Review & quality
19,181 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
buildinternet/uploads/skills/uploads-cli Skill
21★ repoReference for the uploads CLI and its stdio/hosted MCP tools — exact flags, keys, and contracts for put and attach, screenshot capture, stable PR/issue keys, the managed attachments comment, metadata and search, galleries, config defaults, login/doctor, and output formats. Use when driving the `uploads` CLI or its MCP tools (including the hosted MCP at agents.uploads.sh for agents without local filesystem/git access), when you need a public URL for a local file ("upload this", "host this image", "give me a public URL for this file"), when the CLI itself prints a hint or nudge you need to act on (a `hint` field in `--format json`, or the stderr note suggesting `--pr`/`attach --branch`), or when you need exact flags, key layouts, or setup and auth details. For the when-and-how of getting a screenshot or recording into a GitHub PR or issue, start with the github-screenshots skill — it defers here for CLI detail.
Clientell-Ai/salesforce-skills/skills/sf-eval Skill
21★ repoEvaluate and benchmark Salesforce skill quality. Compares AI-generated code with vs without skill context, scores against a Salesforce-specific rubric (security, governor limits, bulkification, patterns, completeness), and produces a comparison report. Use to run benchmarks, verify skill value, or check Apex code quality. Activate on mentions of "evaluate skills", "benchmark", "skill quality", "run eval", or "compare with/without skills".
The same file is in 2 other repositories
icerain-cmd/humanities-superpowers/skills/responding-to-peer-review Skill
21★ repoUse when authors must interpret real reviewer comments, decide how to revise a humanities manuscript, and produce a transparent point-by-point response grounded in actual changes.
agents-inc/skills/dist/plugins/shared-tooling-biome/skills/shared-tooling-biome Skill
20★ repoBiome v2 unified linter, formatter, and import organizer — single Rust-powered tool replacing ESLint + Prettier with 97% Prettier compatibility and 20x faster performance
Shared tooling eslint prettier
agents-inc/skills/dist/plugins/shared-tooling-eslint-prettier/skills/shared-tooling-eslint-prettier Skill
20★ repoESLint 9/10 flat config with defineConfig(), Prettier v3.0+ shared config, eslint-config-prettier integration, typescript-eslint v8+ projectService
agents-inc/skills/dist/plugins/shared-tooling-git-hooks/skills/shared-tooling-git-hooks Skill
20★ repoHusky v9 setup, lint-staged v16 patterns, commitlint with conventional commits, CI/production handling, monorepo setup, migration from v8
agents-inc/skills/dist/plugins/web-forms-zod-validation/skills/web-forms-zod-validation Skill
20★ repoZod schema validation patterns for TypeScript - schema definitions, type inference, refinements, transforms, discriminated unions
agents-inc/skills/src/skills/shared-tooling-biome Skill
20★ repoBiome v2 unified linter, formatter, and import organizer — single Rust-powered tool replacing ESLint + Prettier with 97% Prettier compatibility and 20x faster performance
Shared tooling eslint prettier
agents-inc/skills/src/skills/shared-tooling-eslint-prettier Skill
20★ repoESLint 9/10 flat config with defineConfig(), Prettier v3.0+ shared config, eslint-config-prettier integration, typescript-eslint v8+ projectService
agents-inc/skills/src/skills/shared-tooling-git-hooks Skill
20★ repoHusky v9 setup, lint-staged v16 patterns, commitlint with conventional commits, CI/production handling, monorepo setup, migration from v8
agents-inc/skills/src/skills/web-forms-zod-validation Skill
20★ repoZod schema validation patterns for TypeScript - schema definitions, type inference, refinements, transforms, discriminated unions
kennethkhoocy/applied-micro-skills/plugins/applied-micro/skills/annotator-input-parity-check Skill
20★ repoBefore designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
kennethkhoocy/applied-micro-skills/plugins/applied-micro/skills/lit-review-orchestrator Skill
20★ repoMaster controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing an article — a full manuscript, an abstract, or a proposal — and it extracts a search plan, runs Undermind (an automated Playwright driver in Classic mode) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Only use this skill when explicitly requested — e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.
The same file is in 1 other repository
kennethkhoocy/applied-micro-skills/plugins/applied-micro/skills/llm-gold-bound-failure-check Skill
20★ repoDiagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes. Use when: (1) a scoring pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the weak label was already low (κ < ~0.6). Core check: if gold POSITIVES share the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).
arezous/pm-pilot/.claude/skills/critique Skill
20★ repoPressure-test a document (PRD, strategy, pitch, positioning) against your product context. Finds gaps, weak logic, and unvalidated assumptions.
ironlint/ironlint/adapters/claude-code/skills/ironlint-review Skill
20★ repoReviews ironlint check health from the telemetry log. Use when the user says "review my ironlint checks", "check health", "which ironlint checks are noisy", "find dead ironlint checks", "ironlint review", or asks for an audit of .ironlint.yml.
TobiasBlask/open-paper-machine/scientific-skills/literature-review Skill
20★ 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.).
The same file is in 1 other repository
TobiasBlask/open-paper-machine/scientific-skills/peer-review Skill
20★ repoStructured 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.
The same file is in 4 other repositories
TobiasBlask/open-paper-machine/skills/peer-review-engine Skill
20★ repoActivate when the user wants to simulate a double-blind peer review of their paper before submission or before sharing with co-authors. Reads the current draft (draft.md or paper.tex), generates 2 independent reviewer reports in the style of top IS/CS conferences (ICIS, ECIS, MISQ level), and saves the output as simulated_reviews.md. The output is formatted to serve as direct input for /respond-reviewers (review-engine feedback loop).
