Review & quality
19,000 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
MauroProto/mis-skills/external/pbakaus-impeccable/skill Skill
0★ repoUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
The same file is in 4 other repositories
aydincan/turk-hukuku-ve-codex/.agents/skills/kvkk-uyum-checker Skill
0★ repoKVKK uyum tarayıcısı: veri işleme envanteri, aydınlatma ve açık rıza metinleri, saklama-imha politikası, aktarım ve VERBİS kontrolü; uyum boşluğu raporu ve eylem planı çıktısı. Bu beceriyi KVKK Uyum Denetleyicisi alanındaki sorular, olaylar ve belgeler için kullan (KVKK denetim listesi, veri envanteri, aydınlatma metni, açık rıza, saklama imha, veri ihlali, VERBİS, uyum boşluğu). Alan dışı konularda tetiklenme.
Touchdown-Labs/inference-optimization-agent-pack/skills/evidence-review Skill
0★ repoReview inference optimization claims against task success, p95/p99 latency, cost, cache behavior, retries, quality gates, and artifact-backed evidence.
hesprs/harness/skills/review-implementation Skill
0★ repoReview code changes made in a session. Use only when user instructs or other skill references.
aisflows/skill-cleaner/skills/verify-final-map Skill
no license0★ repoUse as step 6 of AIS FLOWS Skill Library Cleaner to verify the cleaned library output and produce FINAL_LIBRARY_MAP.md, FINAL_LIBRARY_MAP.json, and VERIFY_REPORT.md.
shoji9x9/skills/skills/pr-finalize-loop Skill
0★ reposhoji9x9/skills/skills/pr-review-handle Skill
0★ repoDentVega/firebase-agent-skills/skills/firebase-app-check Skill
0★ repoProtects Firebase backends from abuse by attesting that requests come from your real app — Play Integrity (Android), App Attest / DeviceCheck (iOS), reCAPTCHA Enterprise (web). Use whenever the user wants to prevent scraping, quota theft, or unauthorized API access to Firestore, Storage, Cloud Functions, or Realtime Database.
lhenrique42/ai-templates/skills/implement-feature-task Skill
0★ repoImplement a specific feature task by loading required skills, reading PRD and tech spec context, analyzing dependencies, executing code changes with tests, updating task status, and triggering task-reviewer upon completion. Use when asked to implement a task, execute a task, or start work on a specific task number. Do not use for creating tasks, running QA, code review, or bug fixing.
lhenrique42/ai-templates/skills/perform-code-review Skill
0★ repoPerform comprehensive code review by analyzing git diff, verifying conformance with project rules, validating test suites, and checking adherence to technical specs and tasks. Generates a structured code review report with severity-classified findings. Use when asked for code review, code quality validation, or pre-merge verification. Do not use for QA testing, bug fixing, or task implementation.
rauleburro/skills/skills/code-review-4r Skill
no license0★ repoAutonomous, looping code review for a finished PR using the 4R framework (Risk, Readability, Reliability, Resilience). Spawns clean-context agents — an Opus reviewer, an Opus fix-planner, and Sonnet implementers — and iterates review → plan → fix → re-review until the PR is approved, then posts a summary comment on the GitHub PR. Use this whenever the user finishes a PR or branch and says "review my PR", "code review", "revisá la PR", "revisá con 4R", "terminé la PR", "valida este branch antes de merge", or wants automated pre-review that fixes the small stuff so the human reviewer only has to look at what matters. Trigger it even when the user just says they are done with a branch and want it checked before merging.
rauleburro/skills/skills/create-pr Skill
no license0★ repoCreates a GitHub Pull Request after validating that tests, linter, and coverage pass. Pushes the branch, generates an English PR title and description from the commits, and integrates with Jira (links the ticket, updates status). Use this skill when the user says "create PR", "crear PR", "open PR", "push and create PR", "make a pull request", "abre un PR", "sube el PR", "/create-pr", or any variation of wanting to submit their work as a pull request. Also triggers when the user says they're done with a task and want to send it for review. Works with any project stack (Django, Next.js, Node, etc.).
rauleburro/skills/skills/pr-deep-review-agent Skill
no license0★ repoLaunch a clean-context subagent to perform a deep pull request review. Use when the user asks to launch/run/spawn another agent for PR review, final approval review, clean-context code review, or a review that compares code against local documentation and official internet documentation before reporting whether the PR is approved or changes are required.
