One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
rcelebroneSkillrcelebrone/DotAgents/skills/code-review/SKILL.md
Revisão holística pré-commit (estilo PR Review). Valida o diff contra as 3 memórias vivas, a spec da task e Clean Code, em paralelo ao QA/Security (fan-out); a evidência de teste é exigida no join. Executada pelo Tech Lead; veredito escrito em review.md.
Often used withclose-specadd-new-modelcompare-screenshots
arfar-xSkillarfar-x/agent-skills/skills/code-review/SKILL.md
Reviews a git diff (working-tree changes, a commit range, or an explicitly named PR/branch/file) for correctness bugs and code-quality issues -- wrong conditions, removed invariants, broken call sites, duplicated logic, unnecessary complexity, wasted work, fixes at the wrong depth, and convention violations -- using eight independent review angles, a one-pass verification step per candidate, and a capped, severity-ranked report. Also reviews a remote merge request on a hosted platform (through that platform's own skill, e.g. `glab` for GitLab) and, only when asked, posts the findings back as comments. Use when the user asks to review code, review a PR/MR, review this diff, or check recent changes for bugs before merging.
Often used withclose-specadd-new-modelcompare-screenshots
Microsoft AzureSkillAzure/sap-automation-qa/.github/skills/code-review/SKILL.md
Review pull requests in the SAP Testing Automation Framework. Use when reviewing a diff, a pull request, or staged changes touching platform code, Ansible roles and playbooks, custom modules, or the shell CLI. Reviews for correctness, reliability, security, Azure/SAP domain rules, performance, test coverage, and maintainability — in that priority order. Finds defects that let a validation report success without validating, accept a field and then discard it before it acts, break an object's stated contract, or leave one half of the SUSE/RHEL or HANA topology matrix unhandled.
Often used withclose-specadd-new-modelcompare-screenshots
dkubbSkilldkubb/skills/skills/code-review/SKILL.md
Review diffs, commit ranges, fixup chains, or PRs across languages and report findings ordered by severity. Enforces primitive-obsession and smart-constructor blockers, property-test and boundary-test requirements, complexity thresholds and per-language rules (Rust, TypeScript, Lean, SQL, bash, Ruby, Markdown, regex). Delegates commit-history structure and repair to git-review. Also the home for changing review rules or codifying review feedback.
Often used withclose-specadd-new-modelcompare-screenshots
ferologicsSkillferologics/pi-skills/code-review/SKILL.md
Review a pull request for bugs, style issues, and guideline compliance. Local review - does not post to GitHub.
Often used withclose-specadd-new-modelcompare-screenshots
korallisSkillkorallis/skills-collection/code-review/SKILL.md
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
Often used withclose-specadd-new-modelcompare-screenshots
kudeerliu48-webSkillkudeerliu48-web/CloseCode/skills/code-review/skill.md
系统化审查代码质量，从功能、性能、安全、可维护性等维度找出问题并给出改进建议
Often used withclose-specadd-new-modelcompare-screenshots
WalletConnectSkillWalletConnect/skills/skills/code-review/SKILL.md
Provide actionable feedback on code changes. Focuses on bugs, security issues, and structural problems.
Often used withclose-specadd-new-modelcompare-screenshots
2012geekSkill2012geek/skills/skills/code-review/SKILL.md
Review GitCode pull requests with a self-contained multi-agent prompt pipeline, validate JSON review findings, post or delete GitCode inline comments, and create/update GitCode PR metadata with this skill's scripts.
Often used withclose-specadd-new-modelcompare-screenshots
axiomanticSkillaxiomantic/spellbook/skills/code-review/SKILL.md
Use when the user EXPLICITLY asks for a lightweight pass, or for feedback/audit modes. Triggers: 'quick review', 'light review', 'look over this', '--quick', 'check my work', 'self-review before PR', 'review my code', 'audit this code', 'PR comments to address', 'reviewer said', 'address feedback', 'review PR #X comments'. NOT for: unspecified-scope branch review such as 'review this branch' or 'code review' (that DEFAULTS to advanced-code-review), or PR triage and summarization (use distilling-prs). This skill is the explicit opt-in to a lighter pass; if the user did not ask for lightweight by name, do not use it. Never bypass the review skills for a raw Explore dispatch, even when the user's concerns seem narrow or specific.
