agentsclimarketplace

Review & quality

19,016 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Receiving code review

    yigityildiz0/universal-ai-skill-library/skills/archive-variants/receiving-code-review Skill

    no license1★ repo

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires.

  • Using git worktrees

    yigityildiz0/universal-ai-skill-library/skills/archive-variants/using-git-worktrees Skill

    no license1★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists.

  • Accessibility review

    yigityildiz0/universal-ai-skill-library/skills/common/accessibility-review Skill

    no license1★ repo

    Audit a web, mobile, desktop, document, or product flow for practical accessibility issues using current WCAG 2.2 AA-oriented checks, code, screenshots, and interaction evidence. Use for accessibility review, a11y audit, WCAG review, keyboard navigation, screen-reader issues, contrast, or inclusive UX.

  • Behavior preservation checker

    yigityildiz0/universal-ai-skill-library/skills/common/behavior-preservation-checker Skill

    no license1★ repo

    Verify that refactoring preserves existing behavior through before/after comparison, test coverage verification, contract checking, and semantic equivalence.

  • Caveman commit

    yigityildiz0/universal-ai-skill-library/skills/common/caveman-commit Skill

    no license1★ repo

    Draft a terse Conventional Commit message while preserving intent, rationale, breaking-change details, and repository conventions. Use only when the user explicitly invokes $caveman-commit or specifically asks for a Caveman-style commit message. Do not trigger for generic commit or staging requests.

  • Caveman review

    yigityildiz0/universal-ai-skill-library/skills/common/caveman-review Skill

    no license1★ repo

    Produce concise code-review findings with exact locations, evidence, impact, and a concrete fix while retaining necessary rationale for high-risk issues. Use only when the user explicitly invokes $caveman-review or asks for a Caveman-style review. Do not trigger for ordinary review requests.

  • Code commit workflow

    yigityildiz0/universal-ai-skill-library/skills/common/code-commit-workflow Skill

    no license1★ repo

    Implement proper Git commit workflow with conventional commits, atomic changes, and meaningful messages. Use when committing changes, preparing pull.

  • Code review and quality

    yigityildiz0/universal-ai-skill-library/skills/common/code-review-and-quality Skill

    no license1★ repo

    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.

    The same file is in 9 other repositories

  • Code reviewer

    yigityildiz0/universal-ai-skill-library/skills/common/code-reviewer Skill

    no license1★ repo

    Reviews code for bugs, security issues, and quality problems. Use when asked to "review this code", "check my code", "code review", "audit this file", or.

  • Computer health check

    yigityildiz0/universal-ai-skill-library/skills/common/computer-health-check Skill

    no license1★ repo

    Perform a bounded, read-only health check of a Windows, macOS, or Linux computer, covering storage, memory pressure, CPU activity, startup load, battery where available, updates, and obvious errors. Use when asked to check PC health, diagnose a slow computer, inspect disk/RAM/CPU, or summarize system condition; request approval before any cleanup, install, update, or configuration change.

  • Config consistency checker

    yigityildiz0/universal-ai-skill-library/skills/common/config-consistency-checker Skill

    no license1★ repo

    Detects configuration drift and inconsistencies across environments by comparing dev, staging, and production configs, validating schemas, and reporting.

  • Contract reviewer

    yigityildiz0/universal-ai-skill-library/skills/common/contract-reviewer Skill

    no license1★ repo

    Contract-triage skill. Use when Codex should scan a contract for key terms, missing protections, and negotiation priorities.

  • Conventional commit

    yigityildiz0/universal-ai-skill-library/skills/common/conventional-commit Skill

    no license1★ repo

    Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit.

  • Data visualization

    yigityildiz0/universal-ai-skill-library/skills/common/data-visualization Skill

    no license1★ repo

    Design, implement, critique, or validate charts and quantitative visualizations with correct encodings, annotations, accessibility, and source context. Use for chart, graph, data visualization, visualizing metrics, dashboard chart, or figure review.

  • Documentation consistency

    yigityildiz0/universal-ai-skill-library/skills/common/documentation-consistency Skill

    no license1★ repo

    Verify documentation is up-to-date and consistent across all files. Check for broken links, outdated references, deprecated content, and mismatched.

  • Domain contract validator

    yigityildiz0/universal-ai-skill-library/skills/common/domain-contract-validator Skill

    no license1★ repo

    Define and enforce business rule assertions as automated checks using contract testing, schema validation, and invariant verification. Covers API contract.

  • Finishing a development branch

    yigityildiz0/universal-ai-skill-library/skills/common/finishing-a-development-branch Skill

    no license1★ repo

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

    The same file is in 10 other repositories

  • Git bisect assistant

    yigityildiz0/universal-ai-skill-library/skills/common/git-bisect-assistant Skill

    no license1★ repo

    Guide efficient bug-finding with git bisect using binary search across commit history, automated test scripts, skip strategies, and complex history.