tyecode/skills/skills/engineering/git-workflow Skill
0★ repoPassive guardrail that enforces Git workflow guidelines. Install globally — the agent applies commit conventions, branch naming, and PR rules automatically without being asked.
tyecode/skills/skills/engineering/secure-commit Skill
0★ repoPre-commit safety check and passive guardrail against sensitive files. Invoke with /secure-commit to scan staged files or audit git history. Install globally to block leaks automatically before every commit.
tyecode/skills/skills/productivity/grill-me Skill
0★ repoInterviews the user about a plan until requirements are fully resolved and shared understanding is reached. Use when user mentions "grill me", requirements are vague, or before starting something significant.
MaybeMonad/skills/skills/unknown-reduction/implementation-plan-review Skill
no license0★ repoImplementation planning workflow focused on the decisions most likely to change before coding starts. Use when the user asks for an implementation plan, plan in HTML, review the plan before implementation, focus on data models, type interfaces, UX flows, architecture choices, validation gates, or wants to reduce rework before touching code.
Agent boundary change reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-boundary-control-review/skills/agent-boundary-change-reviewer Skill
0★ repoUse when a model, prompt, Skill, tool, MCP server, source, egress rule, trace rule, retention rule, approval path, or runtime changes what an agent can see, reach, log, reuse, infer, or do.
Agent egress allowlist reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-boundary-control-review/skills/agent-egress-allowlist-reviewer Skill
0★ repoUse when an agent workflow needs internet access, browser access, package registry access, vendor APIs, webhooks, search tools, MCP servers, or any outbound network destination.
Exception trigger intake reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-escalation-trigger-review/skills/exception-trigger-intake-reviewer Skill
0★ repoUse when an agent exception, failed run, or proposed recovery action needs to be converted into a normalized escalation trigger before the agent continues.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-interruption-budget-review/skills/batch-review-queue-planner Skill
0★ repoUse when agent uncertainty, repeated minor tool errors, low-risk classifications, or non-urgent decisions should be reviewed in a batch instead of interrupting a human immediately.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-interruption-budget-review/skills/review-signal-learning-loop Skill
0★ repoUse when approval, rejection, override, queue, shadow-mode, or reopened-case signals should update the Skill, guardrail, escalation threshold, or review schedule.
Agent capability diff reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-tool-authority-review/skills/agent-capability-diff-reviewer Skill
0★ repoUse when an updated agent, prompt, Skill, connector, tool, memory path, or retrieval path changes what the workflow can do.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-tool-authority-review/skills/github-agent-input-reviewer Skill
0★ repoUse when an agent reads or acts on GitHub issues, pull requests, comments, workflow files, repo rules, code review text, or generated patches.
Self review writeback governor
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/ai-workflow-eval-and-lifecycle-review/skills/self-review-writeback-governor Skill
0★ repoUse when a repeated failure, review note, exception log, or agent self-review proposes changing memory, a Skill, a workflow, or an automation rule.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/ai-workflow-eval-and-lifecycle-review/skills/skill-lifecycle-reviewer Skill
0★ repoUse when a reusable Skill needs create, validate, publish, monitor, update, deprecate, or retire decisions after workflow changes.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/confidence-calibration-review/skills/override-log-reviewer Skill
0★ repoUse when confidence thresholds, autonomy decisions, or review gates need an override log and recalibration trigger before authority changes.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/customer-success-qbr-expansion/skills/qbr-input-safety-check Skill
0★ repoUse when customer health, adoption, usage, support, or expansion material needs data screening before AI-assisted QBR or renewal work.
Authority boundary transfer checker
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/handoff-ownership-transfer-review/skills/authority-boundary-transfer-checker Skill
0★ repoUse when a handoff changes who may act, which tools may run, which data may be read, or which external state may be changed.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/marketing-ops-campaign-qa/skills/campaign-intake-safety-check Skill
0★ repoUse when raw campaign briefs, segment notes, lists, launch tickets, or personalization ideas need screening before AI-assisted campaign QA starts.
Memory proposal intake reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/memory-write-quarantine-review/skills/memory-proposal-intake-reviewer Skill
0★ repoUse when a raw or planned memory write needs source labels, evidence handling, memory type, and quarantine status before it can become durable.
