Claude skills and agent skills

Galaxy-DawnSkill

code-review-excellence

Galaxy-Dawn/claude-scholar/skills/code-review-excellence/SKILL.md

This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.

Arize-aiSkill

java-code-reviewer

Arize-ai/openinference/.agents/skills/java-code-reviewer/SKILL.md

Review Java OpenInference instrumentation code for correctness and completeness. Use this skill when reviewing a Java instrumentor package — whether it's a new instrumentor, a PR that modifies one, or when the user asks to audit/review/check an existing instrumentor's code quality. Trigger on phrases like "review the instrumentor", "check the Java code", "audit the package", "is this instrumentor correct", or any request to validate an OpenInference Java instrumentation package against project standards.

No other project uses it yet

ag-ui-protocolSkill

agui-dotnet-code-review

ag-ui-protocol/ag-ui/.github/skills/agui-dotnet-code-review/SKILL.md

Review C#/.NET code changes to the AG-UI .NET SDK (sdks/dotnet/) against its specific conventions and architectural rules — AOT serialization, the "no ASP.NET in src/" boundary, the PublicAPI analyzer workflow, wire compatibility with the TypeScript reference, and the house style (sealed/no-records/ConfigureAwait). Runs a phased, rule-by-rule review. USE FOR: reviewing a PR, diff, or branch that touches sdks/dotnet/; checking a new event/message type; verifying serialization, package placement, or public-API changes in the .NET SDK. DO NOT USE FOR: generic C# style nits already enforced by analyzers/EditorConfig; reviewing the TypeScript SDK (sdks/typescript/) or Python SDK (sdks/python/); writing new features (only flag violations, never rewrite code).

No other project uses it yet

udecodeSkill

review-comment

udecode/plate/.agents/skills/review-comment/SKILL.md

Review a Slate PR or a Plate PR based on `main` with Plate v2's research, code and tests from `next`, prove each finding on the PR's head, and draft the GitHub review comment. Use for /review-comment <PR>, a request to draft a review comment on such a PR, or a request for insights from Plate v2's past work on one.

crafter-stationSkill

code-review-excellence

crafter-station/petdex/.agents/skills/code-review-excellence/SKILL.md

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

open-circleSkill

repo-source-code-review

open-circle/formisch/.agents/skills/repo-source-code-review/SKILL.md

Review PRs and source code changes in Formisch packages/ and frameworks/. Use when reviewing pull requests, validating implementation patterns, or checking code quality before merging.

pedrohcgsSkill

review-r

pedrohcgs/claude-code-my-workflow/.agents/skills/review-r/SKILL.md

Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when an R file is touched as part of a paper submission. NOT for running the code — pair with `/audit-reproducibility` for numeric verification.

pedrohcgsSkill

review-r

pedrohcgs/claude-code-my-workflow/.claude/skills/review-r/SKILL.md

Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when an R file is touched as part of a paper submission. NOT for running the code — pair with `/audit-reproducibility` for numeric verification.

denolandSkill

review-pr

denoland/deno/.claude/skills/review-pr/SKILL.md

Review a Deno runtime pull request for correctness, tests, security, and conventions. Use when asked to review a PR or when a PR number/URL is provided for review.

caozhiyuanSkill

copilot-api-code-review

caozhiyuan/copilot-api/.agents/skills/copilot-api-code-review/SKILL.md

Code review guidelines for the copilot-api Bun/TypeScript API gateway. Use when reviewing code changes, pull requests, or uncommitted work in this repository. Defines the review workflow, evidence standards, severity levels, a project-specific checklist (protocol translation, streaming, auth/credentials, proxy/TLS, config/state), verification commands, and the structured CODE_REVIEW_SUMMARY output format. All review output is written in English.

No other project uses it yet

pytorchSkill

pr-review

pytorch/pytorch/.agents/skills/pr-review/SKILL.md

Review PyTorch pull requests for code quality, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

dotnetSkill

sqlclient-code-review

dotnet/SqlClient/.github/skills/sqlclient-code-review/SKILL.md

Review Microsoft.Data.SqlClient pull requests, branch diffs, and local changes for actionable defects. Use for automated PR reviews, drafting or publishing review findings, and follow-up reviews. Summarizes outstanding reviewer feedback before code analysis. Covers driver correctness, behavioral compatibility, TDS, pooling, sync/async paths, resource ownership, tests, and affected build/package surfaces. Prioritizes high-confidence findings over style suggestions.

home-assistantSkill

ha-review

home-assistant/core/.claude/skills/ha-review/SKILL.md

Reviews Home Assistant code changes and provides constructive feedback. Should be used when a review is requested to provide a consistent review behavior and output format. This skill can be used for code reviews in general, not just for GitHub pull requests.

stellarSkill

high-level-code-review

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

reviewing a change for semantic correctness, simplicity, design consistency, and completeness

rtk-aiSkill

pr-review

rtk-ai/rtk/.claude/skills/pr-review/SKILL.md

Batch review des PRs RTK par ordre de complexité croissante (XS → S → M → L). Pour chaque PR : vérifie l'état (conflits, CLA, reviews), lit le diff complet, analyse le code en contexte, présente un résumé avec lien + taille + recommandation. Attend validation explicite avant tout merge. Poste des commentaires boldguy-adapt sur les PRs bloquées (conflit, CLA, CHANGES_REQUESTED). Args: "triage" pour lancer un triage complet avant la review. "from:<num>" pour reprendre à partir d'un numéro de PR spécifique.

NVIDIASkill

review-cudf

NVIDIA/cudf/.agents/skills/review-cudf/SKILL.md

Use this skill to review GitHub pull requests for cudf

AnthropicSkill

review-contract

anthropics/knowledge-work-plugins/legal/skills/review-contract/SKILL.md

Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis. Use when reviewing vendor or customer agreements, when you need clause-by-clause analysis against standard positions, or when preparing a negotiation strategy with prioritized redlines and fallback positions.

AnthropicSkill

contract-review

anthropics/knowledge-work-plugins/small-business/skills/contract-review/SKILL.md

Lightweight NDA, MSA, and vendor contract review for SMBs without legal on staff. Reads contracts from local files, mail attachments (Gmail or M365), a connected file store (Google Drive or M365), or DocuSign envelopes; flags non-standard terms; explains risks in plain English; and outputs a marked-up redline as a separate DOCX. Use when the user says "review this contract," "what am I signing," "red flags," "flag any concerns," "check the payment terms," or uploads/forwards a contract or legal agreement.

handsontableSkill

handsontable-code-review

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

Use when reviewing changed or staged code, a branch, or a PR in the Handsontable monorepo across architecture, code quality, performance, accessibility, and tests. Covers SOLID / Law of Demeter / plugin decoupling / breaking-changes policy, custom ESLint rules / JSDoc / naming / cognitive complexity, large-array and render-batching performance, WCAG 2.2 AA + keyboard navigation, and the tests a change ships (a named exercising test per new path, scoped mutation, a ticket on every weakened assertion). Trigger when asked to review changes, check a diff against Handsontable conventions, assess architectural correctness, spot performance regressions, verify accessibility, or judge whether a change's tests prove it, and as the design lens before or while implementing any core change.

sanity-ioSkill

code-review-and-quality

sanity-io/sanity/.agents/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.

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