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
kjuhwa/skills-hub/skills/workflow/ship Skill
0★ repoShip workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)
kjuhwa/skills-hub/skills/workflow/squash-merge-detection-union Skill
0★ repoClassify "can this branch be cleaned up?" using the union of `git branch --merged` + `git cherry` patch-equivalence + `gh pr list` state, with clear semantics for each signal.
Swagger spec baseline from git
kjuhwa/skills-hub/skills/workflow/swagger-spec-baseline-from-git Skill
0★ repoRe-run spec-based optimization workflow on a clean branch without running the Spring Boot app — restore prior baseline artifacts (swagger-before.json + scripts) via `git show <sha>:<path>` from the commit on another branch that already captured them.
kjuhwa/skills-hub/skills/workflow/worktree-isolation-resolver Skill
0★ repoResolve which git worktree a workflow should run in using an ordered chain (existing ref → same-workflow reuse → linked-issue share → PR branch adoption → create new), each step guarded by worktree-ownership verification against the canonical repo path.
Aryan1718/developer-agent-skills/skills/git-rebase-help Skill
0★ repoUse this skill when the user invokes `git-rebase-help`, mentions rebasing a branch, asks how to bring a branch up to date, or needs mid-rebase conflict help. Triggers on: "git-rebase-help", "rebase this branch", "bring this branch up to date", "mid-rebase conflict help", or similar Git rebase workflow requests. Guide the workflow step-by-step through repository checks, target branch selection, working tree preparation, conflict resolution, and post-rebase cleanup, with confirmation required before any history-rewriting, content-changing, or destructive Git action.
Ref sp agents verification discipline
swiftpostlabs/agentic-tools/.agents/skills/ref-sp-agents-verification-discipline Skill
0★ repoShareable skills and tools for AI agents
swiftpostlabs/agentic-tools/.agents/skills/ref-sp-dev-git-commits Skill
0★ repoReference guidance for grouping changes into focused commits and writing clear commit messages. Use when: deciding how to split changes into commits, writing a commit title or body, deciding whether a commit needs a long description, or documenting an automated command for reproducibility.
swiftpostlabs/agentic-tools/.agents/skills/tool-sp-commit Skill
0★ repoInspect edited files, group them into logical commits, and create focused commits. Use when: the user asks to commit changes, split work into focused commits, or decide how the current diff should be grouped before committing.
Tool sp handle agents local tasks
swiftpostlabs/agentic-tools/.agents/skills/tool-sp-handle-agents-local-tasks Skill
0★ repoRead the local `.agents/tasks/` workspace — the `TODO.md` notes list and the tracked task folders under `new/`, `open/`, `closed/` — choose the next actionable item, and work it through with code changes, validation, folder moves, and status updates. Use when: the user asks to check `.agents/tasks/TODO.md`, continue remaining local tasks, or process the repo's local agent-task backlog.
fxckcode/skills-kit/skills/git-setup-skill Skill
0★ repoPrepares Git/GitHub repositories with .gitignore, .gitattributes, README files, licensing, metadata, tags, releases, and GitHub Actions. Use when the user wants to set up or professionalize a repository, add documentation or licensing, configure CI, or prepare releases and repo metadata.
fxckcode/skills-kit/skills/loop-engineering Skill
0★ repoDesign and implement autonomous agent loops for multi-agent software development. Maker-checker split, nested SDD cycles, worktree isolation, verification layers, and iteration budgets. Use when building systems where AI agents collaborate autonomously on software projects.
fxckcode/skills-kit/skills/verification-loop Skill
0★ repoStructured 7-phase verification system for code changes: Build → Type → Lint → Test → Spec → Security → Smoke. Use after completing any feature, before PR, or when the agent needs to systematically verify a change.
zhangxiangbei/ai-agent-skills/skills/quality-review Skill
no license0★ repoAI Agent skills and workflows for a research-driven solo AI company.
Gowrav-M/agent-skillguard/examples/skills/safe-code-reviewer Skill
0★ repoRead-only code review workflow for local repositories.
Komluc/agent-skills-production/skills/release-review Skill
no license0★ repoPrepares a complete release review by comparing the previous git tag with main. Use when work is complete and ready for a release candidate. Do not use for intermediate reviews during active development. Requires git in PATH.