Milestone intake and confirmation check
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/mutual-action-plan/skills/milestone-intake-and-confirmation-check Skill
0★ repoUse when buyer and seller milestones, dates, owners, or dependencies need to be sorted by confirmation status before building a mutual action plan.
Non effect verification planner
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/negative-authorization-test-review/skills/non-effect-verification-planner Skill
0★ repoUse when a denial test must prove that no file, network request, message, memory write, database row, payment, browser state, MCP tool call, or repository state changed.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/outbound-bdr-response-learning/skills/outbound-input-safety-check Skill
0★ repoUse when target lists, account notes, contact snippets, sequence drafts, or reply excerpts need screening before AI-assisted outbound work starts.
Process evidence intake reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/process-evidence-packet/skills/process-evidence-intake-reviewer Skill
0★ repoUse when event-log exports, process-mining summaries, task-mining notes, tickets, CRM exports, worker observations, or workflow notes need safety review before AI-assisted process redesign.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/process-evidence-packet/skills/variant-and-rework-reviewer Skill
0★ repoUse when redacted logs or process notes show alternate paths, waits, loops, reopens, handoffs, exceptions, or compliance deviations that may change the AI workflow design.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/rfp-rfi-response/skills/rfp-intake-safety-check Skill
0★ repoUse when RFP, RFI, questionnaire, attachment, or buyer-provided material needs classification before drafting or source matching.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/rfp-rfi-response/skills/sme-review-packet Skill
0★ repoUse when blocked, sensitive, low-confidence, legal, security, privacy, or product-specific RFP questions need specialist review.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/sales-engineer-proof-of-concept/skills/poc-intake-safety-check Skill
0★ repoUse when raw opportunity notes, buyer goals, data needs, integration asks, or demo requests need screening before AI-assisted POC planning starts.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/sales-to-implementation-handoff/skills/handoff-input-safety-check Skill
0★ repoUse when closed-won context, sales notes, commitments, customer data, or implementation assumptions need screening before handoff planning.
Questionnaire intake safety check
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/security-questionnaire-triage/skills/questionnaire-intake-safety-check Skill
0★ repoUse when security questionnaire material, customer attachments, NDA context, or control details need data and confidentiality screening before drafting.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/shadow-mode-trace-review/skills/human-correction-reviewer Skill
0★ repoUse when proposed shadow actions need comparison against human approvals, rejections, corrections, and rationale.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/skill-maintenance-schedule/skills/review-trigger-scheduler Skill
0★ repoUse when a reusable AI instruction needs calendar review cadence plus event-triggered reviews for model, tool, workflow, policy, incident, owner, or risk-tier changes.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/skill-smoke-test-runner/skills/smoke-run-reviewer Skill
0★ repoUse when Skill, prompt, runbook, or workflow outputs need to be reviewed against the smoke scenarios and expected-output rubric.
Freshness and error state checker
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/tool-result-contract-review/skills/freshness-and-error-state-checker Skill
0★ repoUse when a tool result has observed time, last modified time, expiration, TTL, retry state, environment drift, partial failure, or ambiguous error handling that affects trust.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/tool-result-contract-review/skills/result-review-gate-router Skill
0★ repoUse when a contract needs a continue, revise, block, or escalate decision before an agent summarizes, stores, acts, publishes, deploys, writes, sends, or hands work to another agent.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/tool-result-contract-review/skills/source-and-schema-validator Skill
0★ repoUse when a result needs source-specific provenance, schema validation, required-field checks, and postcondition checks before the workflow relies on the value.
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/workflow-failure-label-review/skills/failure-label-intake-reviewer Skill
0★ repoUse when a failed or risky AI workflow run needs a structured label record before the team updates a Skill, eval, memory item, tool contract, approval gate, or release decision.
Agent resume checkpoint reviewer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/workflow-readiness-review/skills/agent-resume-checkpoint-reviewer Skill
0★ repoUse when a paused, scheduled, interrupted, failed, or checkpointed AI agent may resume from saved state, pending tool calls, approvals, traces, or memory.
Prompt review checkpoint writer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/workflow-readiness-review/skills/prompt-review-checkpoint-writer Skill
0★ repoUse when an AI-generated plan, draft, answer, or recommendation needs a human checkpoint that preserves judgment before the output becomes workflow state.
