agentsclimarketplace

Review & quality

19,169 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

  • Design review

    m-binimran/design-pack/skills/design-review Skill

    3★ repo

    Critique a design against craft principles - hierarchy, layout, type, color, spacing, accessibility, brand fit. Use when reviewing a draft, a generated image, or a layout before delivery.

  • Confidence check

    unix2dos/skills/confidence-check Skill

    3★ repo

    Use when starting complex tasks like feature development, bug fixes, or code refactoring - runs a pre-implementation confidence check to avoid wasting tokens on wrong directions

  • Go code review

    unix2dos/skills/go-code-review Skill

    3★ repo

    Use when reviewing Go code for performance, concurrency safety, security vulnerabilities, or readability issues

  • Harness audit

    claudialnathan/agent-kitchen/skills/harness-audit Skill

    no license3★ repo

    Audits the coding-agent harness a project's sessions run under, end-to-end: what loads every session, what it costs, whether the harness's own claims hold, and whether its parts work when assembled. Inventories the standing surfaces (CLAUDE.md chain, personal/project/plugin skills, MCP instruction blocks, agent rosters, hooks, settings at every scope), quantifies their per-session token cost, runs setup checks (self-consistency, duplication across scopes, enforcement parity, scope discipline, and a provisional routing-effectiveness check for doc-fleet repos), and after substantial harness changes can run a representative composition probe through the complete installed system. The audit itself is read-only: the deliverable is a ranked findings report leading with the highest-value edit, nothing is applied without the owner's explicit go-ahead, and edits stay inside the project directory. Machine scope (anything under ~/.claude, user or enterprise settings, global plugins) is never edited; those findings are reported with a project-scoped counterweight proposed where one exists. Use to review, slim, or sanity-check a project's harness after major harness changes or when sessions feel slow or behave incoherently from turn one; for a single artifact, the relevant forge owns the audit.

  • Using git

    gerph/riscos-agent-skills/skills/using-git Skill

    3★ repo

    Use when reading status, preparing commits, writing commit messages, comparing local changes, or handling dirty worktrees in this build environment. Focuses on safe non-interactive Git usage, selective staging, and avoiding interference with unrelated user changes.

  • 07 stata runner

    lianxhcn/PXa2026a/skills/core/07-stata-runner Skill

    no license3★ repo

    Use this skill when an AI agent needs to actually run Stata code locally to verify results, check whether a do-file runs, locate errors from Stata output, or execute repetitive data-processing steps. This is a reference-type entry pointing to the Stata AI Skill bundled with the "Stata All in One" VS Code extension; it is installed via the extension, not copied into this repository.

  • High quality content writer

    SwiftAdviser/public-skills/skills/high-quality-content-writer Skill

    no license3★ repo

    Write, rewrite, audit, and iteratively improve prose until it passes isolated content-quality gates. Use when the user asks for high-quality content, cleanup, anti-slop rewriting, article/copy/landing-page improvement, link/text grading, AI-writing trope removal, slop-check validation, or a loop that keeps revising until the final text is clean, specific, fact-dense, and publishable.

  • Admin sharing troubleshooting

    PranavNagrecha/Salesforce-Intelligence/.claude/skills/admin-sharing-troubleshooting Skill

    3★ repo

    Salesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.

  • Commit

    Eipi-Tong/agentic-coding-starter-kit/.claude/skills/commit Skill

    no license3★ repo

    Create a well-formed Conventional Commit. Use when the user says "commit", "commit my changes", or asks you to save progress.

  • Odoo code review

    Immoderate-humulin783/odoo-skills/skills/odoo-code-review Skill

    no license3★ repo

    Review Odoo addon code for correctness, security, performance, migrations, tests, and official Odoo coding guidelines. Use when reviewing Odoo modules, diffs, pull requests, or changed files involving models, fields, XML views, data, controllers, reports, OWL/assets, manifests, access rules, record rules, or OCA migrations.

