Claude skills and agent skills

Soju06Skill

codex-review-loop

Soju06/codex-lb/.agents/skills/codex-review-loop/SKILL.md

Adversarial PR code review using Codex CLI. Codex review (~20-50 min) -> structured findings -> HITL approval -> fix loop.

graphistryReads credentialsSkill

review

graphistry/pygraphistry/.agents/skills/review/SKILL.md

Structured PR review for pygraphistry. Input: PR number/branch (default current branch PR). Output: findings and convergence artifacts under the local task plans directory. Method: multi-wave, evidence-first review across spec, correctness, tests, security, code quality, DRY, concurrency, performance, architecture, operability, and conventions.

Often used withclose-spec·daily-arxiv·design-with-images

SynkraAISkill

coderabbit-review

SynkraAI/aios-core/.claude/skills/coderabbit-review/SKILL.md

Unified CodeRabbit CLI execution via WSL with self-healing loop. Use this skill when running automated code review before commits, PRs, or QA gates. Handles WSL wrapper, severity filtering, and auto-fix iterations.

timeplus-ioSkill

review

timeplus-io/proton/.claude/skills/review/SKILL.md

Review a Proton pull request or diff for correctness, streaming semantics, checkpointing, compatibility, and performance. Make sure to use this skill whenever the user mentions reviewing code, checking changes, PR feedback, or wants an opinion on a diff, even if they just say 'look at this PR' or 'is this change safe'.

Often used withclose-spec·daily-arxiv·design-with-images

samchonSkill

review

samchon/nestia/.agents/skills/review/SKILL.md

Defines exhaustive solo review, Self-Review, and solo repository-wide issue-discovery rounds for nestia. Use for every self-review or unqualified review request and as the default review mode inside issue campaigns. This skill never spawns review agents; use the multi-agent skill only when the user explicitly requests a team, parallel, or multi-agent review.

Often used withclose-spec·daily-arxiv·design-with-images

zereightSkill

review

zereight/gitlab-mcp/.github/skills/review/SKILL.md

Code review with spec compliance and quality checks. Activate when user says: review this, code review, review my changes.

Often used withclose-spec·daily-arxiv·design-with-images

stellarSkill

low-level-code-review

stellar/stellar-core/.claude/skills/low-level-code-review/SKILL.md

reviewing a git diff for small localized coding mistakes that can be fixed without high-level understanding

SentrySkill

review

getsentry/sentry-react-native/.agents/skills/review/SKILL.md

Three-axis review of the branch diff — Standards (this repo's documented standards + public API/bridge surface), Spec (the originating Linear/GitHub issue or PR), and Correctness (runtime bugs + the RN SDK threat model — PII, native crashes/leaks, bridge serialization, arch parity, concurrency). Runs the axes as parallel sub-agents and reports them side by side. Use when reviewing a branch, a PR, or work-in-progress changes before opening or merging, or "review since X".

Often used withclose-spec·daily-arxiv·design-with-images

MaxMiksaReads credentialsSkill

code-review-security

MaxMiksa/Auto-Company/.claude/skills/code-review-security/SKILL.md

Security-focused code review checklist and automated scanning patterns. Use when reviewing pull requests for security issues, auditing authentication/authorization code, checking for OWASP Top 10 vulnerabilities, or validating input sanitization. Covers SQL injection prevention, XSS protection, CSRF tokens, authentication flow review, secrets detection, dependency vulnerability scanning, and secure coding patterns for Python (FastAPI) and React. Does NOT cover deployment security (use docker-best-practices) or incident handling (use incident-response).

Often used withcommunity-led-growth·micro-saas-launcher·ux-audit-rethink

skyllwtReads credentialsSkill

review

skyllwt/OmegaWiki/.claude/skills/review/SKILL.md

General-purpose cross-model review — Review LLM independently reviews any research artifact, outputs structured scores, wiki entity mapping, and improvement suggestions

Often used withclose-spec·daily-arxiv·design-with-images

DenchHQSkill

review

DenchHQ/DenchClaw/skills/gstack/review/SKILL.md

Pre-landing PR review. Analyzes diff for SQL safety, race conditions, LLM trust boundary violations, conditional side effects, and structural issues. Auto-fixes obvious issues, asks about complex ones. Use when reviewing code before merge, or when asked for "code review".

Often used withclose-spec·daily-arxiv·design-with-images

NethermindEthSkill

review

NethermindEth/nethermind/.agents/skills/review/SKILL.md

Deep code review for an Ethereum execution client. Checks consensus correctness, security, robustness, performance, DI patterns, breaking changes, and observability. Use when asked to "review", "check this PR", "look for bugs", "audit", or "review my changes".

Often used withclose-spec·daily-arxiv·design-with-images

GitHubSkill

postgresql-code-review

github/awesome-copilot/skills/postgresql-code-review/SKILL.md

PostgreSQL-specific code review assistant focusing on PostgreSQL best practices, anti-patterns, and unique quality standards. Covers JSONB operations, array usage, custom types, schema design, function optimization, and PostgreSQL-exclusive security features like Row Level Security (RLS).

sodadataSkill

de-review

sodadata/soda-core/.claude/skills/de-review/SKILL.md

Review a PR against this repository's engine review conventions — the invariants that must hold, the checks that matter per kind of change, and the failure shapes agent-written PRs produce here. Use when asked to review a PR or branch, or to self-check before requesting human review.

fabian-hillerSkill

repo-source-code-review

fabian-hiller/valibot/.agents/skills/repo-source-code-review/SKILL.md

Review pull requests and source code changes in /library/src/. Use when reviewing PRs, validating implementation patterns, or checking code quality before merging. Covers code quality checks, type safety, documentation review, test coverage, and common issues to watch for.

YFGaiaSkill

frontend-code-review

YFGaia/dify-plus/.agents/skills/frontend-code-review/SKILL.md

Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, or backend-only code.

Often used withbackend-code-review·frontend-testing·pr-creator

addyosmaniSkill

code-review-and-quality

addyosmani/agent-skills/skills/code-review-and-quality/SKILL.md

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when the diff is pasted inline.

Often used withconstraint-driven-development·observability-and-instrumentation·doubt-driven-development

tombi-tomlSkill

review

tombi-toml/tombi/.claude/skills/review/SKILL.md

tombi の差分レビュー時に correctness / 回帰リスク / 検証不足 / source of truth の整合を優先順位付きで点検する標準フロー

Often used withclose-spec·daily-arxiv·design-with-images

adobeSkill

review

adobe/S3Mock/.agents/skills/review/SKILL.md

Review code changes in pull requests or local diffs for S3Mock. Use when asked to review a PR, inspect changes, or provide structured feedback on correctness, conventions, test quality, and documentation. Outputs findings structured as Must fix / Should fix / Nit.

Often used withclose-spec·daily-arxiv·design-with-images

MuuuunSkill

review

Muuuun/luxas/skills/review/SKILL.md

Write domain-authentic review articles that synthesize rather than stack. Covers 10 scientific domains (physics, chemistry, biology, medicine, mathematics, computer_science, earth_environment, astronomy, economics, materials) with per-domain style guides mined from landmark reviews in RMP / Nat. Rev. X / Annu. Rev. / Chem. Rev. / Bull. AMS / etc. Use this skill when writing a survey / review / report that spans multiple primary papers.

Often used withclose-spec·daily-arxiv·design-with-images