agentsclimarketplace

Review & quality

19,040 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

  • Git finalize pr

    ainova-systems/intelligence-dev-packs/packs/core/skills/git-finalize-pr Skill

    2★ repo

    Drive the current branch's PR to merge-ready: CI green and every review comment handled, ending with an outcome label

  • Git merge pr

    ainova-systems/intelligence-dev-packs/packs/core/skills/git-merge-pr Skill

    2★ repo

    After owner accept: guard-checked squash-merge of the current branch's PR, base sync and branch cleanup

  • Git open pr

    ainova-systems/intelligence-dev-packs/packs/core/skills/git-open-pr Skill

    2★ repo

    Open a pull request for the current branch against its target, using the repo template

  • Git resolve conflicts

    ainova-systems/intelligence-dev-packs/packs/core/skills/git-resolve-conflicts Skill

    2★ repo

    Resolve merge or rebase conflicts semantically, then re-verify the full gates

  • Git review pr comments

    ainova-systems/intelligence-dev-packs/packs/core/skills/git-review-pr-comments Skill

    2★ repo

    Triage PR review comments: fix, discuss, or decline with reason - every thread answered

  • Git scan secrets

    ainova-systems/intelligence-dev-packs/packs/core/skills/git-scan-secrets Skill

    2★ repo

    Scan diff, tree, or branch history for committed credentials

  • Spec create

    ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-create Skill

    2★ repo

    Plan a change as a reviewable spec: grill the owner, then write requirements, plan, tasks - the review gate before execution

  • Truestack ci and delivery

    adtn0810/truestack/skills/truestack-ci-and-delivery Skill

    2★ repo

    Set up CI/CD and ship safely to a self-hosted server — pipeline stages (lint, type-check, test, build), SHA-pinned Actions, least-privilege workflow permissions and GitHub Actions secrets (runtime secrets/.env on the server belong to truestack-deploy-and-runtime), semver + CHANGELOG releases, and health-gated deploy with rollback. Use whenever the user says "set up CI", "set up CI/CD", "GitHub Actions workflow", "lint and tests on PR", "required status checks", "branch protection", "merge queue", "pin actions", "SHA pin", "workflow permissions", "GITHUB_TOKEN", "OIDC (keyless cloud/deploy credentials for workflows)", "cache dependencies", "Docker layer caching", "release automation", "semantic versioning", "bump the version", "generate changelog", "tag a release", "conventional commits", "the CI pipeline that ships a release to production", "health-gated deploy step", "rollback in CI", "smoke test before traffic", or "sequence a migration step in the deploy".

  • Truestack quality control

    adtn0810/truestack/skills/truestack-quality-control Skill

    2★ repo

    Run a deep quality-control sweep after ANY code change before the work is considered done — automatically once a feature or bugfix is implemented, and whenever the user asks to "check", "QC", or "verify" a code change or the work just done, or says "make sure it's solid". Use only AFTER the change exists — verifies, never implements; fix-first requests enter via truestack-orchestrate. Runs tests, type-check and lint, a multi-axis review, a load/perf check, a safety pass, an intent check, and a memory-reconciliation tally. Invoked by truestack-backend-development and truestack-root-cause-debugging; also runs on request.

  • Research pipeline

    sfrangulov/skills/research-pipeline Skill

    2★ repo

    Disciplined multi-source research pipeline that produces a verifiable, citation-backed report — orchestrated subagents, source-discipline, content-addressed snapshots, a deterministic→judge verification funnel, and a mandatory adversarial fact-check pass. Use when a deep-research document (best-practices canon, technology evaluation, claims that downstream code or decisions will lean on) must be source-grounded, fact-checked, and reproducible across sessions or machines — not a quick lookup. Explicit-invocation only.

  • Engifoundry review

    caoyuan-fire/engi-foundry-skill/skills/engifoundry-review Skill

    2★ repo

    Review EngiFoundry planning, Job work, code, documents, research, or other durable outputs in clean context and record pass, rework-required, or factual blocked conclusions.

  • Engifoundry verify

    caoyuan-fire/engi-foundry-skill/skills/engifoundry-verify Skill

    2★ repo

    Verify a jobs-completed EngiFoundry PAK against its complete task goal and acceptance criteria, record durable evidence, and identify the next applicable contract without accepting delivery.