    The same file is in 1 other repository

  • Compliance check

    EvezArt/evez-skills/skills/compliance-check Skill

    no license3★ repo

    Run a compliance check on a proposed action, product feature, or business initiative, surfacing applicable regulations, required approvals, and risk areas. Use when launching a feature that touches personal data, when marketing or product proposes something with regulatory implications, or when you need to know which approvals and jurisdictional requirements apply before proceeding.

    The same file is in 25 other repositories

  • Prompt review and dispatch

    George930502/curated-codex-skills/skills/prompt-review-and-dispatch Skill

    3★ repo

    Audit a GPT-5.6 prompt, clarify purpose through native clickable questions, polish it, require explicit approval, then continue the exact approved prompt in the current Codex conversation by default. Use when the user wants a review-before-execution prompt workflow or explicitly asks to send work to another Codex task.

  • Vault lint

    markphelps/agent-plugins/skills/vault-lint Skill

    3★ repo

    Hygiene pass over active notes, ideas, and projects

  • Vault lint

    markphelps/agent-plugins/vault/skills/vault-lint Skill

    3★ repo

    Hygiene pass over active notes, ideas, and projects

  • Quality gate

    ligyDt/ai-ide-init-template/codebuddy/.codebuddy/skills/quality-gate Skill

    3★ repo

    建立测试策略、验收矩阵、回归检查与发布质量结论。用于实施验证或交付门禁。

  • Security risk review

    ligyDt/ai-ide-init-template/codebuddy/.codebuddy/skills/security-risk-review Skill

    3★ repo

    审查密钥、隐私、外部系统、账号、支付、真实数据、生产和发布风险。用于高风险动作前。

  • Quality gate

    ligyDt/ai-ide-init-template/codex/.agents/skills/quality-gate Skill

    3★ repo

    为交付建立测试策略、验收矩阵、回归风险检查和发布质量结论。用于功能实施前规划覆盖、变更完成后审查验证充分性、缺陷复现,或在发布前需要明确通过与阻断条件时。

  • Security risk review

    ligyDt/ai-ide-init-template/codex/.agents/skills/security-risk-review Skill

    3★ repo

    审查凭据、隐私、外部访问、真实数据、支付、发布和生产操作风险。用于接入第三方系统、处理用户或业务敏感数据、使用自动化账号、建立支付能力、部署或执行任何高风险外部动作前。

  • Quality gate

    ligyDt/ai-ide-init-template/cursor/.cursor/skills/quality-gate Skill

    3★ repo

    建立测试策略、验收矩阵、回归检查与发布前质量结论。用于实现前规划覆盖或交付前审查。

  • Security risk review

    ligyDt/ai-ide-init-template/cursor/.cursor/skills/security-risk-review Skill

    3★ repo

    审查凭据、隐私、外部访问、真实数据、支付、发布和生产操作风险。用于任何高风险外部动作之前。

  • Quality gate

    ligyDt/ai-ide-init-template/trae/.agents/skills/quality-gate Skill

    3★ repo

    建立测试计划、验收矩阵、回归风险检查和发布门禁结论。用于交付验证和质量审查。

  • Security risk review

    ligyDt/ai-ide-init-template/trae/.agents/skills/security-risk-review Skill

    3★ repo

    审查凭据、隐私、外部访问、账号、支付、真实数据、发布和生产操作风险。用于高风险动作之前。

  • Context check

    tmusser/ai-engineering-skills/skills/context-check Skill

    3★ repo

    Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.

  • Grill with docs lite

    tmusser/ai-engineering-skills/skills/grill-with-docs-lite Skill

    3★ repo

    Run a bounded docs-grounded contradiction hunt before mini-spec, separating source facts from decisions, assumptions, and blockers without building a domain model.

  • Tool noise guard

    tmusser/ai-engineering-skills/skills/tool-noise-guard Skill

    3★ repo

    Passive guardrail that compacts repetitive tool-result envelopes, preserves decision-relevant anchors and deltas, and suppresses redundant re-fetches without pretending prior context disappeared.