  • Git commit

    yigityildiz0/universal-ai-skill-library/skills/common/git-commit Skill

    no license1★ repo

    Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

  • Healthcare providers verify

    yigityildiz0/universal-ai-skill-library/skills/common/healthcare-providers-verify Skill

    no license1★ repo

    Validates practitioner credentials and license status against the NPI registry. Cross-references specialties, credentials, and practice addresses against.

  • Intent based review

    yigityildiz0/universal-ai-skill-library/skills/common/intent-based-review Skill

    no license1★ repo

    Review AI-generated code by verifying acceptance criteria pass/fail status rather than reading implementation line-by-line. Triggers detailed code.

  • Performance review

    yigityildiz0/universal-ai-skill-library/skills/common/performance-review Skill

    no license1★ repo

    Profile performance, detect bottlenecks, analyze resource usage, caching strategies, and boundary conditions. Use when addressing performance issues.

  • Pre commit checklist

    yigityildiz0/universal-ai-skill-library/skills/common/pre-commit-checklist Skill

    no license1★ repo

    Implement automated pre-commit quality checks including linting, formatting, type checking, tests, security scans, and commit message validation. Use when.

  • Product metrics review

    yigityildiz0/universal-ai-skill-library/skills/common/product-metrics-review Skill

    no license1★ repo

    Review product metrics, KPI movement, metric definitions, segmentation, anomalies, and decision implications. Use for metrics review, KPI review, product performance, why a metric changed, north-star metric, funnel review, or product health check.

  • Quality gate definitions

    yigityildiz0/universal-ai-skill-library/skills/common/quality-gate-definitions Skill

    no license1★ repo

    Reusable GO/NO-GO quality gate definitions for multi-phase workflows. Provides predefined gate types, criteria templates, and behavior configuration for.

  • Receiving code review

    yigityildiz0/universal-ai-skill-library/skills/common/receiving-code-review Skill

    no license1★ repo

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

  • Requesting code review

    yigityildiz0/universal-ai-skill-library/skills/common/requesting-code-review Skill

    no license1★ repo

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    The same file is in 11 other repositories

  • Security review

    yigityildiz0/universal-ai-skill-library/skills/common/security-review Skill

    no license1★ repo

    Identify security vulnerabilities across 10 domains including OWASP Top 10, race conditions, supply chain risks, and compliance gaps. Use for security audits, penetration test preparation, vulnerability assessment, or as Phase 3 of comprehensive code review.

  • Subagent driven development

    yigityildiz0/universal-ai-skill-library/skills/common/subagent-driven-development Skill

    no license1★ repo

    Execute an implementation plan through bounded implementer and independent reviewer agents with disjoint write ownership, explicit handoffs, evidence gates, and integration tests. Use when tasks are separable or independent review materially reduces risk; use the current host's native delegation without model/provider switching.

  • Testing review

    yigityildiz0/universal-ai-skill-library/skills/common/testing-review Skill

    no license1★ repo

    Assess test coverage, test quality, testing strategy effectiveness, and identify coverage gaps. Use when evaluating test suites, improving test strategy.

  • Using git worktrees

    yigityildiz0/universal-ai-skill-library/skills/common/using-git-worktrees Skill

    no license1★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

    The same file is in 13 other repositories

  • Vanity engineering review

    yigityildiz0/universal-ai-skill-library/skills/common/vanity-engineering-review Skill

    no license1★ repo

    Reviews codebases, architectures, PRs, and technical plans for vanity engineering — code and systems built for the developer's ego, resume, or intellectual.

  • Vendor review

    yigityildiz0/universal-ai-skill-library/skills/common/vendor-review Skill

    no license1★ repo

    Compare vendors, tools, agencies, platforms, or service providers using requirements, evidence, cost, integration, risk, support, and exit criteria. Use for vendor review, supplier comparison, tool evaluation, buy-versus-build, or procurement brief.

  • Verification before completion

    yigityildiz0/universal-ai-skill-library/skills/common/verification-before-completion Skill

    no license1★ repo

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    The same file is in 40 other repositories

  • Yeet

    yigityildiz0/universal-ai-skill-library/skills/common/yeet Skill

    no license1★ repo

    Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

  • Fde review value

    inbusiness23/fde-skill/skills/fde-review-value Skill

    1★ repo

    Compare a workflow baseline with real test results, calculate whether the solution pays for itself within 30 days, and decide to expand, fix once, stop, or wait. Use after a controlled live test and when transferring ownership to the operating team.