LuchoC-Dev/agent-kits/skills/branch-pr Skill
no license0★ repoPR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
LuchoC-Dev/agent-kits/skills/git-commit Skill
no license0★ repoExecute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
LuchoC-Dev/agent-kits/skills/sdd-verify Skill
no license0★ repoValidate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.
asdlem/pr-workflow/skills/mr-pr-template-workflow Skill
no license0★ repoPrepare and optionally create GitLab merge requests or GitHub pull requests with project-native templates, repository language/style consistency, preview-before-submit, and safe gh/glab CLI handling. Use when the user asks to prepare, write, preview, create, submit, or open an MR/PR, merge request, pull request, or review-ready branch.
Debt collection validation preflight
oceanfsdfsvfdsvs/practical-agent-skills/debt-collection-validation-preflight Skill
0★ repoPreflight debt collection validation and dispute packets before a consumer, caregiver, financial counselor, legal-aid intake helper, or benefits advocate responds to a collector, debt buyer, collection agency, or collection law firm. Use when the user needs to check validation notices, 30-day dispute timing, collector identity, original-creditor requests, amount/itemization gaps, not-mine or paid-debt evidence, continued collection after a timely dispute, time-barred-debt review, redaction risks, and owner next steps without making live payments, filing complaints, or giving legal conclusions.
oceanfsdfsvfdsvs/practical-agent-skills/workslop-review Skill
0★ repoReview AI-generated workplace drafts before they create downstream rework. Use when a user asks whether an AI-written email, report, brief, PRD, proposal, meeting summary, slide outline, analysis, or handoff is ready to send, needs repair, lacks evidence, contains hallucinated claims, or feels like "workslop".
rbr7/MedClawMini/skills/drug-target-validation Skill
0★ repoComprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ MedToolkit tools. Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?"
rbr7/MedClawMini/skills/literature-deep-research Skill
0★ repoConduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves official IDs (Ensembl/UniProt), synonyms, naming collisions, and gathers expression/pathway context before literature search. Default deliverable is a report file; for single factoid questions, uses a fast verification mode and may include an inline answer. Use when users need thorough literature reviews, target profiles, or to verify specific claims from the literature.
rbr7/MedClawMini/skills/literature-review Skill
0★ repoConduct 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.).
rbr7/MedClawMini/skills/medical-imaging-review Skill
0★ repoWrite comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray, ultrasound, or pathology imaging. Triggers on requests for "review paper", "survey", "literature review", "systematic review", or mentions of writing academic reviews on deep learning for medical imaging.
Ml model validation regulatory
rbr7/MedClawMini/skills/ml-model-validation-regulatory Skill
0★ repoValidate, document, and monitor clinical machine-learning models for governance and regulatory readiness (Software as a Medical Device / SaMD). Covers validation protocols, model cards and intended-use statements, Good Machine Learning Practice (GMLP), IEC 62304 software lifecycle and ISO 14971 risk management for AI, performance and subgroup acceptance criteria, and post-deployment drift/performance monitoring. Use to take a trained model from notebook to a documented, auditable, monitored production asset.
rbr7/MedClawMini/skills/ontology-validator Skill
0★ repoValidate material sample annotations and data structures against ontology constraints. Use when checking if CMSO annotations are correct, verifying that required properties are present, or validating that object property relationships have consistent domain and range. Catches unknown classes, unknown properties, domain mismatches, and missing required fields.
rbr7/MedClawMini/skills/prior-auth-review-skill Skill
0★ repoAutomate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization decisions.
The same file is in 4 other repositories
rbr7/MedClawMini/skills/simulation-validator Skill
0★ repoValidate simulations before, during, and after execution. Use for pre-flight checks, runtime monitoring, post-run validation, diagnosing failed simulations, checking convergence, detecting NaN/Inf, or verifying mass/energy conservation.
The same file is in 3 other repositories
rbr7/MedClawMini/skills/slurm-job-script-generator Skill
0★ repoGenerate SLURM `sbatch` job scripts and sanity-check HPC resource requests (nodes, tasks, CPUs, memory, GPUs) for simulation runs. Use when preparing submission scripts, deciding MPI vs MPI+OpenMP layouts, standardizing `#SBATCH` directives, or debugging job launch configuration (`sbatch`/`srun`).