  • Verify contract

    tmusser/ai-engineering-skills/skills/verify-contract Skill

    3★ repo

    Record clear evidence that a task works, including commands, results, remaining risks, and whether the implementation stayed under the spec ceiling.

  • Android code review

    adrigm06/Android-Engineering-Skill/skills/android-code-review Skill

    3★ repo

    Structured Android code review skill with severity-based findings across architecture, correctness, maintainability, performance, and security. Use this for PR reviews and technical debt assessments.

  • Req dev lite

    samgao2000/prd-grill/skills/req-dev-lite Skill

    3★ repo

    Requirements-interrogation agent, local lightweight edition (no issue tracker). Trigger when the user says "grill my requirements", "review my requirements (local)", "local PRD", "req-dev lite", "pre-PRD", or "/req-dev-lite". Orchestrates grill-with-docs and layers Mom Test / Impact Mapping / 5 Whys / Specification by Example / Cockburn Extensions / INVEST / Volere QG on top, producing a local markdown PRD (with an Open Items section). Unlike the full req-dev, it creates no GitHub issues and needs no gh CLI. Chinese version: SKILL.zh.md (same folder)

  • Grill with docs

    samgao2000/prd-grill/third_party/grill-with-docs Skill

    3★ 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 8 other repositories

  • Pre ship

    Syo-M/fable-frontend-skills/.claude/skills/pre-ship Skill

    3★ repo

    Pre-merge verification pipeline — runs typecheck, lint, affected tests, then security and a11y review passes scoped to what changed, and reports a single pass/fail table. Use before claiming any change is done, before opening a PR, and whenever the user asks to verify/finalize work. 日本語の依頼例:「出荷前チェック」「マージ前に確認して」「これで完成か確認」「PR出す前のチェック」。

  • Tooling

    Syo-M/fable-frontend-skills/.claude/skills/tooling Skill

    3★ repo

    Lint and enforcement configuration — ESLint, Stylelint, tsconfig flags, env validation, dead-code checks; maps project rules to the tools that enforce them. Use when configuring linters, tsconfig, or when a convention should be automated instead of remembered. 日本語の依頼例:「ESLint/Lint設定」「tsconfig設定」「ルールを自動で強制したい」「Stylelint」「CIで弾きたい」。

  • Pre ship

    Syo-M/fable-frontend-skills/plugin/skills/pre-ship Skill

    3★ repo

    Pre-merge verification pipeline — runs typecheck, lint, affected tests, then security and a11y review passes scoped to what changed, and reports a single pass/fail table. Use before claiming any change is done, before opening a PR, and whenever the user asks to verify/finalize work. 日本語の依頼例:「出荷前チェック」「マージ前に確認して」「これで完成か確認」「PR出す前のチェック」。

  • Tooling

    Syo-M/fable-frontend-skills/plugin/skills/tooling Skill

    3★ repo

    Lint and enforcement configuration — ESLint, Stylelint, tsconfig flags, env validation, dead-code checks; maps project rules to the tools that enforce them. Use when configuring linters, tsconfig, or when a convention should be automated instead of remembered. 日本語の依頼例:「ESLint/Lint設定」「tsconfig設定」「ルールを自動で強制したい」「Stylelint」「CIで弾きたい」。

  • Commitlint

    rshade/agent-skills/skills/commitlint Skill

    3★ repo

    Validate commit messages against the Conventional Commits specification. Auto-detects and installs commitlint CLI if missing. Checks project config or falls back to sensible defaults. Use when validating commit messages, preparing PRs, or enforcing commit conventions.

    The same file is in 2 other repositories

  • Cost check

    rshade/agent-skills/skills/cost-check Skill

    3★ repo

    Generic cost estimation for IaC projects. Detects the IaC stack (Pulumi, Terraform) and compatible cost tool (finfocus, infracost), runs cost analysis, flags expensive resources, cost increases, and total cost against configurable thresholds. Produces a terminal summary and COST_CHECK.md report. Use when checking infrastructure costs, reviewing cost impact of changes, or enforcing budget thresholds in CI.

