look at #12', 'review PR 340 for me', 'what do you think of this pull request', 'look over their changes', or drops a PR link and asks for a look. Disambiguation with pr-feedback: authorship decides. A PR authored by someone else belongs here. A PR Josh authored that has r...Votes: 0GitHub stars: 31
- Pr FeedbackAddress review feedback on a PR Josh authored - fetch the review comments, understand them, implement the fixes locally, and resolve the threads it addressed once Josh has reviewed, approved, and pushed. Never posts on his behalf. Invoke when Josh says things like 'we got some feedback on our PR', 'address the review comments', 'the reviewer said X', 'my PR has comments on it', 'can you handle the feedback on #12', 'fix what the review flagged', or mentions someone reviewing a PR of his. Disa...Votes: 0GitHub stars: 31
- Logging Best Practices & ImplementationComplete logging strategy guide covering SLF4J, Log4j2, Logback, Java Util Logging, structured logging, log levels, appenders, configurations, performance optimization, and production-ready patterns.Votes: 0GitHub stars: 3
- Current Technical Specification SkillReusable skill for the Current Technical Specification — the latest approved design only, generated as a projection of Accepted-or-later ADRs, never hand-authored. Also carries the Final Implementation Record. Owned by architect:spec.Votes: 0GitHub stars: 3
- Apache Pulsar Advanced SkillAdvanced knowledge skill for Apache Pulsar messaging. Covers architecture, producers, consumers, subscription types, schemas, error handling, dead letter topics, Spring for Apache Pulsar, and debugging. Used by coding and health inspection agents.Votes: 0GitHub stars: 3
- Engineering StandardsTeam engineering practice — code conventions and readability, git and branching workflow, commit and pull request hygiene, code review standards, architecture decision records, documentation and runbooks, onboarding, developer experience, and managing technical debt deliberately. Use when the user says "code review", "conventions", "code style", "git workflow", "branching", "commit messages", "pull request", "ADR", "documentation", "README", "onboarding", "developer experience", "technical de...Votes: 0GitHub stars: 3
- Github Fix Failed WorkflowFix failed GitHub Actions runs through diagnosis, implementation, and verification, or create and edit .github/workflows/*.yml and *.yaml files. Use for GitHub Actions repair requests, not routine CI status checks.Votes: 0GitHub stars: 3
- Paw SotSociety of Thought (SoT) — multi-perspective deliberative review engine. Orchestrates specialist personas with parallel or debate interaction, confidence-weighted synthesis, and interactive moderator mode. Use for code review, plan review, design analysis, or any scenario requiring diverse expert perspectives.Votes: 0GitHub stars: 39
- Self Improving AgentA universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.Votes: 0GitHub stars: 403
- Self Improving AgentA universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.Votes: 0GitHub stars: 403