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

  • Aos review

    riz007/architect-os/skills/aos-review Skill

    1★ repo

    Reviews code against ArchitectOS standards — architecture layering, type safety, security, testing, performance, API design, and naming. Reports FAIL/WARN/PASS with file references and concrete fixes. Use when user asks to review code, check standards compliance, review a PR, or says "does this follow ArchitectOS".

  • Aos vuetify

    riz007/architect-os/skills/aos-vuetify Skill

    1★ repo

    Reviews Vuetify 3 + Vue 3 code for correct component usage, Material Design 3 patterns, form validation, theme customisation, and performance. Reports FAIL/WARN/PASS. Use when user asks to review Vuetify components, build Vuetify UI, or says "check my Vuetify code".

  • Architecture review

    hiteshbandhu/skills-i-use/skills/architecture-review Skill

    1★ repo

    Run a structured architecture decision process using subagent personas that debate the decision, then produce a signed ADR (markdown + optional HTML) and update a decision registry. Triggers on "should I use X or Y", "architecture decision", "ADR", "help me decide between", "which approach", "debate this", "tech decision". Use whenever the user is making a technical or architectural choice and needs structured thinking, not just a list of tradeoffs.

  • Cto weekly review

    hiteshbandhu/skills-i-use/skills/cto-weekly-review Skill

    1★ repo

    Generate a deep CTO self-review report: working hours, productivity patterns, focus sessions, AI collaboration depth, cognitive load signals, sustainability health, and codebase velocity — not just commit counts. Triggers on "weekly review", "CTO report", "week summary", "what did I build", "productivity report", "show me my week", "engineer report", "weekly digest". Scans git across repos, AI agent session logs, shell history, file timestamps, and produces markdown + HTML reports. Always trigger this skill for any weekly or periodic review of engineering or product work.

  • Raise pr

    hiteshbandhu/skills-i-use/skills/raise-pr Skill

    1★ repo

    Take a ready change from working tree to merged PR — branch, commit, push, open PR with a body drafted from the diff, watch CI, and squash-merge when green. General and portable: follows each repo's own commit/branch convention rather than imposing one. Never commits, pushes, or merges without explicit confirmation. Triggers on "raise a PR", "open a PR", "pr this", "push and pr", "ship this PR", "merge when green", "commit and open a pr".

  • Ship check

    hiteshbandhu/skills-i-use/skills/ship-check Skill

    1★ repo

    Pre-ship gate before commit or push — runs lint, typecheck, tests, build, secret scan, and git diff review, then outputs a READY/BLOCKED verdict with a proposed commit message. Never commits without explicit user confirmation. Triggers on "ship check", "ready to commit", "pre-push check", "commit and push", "ship this", "can I push".

  • Skill reviewer

    zrosenbauer/skills/skills/skill-reviewer Skill

    1★ repo

    This skill should be used when the user wants to review, audit, or sanity-check an existing agent skill in this repo against authoring conventions. Common triggers include "review the X skill", "audit this skill", "check skill X against repo conventions", "is this skill any good", "second opinion on skill X", "sanity check skill X", and "review skill X before publishing". Produces a severity-tiered report (error / warn / info) with a Clean section even on pass, and classifies the skill type. Skip when authoring a brand-new skill (use skill-creator) or running general code review (use code-reviewer).

  • Cyborg check

    mattdweigand-sketch/agent-skills/skills/cyborg-check Skill

    1★ repo

    Audit whether a judgment-encoding system closes the loop between captured patterns and real outcomes, or is becoming an org-scale cyborg that spreads unverified judgment at machine speed. Trigger on "/cyborg-check", "cyborg check", "does this close the outcome loop", "is this just captured judgment", "capture without grading", "judgment audit", "are these patterns verified", or when assessing an AI/agentic system, eval pipeline, scoring engine, recommendation system, sales-intelligence system, or internal "best practice" tool. Do not use for ordinary grading, document review, rubric scoring, or software with no judgment loop.

  • Quality check eval

    mattdweigand-sketch/agent-skills/skills/quality-check-eval Skill

    1★ repo

    Sort AI output quality checks into four buckets: automate in code, judge with an LLM, keep for human review, or remove. Use when reviews are too manual, evals are vague, a workflow needs clearer quality gates, or the user wants to decide which AI output checks are worth automating. Not for checking whether a system grades encoded judgment against real outcomes; use cyborg-check for that.