Often used withclose-specadd-new-modelcompare-screenshots
henriquecanerSkillhenriquecaner/brain-agent/.agents/skills/code-review/SKILL.md
Perform thorough code reviews. Use when reviewing PRs, auditing code quality, or checking for bugs and anti-patterns.
Often used withclose-specadd-new-modelcompare-screenshots
L-X-TSkillL-X-T/ng-agentic-skills/.agents/skills/code-review/SKILL.md
Code review changed, staged, last-commit, and merge or PR work against requirements and the repository style guide. Use when reviewing current work, staged changes, the last commit, a branch, a merge, or a pull request. For a whole-codebase style audit use ng-review-style-guide instead.
Often used withclose-specadd-new-modelcompare-screenshots
saeedvazirySkillsaeedvaziry/skills/skills/code-review/SKILL.md
Exhaustively review every line in a diff from a fixed point along two independent axes—repository standards and the originating spec—with evidenced findings, explicit coverage, and bounded fix verification.
Often used withclose-specadd-new-modelcompare-screenshots
YassimbaSkillYassimba/loom/skills/code-review/SKILL.md
Review changes since a fixed point along separate Standards and Spec axes. Runs both reviews in parallel sub-agents and reports them side by side. Use for branches, PRs, work-in-progress changes, or "review since X".
Often used withclose-specadd-new-modelcompare-screenshots
aws-solutionsSkillaws-solutions/konductor/skills/code-review/SKILL.md
Use when reviewing a folder, repo, diff or PR, creating or submitting a PR, addressing PR feedback, or reviewing your own changes after implementation. Checks correctness, security and error handling, including in a source tree with no git history. Uses standard git and GitHub CLI (`gh`) commands and classifies findings by severity (CRITICAL/IMPORTANT/SUGGESTION).
Often used withclose-specadd-new-modelcompare-screenshots
iulianditaSkilliuliandita/skills/skills/code-review/SKILL.md
Review a diff, file, or module for bugs, regressions, edge cases, races, and leaks. Use for "review this diff" or "is this change correct". Not security or repo audits.
Often used withclose-specadd-new-modelcompare-screenshots
MicrosoftSkillmicrosoft/amplifier-bundle-skills/skills/code-review/SKILL.md
Review changed code for reuse, quality, and efficiency, then fix any issues found.
Often used withclose-specadd-new-modelcompare-screenshots
Antune-LSkillAntune-L/skillzer/skills/code-review/SKILL.md
Review changed code (session, current branch, or colleague's branch) for principle violations, reinvented wheels, and dead code. Trigger after coding, before merge, or for PR review.
Often used withclose-specadd-new-modelcompare-screenshots
nledfordSkillnledford/engineering-review-board/skills/code-review/SKILL.md
Perform repository-local code reviews. Use for requested diff or pull-request audits, final focused review after implementation, or changes that affect behavior, APIs, domain boundaries, tests, security, workflows, dependencies, CI, documentation, or agent instructions. Do not use as the primary workflow for repository-wide technical-debt portfolio audits, implementation, active failure debugging, or design-only threat modeling.
Often used withclose-specadd-new-modelcompare-screenshots
rshadeReads credentialsSkillrshade/finfocus/.github/skills/code-review/SKILL.md
Pull request review checklist for finfocus. Lists the invariants a reviewer should check that linters and tests do not catch, such as secret redaction, stdout discipline, cache-key completeness, cost-math conventions, plugin module boundaries, MCP exposure, and test isolation.
Often used withclose-specadd-new-modelcompare-screenshots
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
