Claude skills and agent skills

Microsoft AzureSkill

code-review

Azure/typespec-azure/.github/skills/code-review/SKILL.md

Review diffs and pull requests in Azure/typespec-azure for compatibility, .chronus change descriptions, TypeSpec diagnostics and rulesets, SDK emitter and Spector contract regressions, and meaningful tests. Use for Copilot code review in this repository.

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

mzbacSkill

code-review

mzbac/skills/skills/code-review-low/SKILL.md

Lightweight code review for diffs/PRs focusing on high-signal simplifications, code smells, security, performance, and whether new tests are needed; focus on recently modified code unless instructed otherwise.

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

WenWuZhiDaoSkill

code-review

WenWuZhiDao/mattpocock-skills-zh/skills/engineering/code-review/SKILL.md

审查自某个固定基点（commit、分支、tag 或 merge-base）以来的改动，沿两条轴进行——标准（代码是否遵循本仓库记录的编码规范？）和规格（代码是否符合源头工单/规格的要求？）。两项审查在并行子 agent 中运行，并把结果并排报告。当用户想审查一个分支、一个 PR、进行中的改动，或要求「审查自 X 以来」时使用。

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

igmarinSkill

code-review

igmarin/rails-agent-skills/skills/code-review/SKILL.md

Use when reviewing a Rails PR, diff, or merge request. Ground findings in a real file:line. Trigger words: review PR, code review, review my diff, CR.

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

BlockSkill

code-review

block/agent-skills/code-review/SKILL.md

Comprehensive code review checklist for pull requests

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

IsuruMadurangaSkill

code-review

IsuruMaduranga/one-code/skills/code-review/SKILL.md

Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings); with no level given, it follows the session's effort (/effort). Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review.

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

sgaabdu4Skill

code-review

sgaabdu4/building-flutter-apps/.agents/skills/code-review/SKILL.md

Review PR, branch, commit or working-tree changes for concrete defects and fidelity to intended behavior. Also use when explicitly asked to independently challenge a prepared plan, diagnosis or verification claim.

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

szarkansDeletes or force-pushesSkill

code-review

szarkans/multi/skills/code-review/SKILL.md

Code review by several models at once — Claude sub-agents, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report. Reviews whatever is named: a diff, a branch, specific files, one function, a legacy module, a whole repo. Use for any review request, a second or third opinion, a cross-check before a PR, or "code-review", "multi", "consensus review".

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

TakaGotoSkill

code-review

TakaGoto/rag-learning-academy/.claude/skills/code-review/SKILL.md

Get expert feedback on your RAG code

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

rafaelobSkill

code-review

rafaelob/pragmatic-agent-skills/skills/code-review/SKILL.md

Use when asked to review a diff, PR or uncommitted change for correctness and regressions. Not OWASP/authz -> security-review. Not deleting extras -> kill-slop.

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

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

ethosagentSkill

code-review

ethosagent/ethos/skills/software-development/code-review/SKILL.md

Pre-commit gate. Reviews staged or branch-scoped diff for security issues, quality regressions, and adherence to project conventions. Auto-fixes safe items; flags judgment calls. Reads CLAUDE.md / AGENTS.md / DESIGN.md as the convention source.

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

gtrabancoSkill

review-code

gtrabanco/agentic-workflow/skills/review-code/SKILL.md

Internal correctness + simplification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks correctness, error handling, duplication, dead code, and simplification opportunities against the project's own conventions. Findings only; never edits code.

mbeacomSkill

code-review

mbeacom/adrkit/.github/skills/code-review/SKILL.md

Review pull requests in adrkit for actionable defects and conflicts with governing architecture decisions. Use during Copilot code review to inspect changed paths, retrieve relevant ADR context through the adrkit MCP server, and produce evidence-backed inline findings.

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

a16zSkill

ci-code-review

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

Deep code review of a pull request using parallel analysis agents (semantic consistency, bugs, tech debt, security). USE FOR: - Reviewing PRs for bugs, security issues, and code quality - Analyzing new abstractions for consistency and correctness - Identifying tech debt and architectural concerns - Posting review comments to specific lines on GitHub 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"

ConnorGriffinSkill

code-review

ConnorGriffin/skills/skills/tools/code-review/SKILL.md

Review the changes since a fixed point (commit, branch, tag, PR, or merge-base) on two axes — Standards (does it follow this repo's documented rules?) and Spec (does it do what the originating issue asked?). Each axis returns a verdict per enumerated item rather than an open-ended list of findings, so a round terminates. Use when the user wants to review a branch, a PR, working-tree changes, or asks to "review since X"; and again after fixes, to review the fix.

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

LuqueeeSkill

code-review

Luqueee/kivgraph/.claude/skills/code-review/SKILL.md

AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).

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

IntegralistSkill

code-review

Integralist/agent-skills/.agents/skills/code-review/SKILL.md

Review a PR or local changes with risk-based read-only reviewers, verify findings, and check the change against its project's spec and plan. Use when reviewing a remote PR or local code, including unpushed or uncommitted changes. Pass --plan=<path> to name the plan or task list.

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

jasonkneenSkill

code-review

jasonkneen/agent-skills/.claude/skills/code-review/SKILL.md

Code Review Skill ## Purpose Provide consistent, high-signal code reviews by focusing on correctness, clarity, maintainability, security, performance, tests, and developer experience. ## Inputs - PR description and linked issues - Code diffs

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

mhylleSkill

code-review

mhylle/claude-skills-collection/skills/code-review/SKILL.md

Six-dimension code review of a phase's changes: service delegation, framework standards, ADR compliance, plan sync, coding standards and general quality. Returns a binary PASS or NEEDS_CHANGES verdict with every finding classed BLOCKING, RECOMMENDATION or NOTE. Used by implement-phase as its Step 4 quality gate, or manually to review a set of changes against the project's own standards and ADRs. Invoked as devflow:code-review; Claude Code's built-in /code-review is a different, bug-focused review of the current diff. For a hostile multi-persona review use adversarial-reviewer; for security depth use devflow:security-review.

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