  • Lint fix

    rshade/agent-skills/skills/lint-fix Skill

    3★ repo

    Detect project linting and validation tools, build an execution pipeline, run all tools to zero errors, and fix issues using an atomic fix protocol. Auto-detects Makefile targets, package.json scripts, Go tools, Python tools, and other common linters. Use when fixing linting errors, running validation pipelines, or ensuring code quality before committing.

    The same file is in 2 other repositories

  • Pull request msg with gh

    rshade/agent-skills/skills/pull-request-msg-with-gh Skill

    3★ repo

    Generate a PR_MESSAGE.md file from session context using GitHub CLI. Detects related issues via branch-keyword search, writes a structured PR description with commit subject, summary, test plan, and changelog. Validates with commitlint and markdownlint. Use when preparing a pull request on GitHub.

    The same file is in 2 other repositories

  • Rebut

    next-friday/next-friday-skills/plugins/next-friday/skills/rebut Skill

    3★ repo

    Use on an open pull request that carries AI code-review comments from CodeRabbit, Gemini Code Assist, or a similar bot reviewer that need handling, and right after pushing to a PR where such a reviewer is expected to weigh in. Triggers on requests like 'audit the bot comments', 'respond to coderabbit', 'rebut the reviewer', 'go through the AI review', or whenever an open PR shows unresolved bot review threads to triage.

  • Polymarket guard

    evidai/agent-payment-mcp/io.github.evidai/polymarket-guard MCP server

    3★ repo

    Polymarket prediction markets — buy/sell positions in USDC. LemonCake pay-per-call billing.

  • Artefact discipline check

    jposluns/grc_library/dev-security/claude-rules/skills/artefact-discipline-check Skill

    2★ repo

    Routes a change through the correct workflow when the change touches a generated artefact or a protected branch. Use before hand-editing a file that is produced by a generator (build outputs, schema dumps, taxonomies, doc portals, scorecards, lockfiles). Use before pushing directly to, force-pushing, or `reset --hard`ing a protected branch (the default branch, release branches, long-lived integration branches). Use when CI flags generated-artefact drift or a protected-branch operation. The workflow redirects to "edit source, run the generator, commit both halves" or "open a PR through the documented merge mechanism", never to "hand-edit the artefact" or "force-push past the check".

  • Citation quote verification

    jposluns/grc_library/dev-security/claude-rules/skills/citation-quote-verification Skill

    2★ repo

    Before any completion claim on a change that touches a document containing external-source citations (verbatim quotes, paraphrased synthesis, or framework references with article / section / clause locators), verify each citation's text against the cited source at the cited location. Catches the failure mode where a confidently-cited quote does not actually appear in the source, or a paraphrase mis-represents the source's meaning. Catches what the mechanical citation linters (format and currency) cannot reach: quote-to-source correspondence.

  • Deep qa review

    jposluns/grc_library/dev-security/claude-rules/skills/deep-qa-review Skill

    2★ repo

    Trust-recovery deep quality-assurance pass. A six-subagent forensic review specialized for AI-failure-pattern classes, run over a defined PR window plus the files those PRs reference, when an AI coding assistant's discipline failures (abbreviated QA, skipped post-commit audits, wrong-cadence timers, inferred-not-validated premises) call for a white-box re-examination beyond the routine per-PR and periodic sweeps. Slash command `/full-qa`. Pairs with `library-fitness-review` (`/fitness`): deep-qa-review is one deeply-contextualized lens tuned to how AI assistants fail; fitness is ten context-stripped persona lenses. Together they form the trust-recovery escalation tier. Findings route to the project backlog tiered by severity (High[critical]/High to the top-priority tier, Medium/Low to the next tier), none dropped, for maintainer triage; the pass terminates on explicit maintainer sign-off, not on an empty finding-set.

  • Fresh reader validation

    jposluns/grc_library/dev-security/claude-rules/skills/fresh-reader-validation Skill

    2★ repo

    Before declaring a new or substantively-revised governance document complete, dispatch a fresh subagent with no session context to read the document and surface tacit-context gaps (ambiguous terms, missing definitions, implicit assumptions, unresolved references that the author knows but did not write down). Catches the failure mode the author cannot catch directly: the "I know what I meant" blind spot that fills the document's gaps invisibly during authoring.

