Claude skills and agent skills

imMamdouhaboammarSkill

code-review

imMamdouhaboammar/matts-skills-into-chatgpt/skills/code-review/SKILL.md

Review changed code against repository coding standards and original specification intent. Use when reviewing a branch, diff, PR, pull request, merge-base changes, or verifying code against documented standards — even if the user just says \"review this\". Do NOT use for authoring new code or diagnosing failing runtime bugs.

Often used withclose-spec·add-new-model·compare-screenshots

lilangMaxSkill

code-review

lilangMax/ClaudeCodeGameStudios/.claude/skills/code-review/SKILL.md

Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.

Often used withclose-spec·add-new-model·compare-screenshots

LuisSambranoSkill

code-review

LuisSambrano/antigravity-config/skills/core/code-review/skill.md

Systematic code review and static analysis directive. Validates vulnerability thresholds, architectural patterns, and production reliability via automated CI/CD security constraints.

Often used withclose-spec·add-new-model·compare-screenshots

marblo-appSkill

code-review

marblo-app/marblo/skills/code-review/SKILL.md

Use before merging agent-generated code — review a diff for correctness, security, and simplicity, and report findings ranked by severity.

Often used withclose-spec·add-new-model·compare-screenshots

mateonunezSkill

code-review

mateonunez/skills/skills/engineering/code-review/SKILL.md

Review a diff or PR against my conventions — Result not throw, vertical slices, AItError codes, node:test, Biome, entity normalisation, a11y. Findings are triaged by severity (correctness → conventions → polish), not piled in a flat list. Use when reviewing a diff, reviewing a PR before merge, self-reviewing before opening a PR, or when user says "review this", "review the diff", "code review", or invokes `/code-review`.

Often used withclose-spec·add-new-model·compare-screenshots

mgiovaniSkill

review-code

mgiovani/cc-arsenal/skills/review-code/SKILL.md

Runs one adaptive multi-agent code review of a PR, commit, or the whole codebase. Always covers six core dimensions (correctness, performance, code style, test coverage, error handling, simplicity/over-engineering) plus architecture and design patterns, then adds security, dependency, deep-performance, and UI/motion lanes when the change touches those areas. Critical and Major findings are adversarially verified before the severity-ranked report with file:line findings and fixes goes out in chat. Use when the user wants a thorough review, asks to review a PR or diff, or wants over-engineered code flagged. Analysis only: never edits code, commits, or applies fixes, and posts to GitHub only when explicitly asked. Not for a standalone security audit (use review-security), a standalone dependency audit (use review-deps), a standalone performance investigation (use review-perf), or a standalone UX/design critique (use review-design).

PANYUXIN6Skill

code-review

PANYUXIN6/pyx-skills/code-review/SKILL.md

审查代码和供机器使用的实现产物中的缺陷、风险、质量、正确性、需求或标准问题。用户要求实现审查、发现或审查结论（包括聚焦审查）时使用。排除对散文文档的审查，以及仅要求阅读、解释、总结、绘制地图或追踪实现的请求；单独使用“检查”或“查看”等中性动词不构成审查意图。

Often used withclose-spec·add-new-model·compare-screenshots

paultyngSkill

review-code

paultyng/skill-issue/skills/review-code/SKILL.md

Use when the user asks for a code review, architecture review, Go review, Go best practices review, protobuf review, proto or API design review, SOLID review, design pattern review, package design review, coupling or cohesion review, testability review, "review this code", "is this well designed", "is this idiomatic Go", a gocyclo or staticcheck pass, or a buf lint run. Also use when another skill dispatches a code review.

phatysddevSkill

code-review

phatysddev/skills/.agents/skills/code-review/SKILL.md

Review one implementation change against its Phat task, feature spec, acceptance criteria, repository engineering standards, and any accepted prototype evidence. In standalone or final mode record supported task evidence/status; in delegated mode return a read-only report to the parent. Use after implement-task or when reviewing a working tree, staged change, commit, or branch.

Often used withclose-spec·add-new-model·compare-screenshots

Prat011Skill

code-review

Prat011/nano-claude-code/skills/code-review/SKILL.md

code-review Use this skill when the task is a code review rather than feature implementation. Focus on: - correctness bugs - regressions - missing tests - risky assumptions Return findings first. Keep

Often used withclose-spec·add-new-model·compare-screenshots

QBall-IncSkill

code-review

QBall-Inc/the-bulwark/skills/code-review/SKILL.md

Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.