  • Runtime guard

    mattdweigand-sketch/agent-skills/skills/runtime-guard Skill

    1★ repo

    Prevents an agent from editing or publishing without clearly defined authority, boundaries, stop conditions, or rollback.

  • Ss6 data migration

    jsirish/silverstripe-skills/skills/ss6-data-migration Skill

    1★ repo

    Repeatable workflow for Silverstripe 6 upgrade data migrations. Use this skill when the user wants to "run the SS6 migration", "sync and migrate for SS6", "test the linkfield migration", or rebuild a local site to match production after an SS6 upgrade. Sequence is - sync the production database, dev/build, run each migration task with row-count verification, verify the front end against production.

  • Grill with docs

    merllinsbeard/merlin-skills/skills/grill-with-docs Skill

    1★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 11 other repositories

  • Jvm fatjar deploy verification

    jbiscella/skills-dungeon/skills/code/jvm-fatjar-deploy-verification Skill

    1★ repo

    Verify that a Java fat/uber jar produced by Maven Shade Plugin is structurally sound before deploying it to AWS Lambda, container scratch images, or any environment where the artifact runs without your local classpath. Use this skill whenever you build a fat jar for deployment, configure or troubleshoot maven-shade-plugin, or face runtime errors like NoClassDefFoundError, "Property doesn't exist", PropertySourceLoader not found, or other "works in IDE but fails when deployed" symptoms. Especially load when you see suspiciously small thin jars under 10 MB for a typical Spring or Micronaut app, missing application.yml at runtime, or META-INF/services entries lost after shading.

  • Setup pre commit

    dominikwozniak/claude-kit/skills/setup-pre-commit Skill

    1★ repo

    Use when adding pre-commit hooks to a JS/TS project. Detects package manager, installs husky + lint-staged + prettier, wires .husky/pre-commit to run lint-staged (and optionally typecheck + test). When pnpm is the detected manager, also enforces pnpm-only via `packageManager` field + `preinstall: npx only-allow pnpm` + `.npmrc engine-strict=true`. COMMITS to the repo — affects teammates. Trigger phrases: "set up pre-commit", "add husky", "configure lint-staged", "add commit-time formatting", "enforce pnpm".

  • Agent output review

    stephenrogan/leadership-skills/skills/agent-output-review Skill

    1★ repo

    Reviews AI agent outputs for correctness, evidence, completeness, safety, decision boundaries, and usability before a leader relies on them. Use when evaluating reports, drafts, code, research, strategy memos, customer responses, or autonomous agent deliverables.

  • Smart git automation

    mskadu/opencode-agent-skills/skills/smart-git-automation Skill

    1★ repo

    Smart change detection, auto branch naming, and streamlined commit/PR workflow

  • Wiki lint

    jehrhardt/agents/skills/wiki-lint Skill

    no license1★ repo

    Health-check the LLM wiki. Find orphan pages, check index completeness, flag stale claims, identify missing cross-references, and detect contradictions. Use when the user asks to check wiki health or wants periodic maintenance.

  • Code review and quality

    Xrenya/safe-agent-skills/skills/code-review-and-quality Skill

    1★ 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

  • Git workflow and versioning

    Xrenya/safe-agent-skills/skills/git-workflow-and-versioning Skill

    1★ repo

    Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

    The same file is in 9 other repositories

  • Lifecycle reviewer

    zaixincheng174-ai/codex-agent-governance-skills/core/skills/lifecycle-reviewer Skill

    1★ repo

    project-lifecycle 协议的 PHASE 3 角色。在实现门禁通过后执行独立审查。唯一职责: 以只读身份审查产物的逻辑严密性、安全性、与设计的一致性,发现问题打回 BUILD。 由 project-lifecycle 总控调用,不单独触发。

  • Review

    Tiao553/sdd-harness-copilot/.github/skills/review Skill

    no license1★ repo

    AgentSpec review commands. Use /review-commands + command. Commands: /review, /judge

  • Passive review skill

    Podcast72/agent-skill-starter-kit/examples/passive-review-skill Skill

    1★ repo

    Use this skill as an example of a local review-oriented skill that can optionally record minimal usage metadata for later manual review.

