Find the best CLAUDE.md, AGENTS.md and Claude skills

BlockSkill

code-review

block/berd/.agents/skills/code-review/SKILL.md

Senior engineer code review focused on catching issues before they become PR comments. Reviews only changed lines, categorizes issues by priority, and fixes them one by one. Use when the user says "code review", "review my code", "review this branch", or wants pre-PR feedback.

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

PrismML-EngSkill

code-review

PrismML-Eng/llama.cpp/skills/code-review/SKILL.md

Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR. Use when the user wants to review a diff, branch, or PR.

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

bennycodeSkill

code-review

bennycode/trading-signals/.github/skills/code-review/SKILL.md

Repository coding standards for reviewing pull requests. Apply when reviewing TypeScript code.

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

EveryIncSkill

ce-code-review

EveryInc/compound-engineering-plugin/skills/ce-code-review/SKILL.md

Review a named diff or PR for bugs, regressions, tests, and standards. Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally. Use ce-resolve-pr-feedback for feedback already left on a PR.

DeepSeekSkill

dsh-code-review

deepseek-ai/deepseek-harness/.agents/skills/dsh-code-review/SKILL.md

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

Often used withdsh-doc-site-sync·dsh-doc-standards

ClickHouseReads credentialsSkill

codex-review

ClickHouse/ClickHouse/.claude/skills/codex-review/SKILL.md

Run a local pre-push AI code review of the current branch with the OpenAI `codex` CLI, the same way ClickHouse CI does, and optionally iterate fix and re-review until clean. Use when asked to review the current branch before pushing, run "the codex review" / "the AI review" locally, or get an independent second opinion on a diff. Not for reviewing someone else's PR on GitHub (CI already does that).

Often used withaddskill·apply-firmware·astra-fullreview

GoogleSkill

code-reviewer

google-gemini/gemini-cli/.gemini/skills/code-reviewer/SKILL.md

name: code-reviewer description: Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses

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

a16zReads credentialsSkill

ci-code-review

a16z/jolt/.claude/skills/ci-code-review/SKILL.md

Review a Jolt pull request with extreme thoroughness, outside CI, before an authorized account attests a clean review of its exact head: a lead reviewer fans out parallel subagents that hunt bugs and tech debt, and runs checks in a credential-free sandbox. USE FOR: - Reviewing a pull request before attesting it - Posting one review to a PR when a reviewer routine asks for it TRIGGERS: - "review PR", "code review", "review changes" - "diff review", "PR feedback", "check PR" - "analyze diff", "critique code", "review code" - "pull request review", "GitHub PR review"

GitHubSkill

sql-code-review

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

Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code standards, and anti-pattern detection. Complements SQL optimization prompt for complete development coverage.

QuivrHQSkill

review-code-dev

QuivrHQ/quivr/.agents/skills/review-code-dev/SKILL.md

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

go-musicfoxReads credentialsSkill

om-code-review

go-musicfox/go-musicfox/.agents/skills/om-code-review/SKILL.md

Review a diff, branch, or PR against correctness, security, breaking-change, and quality standards — runs the validation gate, applies the built-in checklist plus any repo-local one, and produces severity-ranked findings with an approve/request-changes verdict. The review engine behind om-auto-review-pr and om-review-prs.

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

dataelementSkill

sdd-code-review

dataelement/bisheng/.claude/skills/sdd-code-review/SKILL.md

SDD 第 8 步：Feature 全部任务完成后、合入前的特性级多维度代码审查，对照 spec/design/tasks 按 7 个维度出 PASS / NEEDS_FIX 报告。 用法：/sdd-code-review --base <目标分支>（通常是发版线，如 feat/3.0.0）。 TRIGGER when: 用户运行 /sdd-code-review，或在 SDD feature 合入前要求特性级代码审查。 与 Claude Code 自带的 /code-review（云端多 agent 找缺陷）不是同一个工具。

No other project uses it yet

chaseai-ytSkill

codex-review

chaseai-yt/claudex-loop/skills/codex-review/SKILL.md

Have Codex independently review an existing implementation plan while Claude coordinates a bounded revision loop. For automatic reviewer selection from either host, use claudex-loop with mode=review.

Often used withaddskill·apply-firmware·astra-fullreview

shiwenwenSkill

ha-code-review

shiwenwen/hope-agent/skills/ha-code-review/SKILL.md

Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.

No other project uses it yet

open-gsdSkill

gsd-code-review

open-gsd/gsd-core/skills/gsd-code-review/SKILL.md

Review source files changed during a phase for bugs, security issues, and code quality problems

morethanwordsSkill

codex-review

morethanwords/tweb/.claude/skills/codex-review/SKILL.md

Code review by Codex (GPT) instead of reviewing your own change: hand the change and what it is for to `scripts/codex-review.sh` (Codex at xhigh effort), check every finding against the code, then fix or report it. Review in this session only when Codex is unavailable. Use whenever a code review is asked for — \"сделай ревью\", \"проверь изменения\", \"ревью и поправь\", \"review this\", \"review before committing\" — unless the request names another reviewer.

Often used withaddskill·apply-firmware·astra-fullreview

bmad-code-orgSkill

bmad-code-review

bmad-code-org/BMAD-METHOD/skills/method/bmad-code-review/SKILL.md

Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code"

Often used withbmad-dev-auto·bmad-editorial-review·bmad-checkpoint-preview

expoReads credentialsSkill

deep-code-review

expo/expo/.claude/skills/deep-code-review/SKILL.md

In-depth design-focused code review - understands codebase context before evaluating PR changes, posts structured feedback to GitHub

alibabaSkill

open-code-review

alibaba/open-code-review/skills/open-code-review/SKILL.md

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.