  • Code reviewer

    rumotion/ai-agent-project-template/.cline/skills/code-reviewer Skill

    2★ repo

    Reviews code changes for correctness, maintainability, security, performance, tests, and adherence to project rules. Use when reviewing diffs, PRs, or completed agent work.

  • Exp service review

    guofu-shiqu/ux-expert-skills/skills/exp-service-review Skill

    2★ repo

    服务体验复盘。当一次服务事件结束后,需要进行系统复盘、提炼经验教训时调用。

  • Literature review

    Lord1Egypt/scientific-agent-toolkit/scientific-skills/literature-review Skill

    2★ repo

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

  • Peer review

    Lord1Egypt/scientific-agent-toolkit/scientific-skills/peer-review Skill

    2★ repo

    Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

  • Timesfm forecasting

    Lord1Egypt/scientific-agent-toolkit/scientific-skills/timesfm-forecasting Skill

    2★ repo

    Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

    The same file is in 3 other repositories

  • Wiki lint

    AIwork4me/open-llm-wiki/skills/wiki-lint Skill

    2★ repo

    Run a health check for an open-llm-wiki vault. Use when the user asks to lint, audit, validate, or periodically check wiki quality. The default mode is report-only: inspect schema compliance, QA coverage, links, stale claims, contradictions, and log health. Modify files only when the user explicitly requests fix mode or a scheduled automation has been configured to allow safe maintenance writes.

  • Writing commit messages

    gg-mo/repo-hygiene/skills/writing-commit-messages Skill

    2★ repo

    Use when drafting any commit message — sets format (imperative subject under 72 chars, explanatory body when the why isn't obvious from the diff) and prevents the "Fix X" one-liner reflex for non-trivial fixes

  • Lean pr

    r-irbe/proof-skills/skills/_overrides/lean-pr Skill

    2★ repo

    USE FOR: opening, titling, or labelling a PR against any Lean ecosystem repo (`leanprover/lean4`, `leanprover-community/mathlib4`, Cslib, or downstream projects), picking the right commit-message convention, applying upstream-specific labels (changelog-* for Lean core; t-* / easy / awaiting-author for Mathlib), running `lake exe mk_all` for Mathlib file renames, cross-linking dependent PRs. DO NOT USE FOR: in-tree proof review (use @lean-proof-review), Mathlib PR-review checklists (use `references/upstream/mathlib4-review.md`), writing the actual proof (use @lean-proof), building the change locally (use @lean-build), minimising an upstream-bug repro (use @lean-mwe). TRIGGERS: PR, pull request, "open a PR", changelog label, bors, maintainer-merge, `lake exe mk_all`, upstream filing.

  • Mathlib review

    r-irbe/proof-skills/skills/_overrides/mathlib-review Skill

    2★ repo

    REDIRECT — Mathlib PR review standards (attributes API, simp squeezing, normal forms, transparency, file size, naming/style URLs) have been demoted to `references/upstream/mathlib4-review.md`. Generic Lean proof review lives in `lean-proof-review`. This stub preserves the slug for Ctrl-F discoverability and incoming cross-references (per the zero-deletions Chesterton protocol).

  • Lean enforcement

    r-irbe/proof-skills/skills/lean-enforcement Skill

    2★ repo

    USE FOR: running programmatic CI / pre-review / post-review gates for a Lean 4 project — axiom audit, council precheck, review coverage, metric sync, zettelkasten lint, bridge validation, proof quality, ecosystem health, workflow gate enforcement. DO NOT USE FOR: semantic / judgement review (use @lean-proof-review or @lean-review-council); orchestrating the broader QA lifecycle (use @lean-quality-engine); routing tasks across skills (use @lean-gateway). TRIGGERS: enforcement, CI gate, axiom audit, council_precheck, workflow_gate, ecosystem_health, sorry check.