  • Review closeout skill

    Podcast72/agent-skill-starter-kit/examples/review-closeout-skill Skill

    1★ repo

    Use this skill for a controlled final review after non-trivial local edits. It helps evaluate advisory findings, apply only verified fixes, run targeted checks, and produce a final closeout report.

  • Feasibility check

    NjoyimPeguy/augments/plugins/augments/skills/feasibility-check Skill

    1★ repo

    Use before committing to a project or initiative — to decide whether the goal is achievable within the real constraints (time, team, tech, budget), surface the risks that could sink it, and route the riskiest unknowns to prototyping. Skip when the approach is already proven or the commitment is trivially reversible.

  • Finishing a branch

    NjoyimPeguy/augments/plugins/augments/skills/finishing-a-branch Skill

    1★ repo

    Use when a change's checks are verified green and you're ready to wrap the branch — clean commits, a real PR description, and a merge/keep/discard decision. If done or tested is only asserted, not yet run, verify first (verifying-completion). Skip mid-development — this is the wrap-up.

  • Receiving code review

    NjoyimPeguy/augments/plugins/augments/skills/receiving-code-review Skill

    1★ repo

    ALWAYS invoke when review feedback arrives — from a human or another agent — on code you wrote, before you respond or act on any finding. Verifying each finding against the code first is mandatory; agreeing or editing without checking is the mistake. Push back with evidence when a finding is wrong; refuse performative agreement.

  • Requesting code review

    NjoyimPeguy/augments/plugins/augments/skills/requesting-code-review Skill

    1★ repo

    Use when a non-trivial change reaches a done boundary — before calling it complete, committing, merging, or opening a PR, not only when you already want fresh eyes. Skip a trivial mechanical diff (rename, version bump, config one-liner) — self-review instead.

  • Using task branches

    NjoyimPeguy/augments/plugins/augments/skills/using-task-branches Skill

    1★ repo

    Use before starting repo edits or implementation, or when work needs isolation from the current checkout - ensure a meaningful task branch, harness workspace, or git worktree exists according to user/project preference. Skip for read-only work or when the current branch/workspace is already dedicated to this task.

  • Using task branches

    NjoyimPeguy/augments/skills/common/using-task-branches Skill

    1★ repo

    Use before starting repo edits or implementation, or when work needs isolation from the current checkout - ensure a meaningful task branch, harness workspace, or git worktree exists according to user/project preference. Skip for read-only work or when the current branch/workspace is already dedicated to this task.

  • Finishing a branch

    NjoyimPeguy/augments/skills/deployment/finishing-a-branch Skill

    1★ repo

    Use when a change's checks are verified green and you're ready to wrap the branch — clean commits, a real PR description, and a merge/keep/discard decision. If done or tested is only asserted, not yet run, verify first (verifying-completion). Skip mid-development — this is the wrap-up.

  • Feasibility check

    NjoyimPeguy/augments/skills/planning/feasibility-check Skill

    1★ repo

    Use before committing to a project or initiative — to decide whether the goal is achievable within the real constraints (time, team, tech, budget), surface the risks that could sink it, and route the riskiest unknowns to prototyping. Skip when the approach is already proven or the commitment is trivially reversible.

  • Receiving code review

    NjoyimPeguy/augments/skills/testing/receiving-code-review Skill

    1★ repo

    ALWAYS invoke when review feedback arrives — from a human or another agent — on code you wrote, before you respond or act on any finding. Verifying each finding against the code first is mandatory; agreeing or editing without checking is the mistake. Push back with evidence when a finding is wrong; refuse performative agreement.

  • Requesting code review

    NjoyimPeguy/augments/skills/testing/requesting-code-review Skill

    1★ repo

    Use when a non-trivial change reaches a done boundary — before calling it complete, committing, merging, or opening a PR, not only when you already want fresh eyes. Skip a trivial mechanical diff (rename, version bump, config one-liner) — self-review instead.

  • Gpt pro bridge

    nyxx-stack/agent-skills/skills/gpt-pro-bridge Skill

    1★ repo

    Package the repo and generate an optimized prompt for GPT 5.5 Pro (web) to analyze the codebase — for audits, debugging, refactors, architecture reviews, or any analysis task. GPT's output is constrained to produce a structured Claude Code execution prompt that can be pasted back and run locally. Use this when the user explicitly mentions GPT, ChatGPT, or GPT 5.5 Pro, says things like "ask GPT", "bridge to GPT", "GPT review", or wants to upload the repo to ChatGPT for analysis. Do NOT trigger for "second opinion" or "external review" requests that don't mention GPT specifically — those likely want a Codex or code-review workflow instead.