  • Goal ledger status

    jpbaking/goal-ledger/skills/shared/goal-ledger-status Skill

    1★ repo

    Produce a strictly read-only status and handoff report for the current Goal Ledger, including phase progress, next action, blockers, Git strategy, matching Goal-ID commits, branch or baseline inconsistencies, foreign commits, and dirty crash evidence. Use when the user asks for goal status, where the work stands, what remains, or an inter-agent handoff summary. Never modify files, commits, branches, or statuses.

  • Goal ledger

    jpbaking/goal-ledger/skills/shared/goal-ledger Skill

    1★ repo

    Create and execute a durable, git-tracked Goal Ledger for multi-phase or long-running work: .goal-ledger/GOAL.md plus phase-NNNN.md files, plan and execution approval gates, an isolated goal branch recommendation, committed recovery markers, inter-agent handoff state, and optional safe squashing on acceptance. Use when work needs several distinct phases, may span sessions, needs crash recovery or handoff, or the user asks for a persistent goal, execution ledger, or durable plan. Sections 1-3 are the shared contract used by the goal-ledger-resume, goal-ledger-status, and goal-ledger-abandon skills.

  • Scientific literature review

    yigityildiz0/scientific-agent-skills/skills/common/scientific-literature-review Skill

    no license1★ repo

    Produces traceable biomedical and life-science literature searches, evidence maps, narrative reviews, scoping reviews, and systematic-review drafts with verified citations. Use for PubMed/MeSH searches, research-gap analysis, evidence synthesis, citation checking, review protocols, PRISMA-style reporting, or literature sections where primary sources, exact search strings, deduplication, screening criteria, and uncertainty must be preserved.

  • Delegate to codex

    T0mSIlver/skills/delegate-to-codex Skill

    1★ repo

    Call the OpenAI Codex CLI (`codex exec`) non-interactively to get a second opinion, run a code review, or delegate read-only or edit-capable work to an independent Codex run. Use for Codex CLI subagent-style delegation, long-running worker runs, worktree-isolated edits, machine-readable JSONL output, resume flows, and harness gotchas around stdin and sandboxing.

  • Delegate to opencode

    T0mSIlver/skills/delegate-to-opencode Skill

    1★ repo

    Call the opencode CLI (`opencode run`) non-interactively to get a second opinion, run a code review, or delegate read-only or edit-capable work to an independent opencode run. Use for GLM-5.2/opencode harness delegation, primary/all agent configs with edit permissions, worktree-isolated edit workers, JSON event capture, session resume/fork flows, and gotchas around `mode: subagent`, `--auto`, prompt files, and `--dir`.

  • Grill with docs

    M0rtalPhe0nix/dotfiles/.agents/skills/grill-with-docs Skill

    1★ repo

    A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    The same file is in 19 other repositories

  • Setup pre commit

    M0rtalPhe0nix/dotfiles/.agents/skills/setup-pre-commit Skill

    1★ repo

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    The same file is in 19 other repositories

  • Grill feature diagrams

    M0rtalPhe0nix/dotfiles/.claude/skills/grill-feature-diagrams Skill

    1★ repo

    Elicit a feature exhaustively through a rigorous one-question-at-a-time interview, synthesize an approved feature brief, then delegate creation of a detailed portfolio of editable Excalidraw diagrams to a low-cost model. Use when a user wants to explore, define, visualize, or hand off a product or software feature and needs both deep requirements discovery and architecture, workflow, data, state, sequence, rollout, or operational diagrams.

  • Grill me

    M0rtalPhe0nix/dotfiles/.claude/skills/grill-me Skill

    1★ repo

    Interview the user relentlessly to stress-test a plan or design until reaching shared understanding and resolving every material branch of the decision tree. Use when the user asks to be grilled, wants a plan or design interrogated, challenged, pressure-tested, or clarified through a rigorous one-question-at-a-time interview.

  • Review agent

    M0rtalPhe0nix/dotfiles/.claude/skills/review-agent Skill

    1★ repo

    Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.

  • Owner adversarial review

    XHdW/owner-mode/skills/owner-adversarial-review Skill

    1★ repo

    Adversarial review: use when the user invokes $owner-adversarial-review or requests adversarial or multi-agent review; or when current evidence suggests a concrete material failure mechanism, false-pass path, or overlooked alternative in an identifiable direction, assumption, design, implementation, experiment plan, evidence package, or completion claim, with enough consequence to change direction, scope, completion, or a hard-to-reverse decision.

  • Relay10 review

    minwoo19930301/relay10/plugins/relay10/skills/relay10-review Skill

    1★ repo

    Review a fixed change set for specification compliance, correctness, security, regression risk, and evidence quality. Use for code or release review; remain read-only unless the user separately requests fixes.

  • Commit helper

    kero168/skillcheck/fixtures/commit-helper Skill

    1★ repo

    Generates Conventional Commits style commit messages from staged changes. Use when the user asks for a commit message or wants staged diffs summarized.