  • Lean proof review

    r-irbe/proof-skills/skills/lean-proof-review Skill

    2★ repo

    USE FOR: reviewing one Lean 4 proof / file for correctness, soundness, statement faithfulness, non-triviality, and proof quality; running the 4-layer verification checklist (formal soundness → statement → non-triviality → quality); flagging common Lean pitfalls; recommending tactic alternatives from the Mathlib + Aesop + Duper + Canonical stack. DO NOT USE FOR: writing a new proof (use @lean-proof); multi-agent council deliberation (use @lean-review-council); running CI scripts (use @lean-enforcement); scoring the whole project (use @lean-quality-engine). TRIGGERS: proof review, audit proof, verify Lean, 4-layer checklist, lean-pitfalls, proof quality.

  • Lean quality engine

    r-irbe/proof-skills/skills/lean-quality-engine Skill

    2★ repo

    USE FOR: assessing overall Lean 4 project quality across seven dimensions (soundness, faithfulness, completeness, novelty, elegance, integration, documentation); preparing for milestones; orchestrating QA gates that wrap enforcement scripts, council reviews, coverage tracking, and health monitoring. DO NOT USE FOR: running a single enforcement script (use @lean-enforcement); reviewing one proof (use @lean-proof-review); council deliberation itself (use @lean-review-council); writing retros (use @lean-retro-methodology). TRIGGERS: QA, quality gate, milestone check, project health, qa-engine, quality score, QA lifecycle.

  • Lean review council

    r-irbe/proof-skills/skills/lean-review-council Skill

    2★ repo

    USE FOR: orchestrating a 5-member Lean 4 proof review council (Σ Kernel Guardian, Φ Statement Oracle, Ν Novelty Scout, Λ Quality Architect, Ω Integration Sentinel); running RALPH (Review-Analyze-Learn-Plan-Handle) loops at member / council / project / meta scales; structured voting with structured-disagreement-resolution (SDR); council topology selection (Star / Pipeline / Mesh / Hierarchical / Swarm / Ring / Hub-Spoke); maximum-parallel agent dispatch with cascading completion handlers; specification lifecycle (requirements → design → docs); inter-council collaboration; Zettelkasten knowledge synthesis; calibration scoring; enforcement tactics. DO NOT USE FOR: reviewing one Lean proof in isolation (use @lean-proof-review); writing a proof (use @lean-proof); running CI scripts (use @lean-enforcement); single-skill council convocation when no multi-layer review is needed (use the relevant skill directly). TRIGGERS: review council, RALPH loop, council vote, SDR, council topology, kernel guardian, statement oracle, novelty scout, quality architect, integration sentinel, meta-council, council session.

  • Python secure coding

    konstruktoid/agent-instructions-skills/skills/python/python-secure-coding Skill

    2★ repo

    Authors and modifies Python source code with security best practices that static analysis alone does not fully cover, including input handling, deserialization, secrets, subprocess/SQL/crypto usage, SSRF, and dependency hygiene, layered on the ruff/ty quality gate. Use when writing or editing Python, and especially for changes touching user input, subprocess/OS calls, SQL or other query construction, templating, cryptography, secrets/credentials, or access control.

  • Cavecrew

    john-data-chen/hermes-agent-backup/skills/cavecrew Skill

    2★ repo

    Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

  • Caveman commit

    john-data-chen/hermes-agent-backup/skills/caveman-commit Skill

    2★ repo

    Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

  • Caveman review

    john-data-chen/hermes-agent-backup/skills/caveman-review Skill

    2★ repo

    Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

    The same file is in 11 other repositories

  • Github code review

    john-data-chen/hermes-agent-backup/skills/github/github-code-review Skill

    2★ repo

    Review PRs: diffs, inline comments via gh or REST.

    The same file is in 1 other repository

  • Github pr workflow

    john-data-chen/hermes-agent-backup/skills/github/github-pr-workflow Skill

    2★ repo

    GitHub PR lifecycle: branch, commit, open, CI, merge.

    The same file is in 1 other repository

  • Requesting code review

    john-data-chen/hermes-agent-backup/skills/software-development/requesting-code-review Skill

    2★ repo

    Pre-commit review: security scan, quality gates, auto-fix.

    The same file is in 1 other repository

  • Word diet

    brenbuilds1/cutweight/skills/word-diet Skill

    2★ repo

    Puts the agent's replies on a word diet. Compressed output that cuts reply tokens by roughly a third to half, more on ultra, while keeping full technical accuracy. Answers like a cornerman between rounds: only what changes the next round. Adds source discipline: verify current-year, recent, latest, changing, risky, or source-sensitive facts before confident answers. Use when user says word-diet, corner mode, cornerman, less tokens, fewer tokens, low tokens, be brief, or /word-diet. Also auto-triggers when token efficiency or fresh source verification is requested.