  • Gate discipline diagnose

    jposluns/grc_library/dev-security/claude-rules/skills/gate-discipline-diagnose Skill

    2★ repo

    Diagnoses a failing CI gate, lint, or audit and fixes the artefact rather than weakening the gate. Use when a gate fails. Use when tempted to bypass a check with --no-verify, blanket suppression, severity-threshold lowering, or exemption-list addition. Use when a pre-commit hook blocks a commit. Use when a required status check on a PR shows red.

  • Guardrail review

    jposluns/grc_library/dev-security/claude-rules/skills/guardrail-review Skill

    2★ repo

    When the governance machinery itself (the rules, skills, and audit gates that keep a governed codebase honest, plus their wiring surfaces) needs a structural-integrity review, run this skill. It is the periodic guard-rail review: a judgment-based pass over the machinery for overlap (two rules or gates covering the same ground), gap (a stated discipline no gate enforces, a recurring failure mode no rule names), and drift (a rule, skill, or gate whose intent has diverged across its wiring surfaces in a way the mechanical parity gates cannot detect, because they check identity and count, not meaning). Maintainer-triggered, and auto-prompted after any PR that adds, removes, or renames a rule, skill, or gate. Catches the architectural erosion the per-PR and corpus-content sweeps are not built to see. Slash command `/guardrails`.

  • High assurance verification

    jposluns/grc_library/dev-security/claude-rules/skills/high-assurance-verification Skill

    2★ repo

    Run the heavier pre-apply verification harness for a SENSITIVE change, one that is gate-blind on correctness (a fit or semantic property no existence gate can check), delicate at scale (a wide reshape or bulk mapping where a hand-edit is itself a defect risk), and costly to get wrong (a cited or downstream-relied-on artefact). Use before applying such a change, when the maintainer directs absolute-integrity rechecking, or when resuming a sensitive item left open in the register. It composes research fan-out, a mechanical signal pass over the negatives, two independent adversarial verifiers from different model families (false-negative and false-positive lenses, blind to each other and to the research), a programmatic invariant floor, and a deterministic scripted apply plus re-parse, so apply-correctness does not rest on the orchestrator's in-context precision. It catches the plausible-but-wrong value that survives every existence gate because the gate confirms the value is well-formed, not that it is right.

  • Library fitness review

    jposluns/grc_library/dev-security/claude-rules/skills/library-fitness-review Skill

    2★ repo

    Trigger a comprehensive whole-corpus library-fitness review with a project-defined catalogue of persona reviewers when a governance/security documentation library undergoes a major change (new domain dir, new document type, multiple governance rule additions, major restructure) or quarterly minimum. Each invocation dispatches a fan-out of independent persona subagents (for example an executive reader, a security practitioner, an auditor, a newcomer) who review every page from a fresh-reader perspective without inheriting maintainer mental models. Catches comprehensibility, usability, logical-structure, standardization, governance/security quality, auditability, maintainability, and reader-experience gaps that per-PR validation sweeps and mechanical audit gates do not detect. Surfaces prioritized recommendations and a discrete remediation backlog the maintainer drives through subsequent PRs.

  • Validation sweep pr scoped

    jposluns/grc_library/dev-security/claude-rules/skills/validation-sweep-pr-scoped Skill

    2★ repo

    PR-scoped validation sweep. Runs after every successful PR merge to catch issues the merge introduced before they compound across subsequent PRs. Dispatches Subagent A (recent-PR deep review) scoped to the just-merged PR's diff plus a lightweight cross-reference check for files cited by other documents. Complements the corpus-wide `validation-sweep` skill (`/validate`): `/validate-pr` is fast and runs after every merge; `/validate` is comprehensive and runs every 10 merges or maintainer-triggered. The two skills together cover both per-PR drift (caught fast) and corpus-wide drift (caught broadly).