  • Api review

    San-Z1/skill-doctor/examples/problematic-skills/api-review Skill

    1★ repo

    Use when reviewing API skills for trigger precision and quality.

  • Security review

    nguyenthdat/opencode-manager/registry/skills/security-review Skill

    1★ repo

    Expert code security, correctness, and maintainability review for any language — Rust, TypeScript/JavaScript, Python, Go, C#, Kotlin, C, C++, Swift — used for code audits, PR/diff review, unsafe/native-interop audit, dependency and supply-chain review, or reviewing any module, service, or codebase. Triggered by: security review, audit, code review, PR review, unsafe review, vulnerability scan, dependency audit, crate/package review.

  • Nestjs validation pipes

    dkmqflx/nestjs-best-practices-plugin/plugins/nestjs-best-practices/skills/nestjs-validation-pipes Skill

    1★ repo

    NestJS validation and pipes best practices. Use when validating or transforming request input in NestJS — DTO validation, ValidationPipe, class-validator/class-transformer, or custom pipes. Triggers on ValidationPipe, @IsString/@IsEmail, ParseIntPipe, whitelist, or transform.

    The same file is in 1 other repository

  • Source audit

    metalaihq/trip-event-curator/skills/source-audit Skill

    1★ repo

    Run the pre-output guard over any deliverable in this plugin, now with a source-permission gate: verify ToS/robots verdicts for every source actually used (Luma/Meetup/RA usable per 2026-07-08 measurement, Eventbrite API prohibited, Devpost direct fetching prohibited per its explicit anthropic-ai disallow — substitutions must be stated), plus source-tag coverage on every claim, travel-window intersection on every adopted event, dual-timeline and capture-timestamp presence, travel-worthiness verdicts recorded, honest nulls instead of fabricated prices, PII zero (URL/DOI tokens stripped before phone-pattern checks), secrets zero, and estimate-label integrity with no causal assertions. Use when the user says '검사해줘', '감사 돌려줘', '내보내기 전에 점검', '소스 써도 되는 거야?', 'PII 없지?', or before report-builder publishes any deliverable. Verdict per item; no partial runs.

  • Scientific review writer

    k-telux/SciReviewWriter/skills/scientific-review-writer Skill

    1★ repo

    Evidence-gated workflow for planning, drafting, revising, auditing, and packaging scientific literature reviews, thesis reviews, and paper-style manuscripts from source notes, PDFs, BibTeX, LaTeX, DOCX, figures, or reviewer feedback. Use when the work must be mechanism-first, citation-traceable, visually verified, privacy-safe, and explicit about uncertainty, competing interpretations, and publication readiness.

  • Review changes

    himanshi-28/coding-agent-skills/skills/review-changes Skill

    1★ repo

    Explicit-invocation workflow for evidence-based review of a working tree, branch, commit, or pull-request diff, including prioritized findings, reviewer questions, and truthful review context. Use only when the user directly invokes the review-changes skill.

  • Rework commits

    himanshi-28/coding-agent-skills/skills/rework-commits Skill

    1★ repo

    Explicit-invocation workflow for safely reorganizing completed branch work into small, dependency-ordered, semantic Git commits, proving the rewritten tree matches the original result, and optionally pushing the polished history. Use only when the user directly invokes the rework-commits skill.

  • Fbar threshold check

    zztimur/skills-to-pay-the-bills/plugins/fbar-proof-kit/skills/fbar-threshold-check Skill

    1★ repo

    Check the $10,000 FBAR threshold from foreign account statements. Use for reviewed preflight handoffs, daily ledgers, multi-account aggregation, and year-end FX conversion.

  • Audit permissions

    LeonardSEO/power-platform-skills-codex/plugins/power-pages/skills/audit-permissions Skill

    1★ repo

    Audits existing table permissions on a Power Pages site by analyzing them against site code and Dataverse metadata. Generates an HTML audit report with findings grouped by severity (critical, warning, info, pass) and suggests fixes for issues found. Use when the user wants to review, verify, or check table permissions for security issues.

    The same file is in 1 other repository

  • Security review

    LeonardSEO/power-platform-skills-codex/plugins/power-pages/skills/security-review Skill

    1★ repo

    Runs a guided, end-to-end security review of a Power Pages site and consolidates every finding into one HTML report covering source code and dependencies, the live site, browser headers, firewall, authentication, and role-based permissions. Use when the user wants a full security review, a release-readiness check before publishing, a code-and-config check during development, live site monitoring, or asks open-ended questions like "review my site security", "is my site safe to ship", "do a security check", "monitor my site" — even if they do not name the individual checks.

    The same file is in 1 other repository

  • Test site

    LeonardSEO/power-platform-skills-codex/plugins/power-pages/skills/test-site Skill

    1★ repo

    Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

    The same file is in 1 other repository