  • Thermo nuclear simplify review

    nyxx-stack/agent-skills/skills/thermo-nuclear-simplify-review Skill

    1★ repo

    Run an agent-native simplify pass for explicit cleanup, maintainability, hardening, thermonuclear review, or code-quality audit requests. Reviews with subagents, then fixes high-confidence issues unless review-only is requested.

  • Implement review

    montgomeryunpopular607/anywhere-agents/skills/implement-review Skill

    1★ repo

    Review loop for staged changes. Detects content type, prepares a review request for Codex (terminal or plugin), categorizes feedback, revises, and iterates. Works for code, papers, proposals, or any text-based output.

  • Release sw project en

    roebi/sw-dev-agent-framework/skills/release-sw-project-en Skill

    no license1★ repo

    Performs the release phase of a software project: bumps version, generates changelog, creates a git tag, and publishes the artifact (PyPI, npm, or GitHub Release). Uses semver, conventional commits, and PyPI Trusted Publishing (OIDC) for Python packages. Use after code review passes with zero critical or major findings. Activate for trigger phrases like: "release the project", "release phase", "publish to PyPI", "create a release", "bump version and tag", "cut a release", or "ship it".

  • Engineering paper router

    169884902hzl/engineering-paper-skills/skills/engineering-paper-router Skill

    1★ repo

    Route ambiguous or mixed English engineering paper tasks to the correct engineering paper skill. Use when the user asks broadly to improve my paper, check my manuscript, revise this draft, prepare submission, respond to comments, or combine drafting, polishing, figure/table work, response drafting, and validation.

  • Engineering validation

    169884902hzl/engineering-paper-skills/skills/engineering-validation Skill

    1★ repo

    Validate English engineering manuscript readiness before claiming edits are complete. Use when the user asks to check a paper, compile LaTeX, inspect references, page count, citations, figure/table consistency, claim-evidence anchors, final-paper synchronization, submission checklist, or whether a conference/journal manuscript is safe to submit. This is readiness validation, not certification that experiments, citations, or claims are true unless the relevant sources and checks were actually provided and inspected.

  • Conventional commits

    idanmann10/vivarium-world/domains/coding/skills/conventional-commits Skill

    no license1★ repo

    Use terse conventional commit messages that describe behavior.

  • Review findings first

    idanmann10/vivarium-world/domains/coding/skills/review-findings-first Skill

    no license1★ repo

    Lead code reviews with bugs and risks, then summaries.

  • Freshness check

    idanmann10/vivarium-world/domains/research/skills/freshness-check Skill

    no license1★ repo

    Verify time-sensitive facts against current sources.

  • Plan review

    SamuelBostic29/claude-skills/skills/plan-review Skill

    1★ repo

    Review a saved plan with convergence-oriented discipline — verdict first, blockers capped, "I don't understand" converted to questions instead of findings. Use when asked to "review the plan", "sanity-check the plan", or for a fresh-eyes second opinion on a saved plan file before executing it; reads prior review entries so repeated rounds converge instead of re-litigating. Designed to avoid the fresh-eyes nit-list pattern where every review produces 6-8 items regardless of plan maturity.

  • Review session

    SamuelBostic29/claude-skills/skills/review-session Skill

    1★ repo

    Spin up a fresh, INTERACTIVE Claude Code session in a separate terminal to review the whole branch's changes vs the base (every commit over the base plus uncommitted edits) with zero context from the work that produced them. Use when asked to "review my changes in a fresh/separate session", "cold review before I open the PR", "spin up another Claude to review this", or "get an unbiased second pair of eyes on this branch". Hands the reviewer the exact diff automatically; the review happens in the new window, not here.

  • Validator generator

    SamuelBostic29/claude-skills/skills/validator-generator Skill

    1★ repo

    Generate a FluentValidation validator for a .NET DTO or command — create, update, delete, shared-save, or import variant — with rules grounded in the DTO's real properties and the repo's existing validator conventions. Uniqueness and dependency checks go through an adopter-owned abstraction, so FluentValidation stays the only named third-party dependency. Use when asked to write/generate/add a validator or "add validation for <DTO>".