  • Secure code review

    xAmirHamza77/PenKit51/skills/secure-code-review Skill

    no license2★ repo

    安全代码审查的专业技能和方法论

  • Commit message

    TeamDzX/myllm-skills/skills/commit-message Skill

    2★ repo

    Write a Conventional Commits message from a description of code changes. Use when the user asks for a commit message or describes a diff.

  • Generate pr description

    kimgoetzke/coding-agent-configs/skills/generate-pr-description Skill

    2★ repo

    Generates a concise pull request description from a PR or the current branch. Use only when explicitly invoked by the user to draft PR text.

  • Grill me

    kimgoetzke/coding-agent-configs/skills/grill-me Skill

    2★ repo

    Grilling session that challenges a plan against the existing domain model (or helps to create one), 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.

  • Review pr

    kimgoetzke/coding-agent-configs/skills/review-pr Skill

    2★ repo

    My personal skills, agents, and other configuration files for agentic coding.

  • Grill gaps

    Vladick-Pick/business-ontology/skills/grill-gaps Skill

    2★ repo

    Use when open ontology gaps block a decision. Asks one focused question at a time, with a recommended answer and a fixed question budget.

  • Code analyzer

    maurigre/mgr-method/skills/code-analyzer Skill

    no license2★ repo

    Rigorous TWO-AXIS code reviewer. Standards - does the code follow THE PROJECT's rules guide (docs/sdd/09-review-rules.md)? Spec - did the code fulfill its originating spec/PRD (did it do what was asked)? The two are measured separately and reported side by side; a reproval is always anchored in a textual citation (a guide rule OR a spec line) - it never invents. Use when the user asks to review code, analyze conformity, do a code review, check whether the code follows the standards or fulfilled the spec, or when spec-create suggests a review at the end of a feature. Agnostic to architecture and language.

  • Finishing a development branch

    oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/finishing-a-development-branch Skill

    no license2★ 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

  • Receiving code review

    oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/receiving-code-review Skill

    no license2★ 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

    oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/requesting-code-review Skill

    no license2★ repo

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

  • Using git worktrees

    oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/using-git-worktrees Skill

    no license2★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

  • Verification before completion

    oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/verification-before-completion Skill

    no license2★ 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

  • Wrap up

    oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/wrap-up Skill

    no license2★ repo

    Lightweight end-of-phase checkpoint. Use after completing a task or feature to update backlog, changelog, commit, and move to the next item. For branch-based workflows with merge/PR, use finishing-a-development-branch instead.

  • Complete implementation

    lil-lon/.claude/skills/complete-implementation Skill

    2★ repo

    Complete an implementation end-to-end: stage targeted changes, run `codex-review`, fix any P1/P2 findings (loop up to 3×), commit using Conventional Commits, then push. Use when the user asks to finalize, ship, wrap up, or "complete" the current implementation.

  • Gh cli

    lil-lon/.claude/skills/gh-cli Skill

    2★ repo

    Use the GitHub CLI (`gh`) to fetch information from GitHub: issues, PRs, comments, reviews, workflow runs, repos, and search. A curated set of read-only `gh` subcommands and read-only `gh api` endpoints are pre-approved and run without prompts. The sandbox lets `gh *` reach the network unsandboxed. Write operations (anything that changes state on GitHub) are NOT pre-approved and MUST NOT be executed unless the user explicitly asks for that write. Even when explicitly requested, run the natural command and let the harness's approval prompt fire — NEVER reshape the command to evade pattern matching. Use this skill whenever you need information from GitHub. Proactively invoke it (do NOT answer from memory or prior conversation) when the user references a GitHub issue, PR, review, comment, action run, or repo, or asks things like "show me the comments", "what's in PR #N", "what did the reviewer say".

  • Qcheck

    3awny/qship/templates/skills/qcheck Skill

    2★ repo

    Review code changes for correctness, security, and convention adherence — the general-purpose code reviewer. Use on a diff or recent changes before committing or opening a PR to catch bugs, risky patterns, and style violations; the central review step in the qship pipeline.