Structured output review surface mapper
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/workflow-readiness-review/skills/structured-output-review-surface-mapper Skill
0★ repoUse when valid JSON, schema-conforming structured output, function-call arguments, or tool-call payloads need review before the workflow acts on them.
commentary-dev/commentary-skills/plugins/commentary-review/skills/commentary-brainstorm-review Skill
0★ repoUse Commentary Brainstorming Reviews from an agent to monitor multi-user consensus, apply accepted changes to reviewed pages, and mark brainstorming threads addressed. Trigger this skill when a user mentions Commentary brainstorming, consensus review, voting on draft changes, accepted consensus, brainstorm status, brainstorm next, applying agreed changes, or when an agent must choose between a remote MCP-only Commentary review and a local file-backed Commentary review using the CLI.
commentary-dev/commentary-skills/plugins/commentary-review/skills/commentary-draft-review Skill
0★ repoUse Commentary draft reviews from an agent via the Commentary CLI for live collaborative review of Markdown, MDX, HTML, and plain text artifacts. Trigger this skill when a user asks to create, draft, edit, revise, share, or review a blog post, spec, proposal, report, documentation page, or other text artifact with Commentary; when they mention Commentary draft reviews, live comments, watch-comment, review it with commentary, or using an agent and human reviewer together; and when the agent needs to set up authentication, create/sync/watch/share a review, read or wait for comments, reply to comments, resolve threads, manage comments by other reviewers, or decide whether to use the CLI or an already-installed Commentary MCP server.
Commentary live preview review
commentary-dev/commentary-skills/plugins/commentary-review/skills/commentary-live-preview-review Skill
0★ repoSet up and use Commentary Live Preview Reviews for web apps through the Commentary review SDK and MCP. Trigger this skill when a user wants to add @commentary-dev/review-sdk or the Commentary CDN SDK to a React, Next.js, Vite, Vue, Svelte, Angular, Astro, static HTML, or other browser app; launch a localhost or deployed live preview review; listen for Web App Review comments through the Commentary MCP server; address selected-element comments; resolve review threads; handle localhost immediate feedback; or apply deployed-review rules based on review owner, current user, comment author, and agent alias tags.
commentary-dev/commentary-skills/skills/commentary-brainstorm-review Skill
0★ repoUse Commentary Brainstorming Reviews from an agent to monitor multi-user consensus, apply accepted changes to reviewed pages, and mark brainstorming threads addressed. Trigger this skill when a user mentions Commentary brainstorming, consensus review, voting on draft changes, accepted consensus, brainstorm status, brainstorm next, applying agreed changes, or when an agent must choose between a remote MCP-only Commentary review and a local file-backed Commentary review using the CLI.
commentary-dev/commentary-skills/skills/commentary-draft-review Skill
0★ repoUse Commentary draft reviews from an agent via the Commentary CLI for live collaborative review of Markdown, MDX, HTML, and plain text artifacts. Trigger this skill when a user asks to create, draft, edit, revise, share, or review a blog post, spec, proposal, report, documentation page, or other text artifact with Commentary; when they mention Commentary draft reviews, live comments, watch-comment, review it with commentary, or using an agent and human reviewer together; and when the agent needs to set up authentication, create/sync/watch/share a review, read or wait for comments, reply to comments, resolve threads, manage comments by other reviewers, or decide whether to use the CLI or an already-installed Commentary MCP server.
Commentary live preview review
commentary-dev/commentary-skills/skills/commentary-live-preview-review Skill
0★ repoSet up and use Commentary Live Preview Reviews for web apps through the Commentary review SDK and MCP. Trigger this skill when a user wants to add @commentary-dev/review-sdk or the Commentary CDN SDK to a React, Next.js, Vite, Vue, Svelte, Angular, Astro, static HTML, or other browser app; launch a localhost or deployed live preview review; listen for Web App Review comments through the Commentary MCP server; address selected-element comments; resolve review threads; handle localhost immediate feedback; or apply deployed-review rules based on review owner, current user, comment author, and agent alias tags.
specdd/plugin-antigravity/skills/specdd-review Skill
0★ repoUse when Antigravity needs to review changes against active SpecDD specs.
mysteryon88/skills/mina-protocol/skills/mina-o1js-security-review Skill
0★ repoUse when auditing, threat modeling, hardening, or reviewing Mina o1js zkApps, circuits, AccountUpdates, permissions, custom tokens, frontend prover flows, privacy, or deployment security.
honerlaw/agent-marketplace/plugins/minerva/skills/explore Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.