  • Validation sweep

    jposluns/grc_library/dev-security/claude-rules/skills/validation-sweep Skill

    2★ repo

    Corpus-wide regression sweep run as a follow-up after any issue is identified and corrected, to confirm no sibling issue remains anywhere in the repository. Invoke after fixes that touch multi-surface artefacts, gate inventories, prose claims about repo state, AI-inferred citations, or generated artefacts. Combines the mechanical audit suite with a structured semantic fan-out, and loops until clean.

  • Bom validation workflow

    Ed3Design/ed3design-engineering-bundles/maker-fdm/skills/bom-validation-workflow Skill

    2★ repo

    Use when validating a Bill of Materials (BOM) for a Maker-3D project — an embedded controller project, a speaker/audio build, a smart-home build, or any other physical build with more than 5 components. Trigger on phrases like "check the BOM", "validate the parts list", "review the parts list", "missing components", "reconcile parts inventory", "check hardware stock", "what still needs to be ordered", "check BOM against stock", "audio build BOM", "BOM review". Do NOT load for software dependency lists (use package.json/requirements.txt tooling), for pure schematic checks without physical components, or when the project has only 1-2 components (cost/benefit ratio too low). Encodes the end-to-end-builder pattern: before ordering, check against the hardware stock; do not forget connections + consumables.

  • Review coverage

    cheukswiss/etdxm/.claude/skills/review-coverage Skill

    2★ repo

    覆奏机制,尚书省汇总完毕提交时触发,门下省事后审查执行结果是否忠于原旨

  • Hardening codebase

    qte77/claude-code-plugins/plugins/codebase-tools/skills/hardening-codebase Skill

    2★ repo

    Audit and tighten codebase quality gates — architecture, lint, types, tests, docs, code review. Use when onboarding a project, before a release, or when validation is too permissive.

  • Committing staged with message

    qte77/claude-code-plugins/plugins/commit-helper/skills/committing-staged-with-message Skill

    2★ repo

    Generate commit message for staged changes, pause for approval, then commit. Stage files first with `git add`, then run this skill.

    The same file is in 1 other repository

  • Creating pr from branch

    qte77/claude-code-plugins/plugins/commit-helper/skills/creating-pr-from-branch Skill

    2★ repo

    Create a pull request from the current branch. Analyzes commits, generates title+body from PR template, pauses for approval, then pushes and creates PR. Use after committing changes.

  • Ballot

    eins78/agent-skills/skills/ballot Skill

    2★ repo

    Use when decisions happen async — reviewer(s) look at it over chat, on a PR, on a train, or any time outside the agent session. Triggers: async decision, PR review, pull request, remote reviewer, handoff, away-from-keyboard, decision ballot, architecture call, architecture decision record, ADR, hiring panel, vendor selection, household decision, reconcile, per-reviewer, tick box, ballot.

  • Literature review

    ajaygunalan/flow-friction/skills/literature-review Skill

    no license2★ repo

    Finds and synthesizes papers using seed-then-snowball strategy. S2 for seeds + citation chasing, OpenAlex for semantic search + trust signals. Three modes: landscape (map a field), validate (test a claim), critique (stress-test a document). AI reads papers and teaches through chat. User may also read directly.

  • Merge

    ajaygunalan/flow-friction/skills/merge Skill

    no license2★ repo

    Squash-merge a worktree branch into main — rebase, test, merge, free slot

  • Code review and quality

    LLl0k0laD/agent-skills/skills/code-review-and-quality Skill

    2★ repo

    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.

  • Git workflow and versioning

    LLl0k0laD/agent-skills/skills/git-workflow-and-versioning Skill

    2★ repo

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

  • Ios native review

    Paretofilm/superpowers-gstack/skills/ios-native-review Skill

    no license2★ repo

    After a PRD/spec/plan for an iOS app, before implementation: validate the artifact against Apple HIG (iOS) via WebFetch citations. Asks "is this iOS-native?" — complements pitfall-verification and quality-review.