  • Qcheckf

    3awny/qship/templates/skills/qcheckf Skill

    2★ repo

    Review a single function in depth — signature, parameters, edge cases, error handling, and whether it does one thing well. Use when you want a focused critique of one function (not a whole diff), e.g. a complex or hot-path routine you're about to ship.

  • Qcheckt

    3awny/qship/templates/skills/qcheckt Skill

    2★ repo

    Review test code for coverage and quality — are the right behaviors tested, edge cases included, assertions meaningful, and tests free of tautologies/flakiness. Use when reviewing or writing tests for a change; qship runs it as a dedicated reviewer in the Phase-2 review fan-out.

  • Qship

    3awny/qship/templates/skills/qship Skill

    2★ repo

    Full Jira-ticket → PR pipeline (plan, implement, review, test, ship). Supports parallel and epic-mode execution. Two independent engine knobs — `provider=claude|codex` chooses the Step 7 implementer (default Claude Opus 4.7 1M, medium reasoning), and `reviewer=claude|codex` chooses the Phase 2 reviewer (default Claude). Most useful combination beyond defaults is `provider=claude reviewer=codex` (Opus implements, gpt-5.5 high reasoning hunts bugs) — different model families catch different defects.

  • Qshipmaster

    3awny/qship/templates/skills/qshipmaster Skill

    2★ repo

    Epic-level orchestrator for qship. Takes a Jira Epic ID, builds a topologically-sorted wave plan from its children, spawns one qship-persist.sh per ticket per wave in parallel, merges each wave into a consolidated epic branch, runs a lightweight wave-gate after each wave (migration check + targeted tests + 2 bug hunters + qbcheck, blocks only on Critical) and ONE full epic-level Phase 2 review after the last wave on the cumulative diff, and ships ONE consolidated PR per repo. Two engine knobs — `provider=claude|codex` chooses the Step 7 implementer (default Opus 4.7 1M, medium), and `reviewer=claude|codex` chooses the Phase 2 reviewer (default Claude). The diversified combo `provider=claude reviewer=codex` runs Opus implementing + gpt-5.5 high reviewing for different-family second opinion. Set `QSHIP_PER_WAVE_REVIEW=full` to restore full Phase 2 per wave, or `=none` to skip per-wave review entirely. Resumable, state-driven, idempotent.

  • Code review and quality

    vignesh2027/AI-AGENT-SKILLS/skills/code-review-and-quality Skill

    2★ repo

    Conduct staff-engineer-level code reviews across correctness, security, performance, readability, and architecture

  • Git workflow and versioning

    vignesh2027/AI-AGENT-SKILLS/skills/git-workflow-and-versioning Skill

    2★ repo

    Branching strategy, commit discipline, PR hygiene, and semantic versioning

  • Evaluate

    jvalin17/agent-toolkit/skills/evaluate Skill

    2★ repo

    Comprehensive quality grading. Checks prompt compliance, code quality, security, test coverage, architecture fitness. Produces a percentage score. Not lenient. Keywords: evaluate, grade, check, verify, validate, scorecard, quality, percentage, score, how good

  • Precommit

    jvalin17/agent-toolkit/skills/precommit Skill

    2★ repo

    Quality gate before every commit. Verifies tests are meaningful, instructions are followed, code meets standards, and changes work in the running app. Keywords: commit, push, pre-commit, quality, check, verify, ready, standards, before commit, gate

  • Reviewer

    jvalin17/agent-toolkit/skills/reviewer Skill

    2★ repo

    Review code, test coverage, runtime, accessibility, dependencies, UI quality. Keywords: review, test, coverage, quality, a11y, smoke test, validate, audit

  • Verify

    jvalin17/agent-toolkit/skills/verify Skill

    2★ repo

    Verify changes actually work and output is useful. Session health check, output quality, user confirmation. Keywords: verify, test, check, does it work, QA, validate, is it right, output quality

  • Release gate

    wakqasahmed/ai-engineering-workflow-skills/skills/engineering/release-gate Skill

    2★ repo

    Check deployment, staging, rollback, and health verification before release. Use for user-facing, infrastructure, CI/CD, integration, or high-risk changes.