  • Shape product design

    workingclassbuddha/codexmaxxing/skills/shape-product-design Skill

    1★ repo

    Design, critique, and polish frontend product surfaces until they feel intentional and usable. Use when Codex is asked to design, redesign, review, or improve a web app, dashboard, landing page, tool UI, mobile screen, component, visual system, or screenshot-based frontend experience, especially when layout, typography, color, interaction states, responsiveness, or product taste matter.

  • Mission control evidence check

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-evidence-check Skill

    1★ repo

    Check whether Mission Control claims have backing evidence. Use when the user wants to know whether tests, builds, screenshots, artifacts, or handoff confidence are real, missing, weak, or dry-run only.

  • Mission control plugin health

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-plugin-health Skill

    1★ repo

    Run a Mission Control plugin, daemon, and bridge health check. Use when the user wants to verify daemon status, MCP connectivity, skills availability, runner registry, local binding, or general bridge health from Codex chat.

  • Mission control review burst

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-review-burst Skill

    1★ repo

    Use when Mission Control should recommend a bounded read-only review burst across correctness, security, testing, maintainability, and docs.

  • Mission control review tests

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-review-tests Skill

    1★ repo

    Review Mission Control testing coverage and status. Use when the user wants to know what tests exist, what ran, what failed, what was skipped, or where validation coverage is still weak.

  • Mission control run validation

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-run-validation Skill

    1★ repo

    Ask Mission Control to run or plan validation. Use when the user wants build, tests, typecheck, lint, smoke, docs check, or manual verification routed through Mission Control with approvals preserved.

  • Mission control scope creep check

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-scope-creep-check Skill

    1★ repo

    Ask Mission Control whether the project is drifting beyond approved scope. Use when the task list is growing, the user asks for more work midstream, or you need a Manager recommendation on include now versus defer.

  • Mission control security review

    MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-security-review Skill

    1★ repo

    Ask Mission Control for a security review. Use when the user wants secrets risk, auth risk, dependency risk, command safety, file permission risk, deployment exposure, risky code patterns, or remediation planning summarized through Mission Control.

  • Mission control evidence check

    MN755/Codex-Mission_Control/.codex/skills/mission-control-evidence-check Skill

    1★ repo

    Check whether Mission Control claims have backing evidence. Use when the user wants to know whether tests, builds, screenshots, artifacts, or handoff confidence are real, missing, weak, or dry-run only.

  • Mission control plugin health

    MN755/Codex-Mission_Control/.codex/skills/mission-control-plugin-health Skill

    1★ repo

    Run a Mission Control plugin, daemon, and bridge health check. Use when the user wants to verify daemon status, MCP connectivity, skills availability, runner registry, local binding, or general bridge health from Codex chat.

  • Mission control review burst

    MN755/Codex-Mission_Control/.codex/skills/mission-control-review-burst Skill

    1★ repo

    Use when Mission Control should recommend a bounded read-only review burst across correctness, security, testing, maintainability, and docs.

  • Mission control review tests

    MN755/Codex-Mission_Control/.codex/skills/mission-control-review-tests Skill

    1★ repo

    Review Mission Control testing coverage and status. Use when the user wants to know what tests exist, what ran, what failed, what was skipped, or where validation coverage is still weak.

  • Mission control run validation

    MN755/Codex-Mission_Control/.codex/skills/mission-control-run-validation Skill

    1★ repo

    Ask Mission Control to run or plan validation. Use when the user wants build, tests, typecheck, lint, smoke, docs check, or manual verification routed through Mission Control with approvals preserved.

  • Mission control scope creep check

    MN755/Codex-Mission_Control/.codex/skills/mission-control-scope-creep-check Skill

    1★ repo

    Ask Mission Control whether the project is drifting beyond approved scope. Use when the task list is growing, the user asks for more work midstream, or you need a Manager recommendation on include now versus defer.

  • Mission control security review

    MN755/Codex-Mission_Control/.codex/skills/mission-control-security-review Skill

    1★ repo

    Ask Mission Control for a security review. Use when the user wants secrets risk, auth risk, dependency risk, command safety, file permission risk, deployment exposure, risky code patterns, or remediation planning summarized through Mission Control.