Often used withclose-spec·add-new-model·compare-screenshots

rexleimoSkill

code-review

rexleimo/rex-skills/code-review/SKILL.md

Automated code review for pull requests and code changes using multi-agent architecture with confidence-based scoring. Use when reviewing PRs, auditing code changes, checking guideline compliance, or detecting bugs in diffs. Works with GitHub, GitLab, and local git repositories. Compatible with Claude Code, Codex, Cursor, Windsurf, and other AI coding tools.

Often used withclose-spec·add-new-model·compare-screenshots

sorafujitaniSkill

review-code

sorafujitani/skills/review-code/SKILL.md

PRベースの多角的コードレビューを実行する。 小規模な差分は直接レビューし、独立した成果物や競合仮説があり調整コストを上回る場合だけ必要な数のsubagentを並列起動する。指摘箇所のコード実在確認・ WebSearchによる公式ドキュメント裏取りでハルシネーションを防止する。 各指摘に前提知識・公式リファレンスURLを付与し教育的なレビューを提供する。 言語・フレームワークを自動検出し、プロジェクト設定+公式ガイドラインに基づくレビューを実施。 以下の場合に使用: (1) PRのコードレビューを依頼されたとき (2) git diffに対するコードレビュー (3) マージ前の品質チェック (4) コードの改善提案が欲しいとき

thechandanbhagatSkill

code-review

thechandanbhagat/claude-skills/skills/code-review/SKILL.md

Perform automated code reviews with best practices, security checks, and refactoring suggestions. Use when reviewing code, checking for vulnerabilities, or analyzing code quality.

Often used withclose-spec·add-new-model·compare-screenshots

tstaplerSkill

code-review

tstapler/dotfiles/.claude/skills/code-review/SKILL.md

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers four practices — receiving feedback with technical rigor, requesting reviews via code-reviewer subagent, verification gates requiring evidence before claims, and security/API-compat awareness. Essential for subagent-driven development, pull requests, and preventing false completion claims.

Often used withclose-spec·add-new-model·compare-screenshots

YepAPISkill

code-review

YepAPI/skills/skills/code-review/SKILL.md

PR review checklist — correctness, security, performance, tests.

Often used withclose-spec·add-new-model·compare-screenshots

NVIDIASkill

code-reviewer

NVIDIA/SkillSpector/tests/fixtures/ssd/ssd_clean/SKILL.md

Reviews code changes and suggests improvements

Often used withgit-doc-updater·shopify-expert·git-precommit

agentpatterns-aiSkill

review-code

agentpatterns-ai/skills/review-code/SKILL.md

Review a source-code diff, PR, or file against canonical review criteria — Fowler code smells with named refactorings, Clean Code / A Philosophy of Software Design red flags, error-handling/resource-safety gaps, testability seams and test smells, security/secrets basics, performance basics, plus concurrency, database/N+1, distributed-systems, API-contract, observability modules — each defect reported as a line-anchored finding with a named fix. Invoke when asked to review code, a diff, or a PR for quality, maintainability, or correctness, or to find code smells and refactoring opportunities in ordinary application source. Skip when the target is a GitHub Actions workflow (use audit-github-actions-security), a SKILL.md (use audit-skill-quality), an agent instruction file (use audit-instruction-file), an agent harness's security/data-flow architecture (use audit-lethal-trifecta) or its LLM-output sinks/install authority (use audit-supply-chain-sinks), or when writing new tests from a spec (use write-tests).

All-The-VibesSkill

code-review

All-The-Vibes/ecorp/.github/skills/code-review/SKILL.md

Review any ECorp pull request against its PR-template merge-readiness rubric, ATV security, Ponytail complexity audit, and Santa verification. Use for automatic Copilot PR reviews, explicit open-PR sweeps, and explicitly authorized TDD remediation with issue-scoped subagents.

Often used withclose-spec·add-new-model·compare-screenshots

conciv-devSkill

code-review

conciv-dev/conciv/.github/skills/code-review/SKILL.md

Review conciv pull requests against this repo's code, SolidJS, styling, testing, and boundary laws.

Often used withclose-spec·add-new-model·compare-screenshots