The same file is in 3 other repositories
SID-SURANGE/cursor-team-ops/skills/community/security-hardening Skill
0★ repoApply security-first practices when building or reviewing code — input validation, secrets management, auth checks, OWASP Top 10 coverage. Triggered by "security review", "harden this", "is this secure", "security-hardening", "check for vulnerabilities", "audit my code", "run a security check", "is there anything unsafe here", "check for SQL injection", "check for XSS", "are there any security issues".
SID-SURANGE/cursor-team-ops/skills/core/commit-history-audit Skill
0★ repoAudit a branch's full commit history for commit hygiene — WIP commits, squash candidates, merge commit policy violations, subject length, and optional convention compliance — before opening a PR. Triggered by "audit my commits", "check commit history before PR", "are my commits clean", "commit-history-audit".
SID-SURANGE/cursor-team-ops/skills/core/commit-message Skill
0★ repoEnforce Conventional Commits discipline — infer type (feat/fix/refactor/…) and scope from the staged diff and changed file paths, and produce a structured `type(scope): subject` message. Goes beyond basic AI commit generation by applying CC rules and scope inference. Triggered by "write a commit message", "what should I commit this as", "help me commit", "what should my commit say", "commit msg", "suggest a commit message", "how do I phrase this commit", "write a good commit", "commit-message".
SID-SURANGE/cursor-team-ops/skills/core/env-drift-check Skill
0★ repoDetect environment drift — mismatches between .env.example, CI environment matrix, Docker base images, and the lockfile runtime — so "works on my machine" failures are caught before they hit staging or production. Triggered by "env drift", "check my environment", "why does it work locally but not in CI", "env-drift-check", "environment mismatch".
SID-SURANGE/cursor-team-ops/skills/core/minimal-diff-review Skill
0★ repoReview a set of code or document changes for scope creep, convention drift, and quality issues following team standards. Use when the user asks to "review my changes", "check the diff", "look at what I changed", "is this good to go", "sanity check my code", "does this look right", "review before I push", "quick review", or before a PR is created. Also use proactively after large edits to check nothing went out of scope.
SID-SURANGE/cursor-team-ops/skills/core/pr-review-canvas Skill
0★ repoGroup PR changes by purpose, flag risky sections, and produce a reviewer map so the reader doesn't parse raw diff. Triggered by "review canvas", "map this PR", "help me review this PR", "understand this PR", "what does this PR change", "walk me through this PR", "review this diff", "what should I focus on in this PR", "pr-review-canvas".
SID-SURANGE/cursor-team-ops/skills/core/pr-summary Skill
0★ repoCreate a pull request with a clear title, summary, and test plan using the gh CLI. Use when the user asks to open a PR, create a pull request, "push and PR", "submit for review", "raise a PR", "write PR description", "write the PR", "I'm ready to merge", "open a pull request", "create PR", "submit my work". Analyzes all commits in the branch, not just the latest.
SID-SURANGE/cursor-team-ops/skills/core/pre-commit-check Skill
0★ repoCheck staged changes before creating a git commit. Reviews the diff for secrets, unrelated changes, debug code, oversized PRs, and matches the repo's commit message style. Use when the user says "commit", "create a commit", "git commit", "commit this", "commit my changes", "ready to commit", "safe to commit", "check my changes", "stage and commit", "push my work", or "I'm done with this task".
SID-SURANGE/cursor-team-ops/skills/core/requirements-qa Skill
0★ repoQuality-check requirements, BRD, discovery, and understanding documents for invented content, open questions, and source conflicts. Use when working in docs/, requirements/, or BRD files; when the user asks to review a discovery question list, update a master doc, check a requirements file, or verify accuracy against source PDFs. Also use when asked "did we capture this correctly?" about any requirements document.
PARS-DOE/doe-skills/pars-json-tools Skill
no license0★ repoTools and utilities for working with PARS CPP JSON files - validation, conversion to Excel, schema reference, and DIQ definition lookup. Use when asked to validate, convert, or analyze PARS JSON data, when the user needs information about PARS CPP data format or schema, or when looking up a specific DIQ (Data Integrity and Quality) check.
vibesec-advisory/skills/skills/mcp-security-review Skill
no license0★ repoUse when reviewing an MCP server, MCP tool, connector, local bridge, hosted integration, or agent tool catalog before connecting it to an assistant, granting credentials, or allowing read/write actions.
vibesec-advisory/skills/skills/vibe-check Skill
no license0★ repoUse when a user needs a fast preflight review of an AI output, workflow, prompt, automation idea, agent action, policy draft, or tool proposal for safety, quality, bias, business risk, and obvious governance gaps before wider use.
fengluisobel/ask-dongfeng-hermes/skills/github/github-code-review Skill
0★ repoReview PRs: diffs, inline comments via gh or REST.
fengluisobel/ask-dongfeng-hermes/skills/github/github-pr-workflow Skill
0★ repoGitHub PR lifecycle: branch, commit, open, CI, merge.
fengluisobel/ask-dongfeng-hermes/skills/software-development/requesting-code-review Skill
0★ repoPre-commit review: security scan, quality gates, auto-fix.
SystemicVoid/agentic-research-skills/skills/review-data-pipeline Skill
0★ repoAudit experiment specs and empirical pipelines for claim-threatening validity and reproducibility failures.
hifizz/skills/skills/creem-merchant-review Skill
0★ repo对「Chrome 扩展 + 官网 + 订阅计费」形态的产品,在提交 Creem(MoR 支付商户)审核前做一次可重复的上线前自查,产出一份带 ✅/⚠️/❌/❓ 判定的 Markdown 自查报告。Use when the user wants to check whether an extension+website product can pass Creem / payment-merchant / MoR review before submitting, or asks for a "过审自查 / 商户审核 / Creem review" report.
unliftedq/agents/android-dev/skills/gplay-cli-usage Skill
no license0★ repoThe cross-cutting conventions every gplay command shares — credential/account resolution order, package targeting and `.gplay/` pinning, output formats (table/json/markdown), semantic exit codes, the `--dry-run`/`--confirm` safety gates, stdout-is-data/stderr-is-logs, and the Edit lifecycle (implicit per-command, or explicit `edits begin/commit/discard` transactions). Use when running or designing any gplay command, wiring gplay into CI, branching on its exit codes, introspecting the Android Publisher API surface offline with `gplay schema`, or building a more specific gplay workflow on top of these rules.
unliftedq/agents/hyperframes/skills/hyperframes-cli Skill
no license0★ repoHyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.
The same file is in 1 other repository
unliftedq/agents/impeccable/skills/impeccable Skill
no license0★ 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 1 other repository
Finishing a development branch
unliftedq/agents/superpowers/skills/finishing-a-development-branch Skill
no license0★ repoUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
The same file is in 10 other repositories
unliftedq/agents/superpowers/skills/receiving-code-review Skill
no license0★ repoUse 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
The same file is in 28 other repositories
unliftedq/agents/superpowers/skills/requesting-code-review Skill
no license0★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
The same file is in 11 other repositories
unliftedq/agents/superpowers/skills/using-git-worktrees Skill
no license0★ repoUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
The same file is in 13 other repositories
Verification before completion
unliftedq/agents/superpowers/skills/verification-before-completion Skill
no license0★ repoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
The same file is in 40 other repositories
unliftedq/agents/winui-dev/skills/pr-review Skill
no license0★ repoMulti-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness, payload/provenance/tests, docs & manifest sync, plus a multi-model cross-check. Reports findings to stdout. Does NOT apply fixes.
The same file is in 1 other repository
unliftedq/agents/winui-dev/skills/winui-code-review Skill
no license0★ repoCode quality review for WinUI 3 apps — MVVM compliance, x:Bind correctness, accessibility, theming, security, and performance. Use before committing to catch issues that the compiler and UI tests won't find.
The same file is in 1 other repository
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/Ar9av__PaperOrchestra/skills/literature-review-agent Skill
no license0★ repoStep 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the related work", or "build the bibliography".
The same file is in 2 other repositories
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/Ar9av__PaperOrchestra/skills/plotting-agent Skill
no license0★ repoStep 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
The same file is in 3 other repositories
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/Boom5426__Nature-Paper-Skills/skills/review/paper-reviewer Skill
no license0★ repoUse when acting as a journal or grant reviewer and writing formal reviewer-side evaluations focused on methodology, statistics, reporting standards, reproducibility, and constructive feedback.