TobiasBlask/open-paper-machine/skills/review-engine Skill
20★ repoActivate when the user provides reviewer or co-author feedback (annotated PDF, pasted comments, or reviewer report) and wants to implement revisions. Extracts review points, maps them to paper.tex locations, classifies actions, implements changes, recompiles, and generates a change log + latexdiff. Handles the full revision loop from feedback to committed changes.
TobiasBlask/open-paper-machine/skills/submission-engine Skill
20★ repoActivate when the user wants to prepare a paper for submission to a specific venue. Handles venue-specific formatting validation, anonymization checks for double-blind review, cover letter generation, suggested reviewer identification, and submission checklist completion. Produces a submission-ready package.
TobiasBlask/open-paper-machine/skills/verification-engine Skill
20★ repoActivate when the user needs to verify citations, check source accuracy, or validate that referenced papers actually support the claims attributed to them. Retrieves source abstracts and full text (for open-access papers), compares each citation claim against actual source content, and produces a structured verification report with classifications (VERIFIED, PLAUSIBLE, MISMATCH, UNVERIFIABLE, NOT FOUND).
Youchu-lawhub/cn-litigation-toolkit/skills/case-review Skill
no license20★ repo收到裁判文书后的研析与复盘——三级覆盖:庭审复盘(庭后五维效果分析)、裁判文书研析报告(主体/诉请与判决/请求权/事实查明/说理/裁判结果六维 + 逐页比对事实认定与证据采信、提炼胜败因)、结案复盘报告(结案报告十项 + 四维反思)。两种深度:自办案件(调取台账/事实梳理/过程文书做深度复盘)与非自办/受限信息(仅基于用户提供的裁判文书与有限信息),输出面向客户/法务领导/业务部门汇报。触发词:复盘、裁判文书分析、判决分析、研析判决、结案报告、结案复盘、办案总结、庭审复盘、败诉分析。
Youchu-lawhub/cn-litigation-toolkit/skills/legal-verification Skill
no license20★ repoAI法律引用准确性核验闸门——自动抽取文中法规/法条/案例引用,经法律检索后端(元典或北大法宝,运行时自动适配+多家灾备)与权威来源逐条比对,输出"准确/时效风险/语义不一致/未命中"判定。本套件所有文书生成技能在产出正式文件前必须先过此闸门;亦可由用户独立调用核验任意文本。触发词:法律引用核验、核验法条、核验引用、复核、核查。
devnomad-byte/cosmosmith/plugins/cosmosmith/skills/cosmosmith-governance-review Skill
20★ repoReview Cosmosmith artifacts, task ledgers, generated project rules, and skill outputs for coherence, layer separation, missing evidence, and rule drift. Use before marking Cosmosmith planning or implementation tasks done, after spec generation, or when project rules and generated rules may have diverged.
krzysztofsurdy/code-virtuoso/skills/knowledge/git-workflow Skill
20★ repoGit workflow patterns and version control best practices for teams of any size. Use when the user asks to choose a branching strategy (trunk-based, GitHub Flow, Git Flow, GitLab Flow), define commit conventions, set up PR workflows, plan release management, structure a monorepo, or establish team git standards. Covers branch naming, merge vs rebase, conventional commits, semantic versioning, changelog generation, and protected branch policies.
Verification before completion
krzysztofsurdy/code-virtuoso/skills/knowledge/verification-before-completion Skill
20★ repoEvidence-based completion discipline. Use before claiming any work is 'done', complete, finished, or ready — whether it is code, config, documentation, a migration, or a bugfix. Requires running verification commands (tests, lints, type checks, builds, smoke tests), capturing output, and citing concrete evidence rather than assertions. Covers tiered definitions of done, evidence patterns, verification checklists by task type, and common fake-completion failure modes. Triggers: 'done', 'finished', 'complete', 'ready', 'should work', 'it's working now', before closing a task, before writing a PR.
krzysztofsurdy/code-virtuoso/skills/playbooks/finishing-branch Skill
20★ repoEnd-to-end workflow for finishing a development branch. Use when implementation is complete and the branch is ready to ship - runs verification checks, reviews the diff, picks the integration path (direct merge, pull request, squash-and-merge, stacked PR), writes the PR/merge message, pushes to the remote, and cleans up branches and worktrees. Covers rebase vs merge vs squash decisions, pre-push checklists, stacked-branch handling, and recovery from common missteps like force-pushing the wrong branch or deleting an unmerged branch. Triggers: 'I'm done', 'ready to merge', 'ready to push', 'ready for review', 'wrap up this branch', 'finish this up'.
krzysztofsurdy/code-virtuoso/skills/roles/qa-engineer Skill
20★ repoAgent team role for quality assurance and test management. Use when the user asks to create test plans, design test cases, perform exploratory testing, write bug reports, verify fixes, define test coverage requirements, or sign off on releases. Owns the quality gate — translates requirements and acceptance criteria into structured test strategies across the delivery pipeline.
krzysztofsurdy/code-virtuoso/skills/tools/pr-message-writer Skill
20★ repoWrite comprehensive pull request messages with structured technical documentation, testing instructions, and verification queries. Framework-agnostic with customizable templates. Use when writing or generating a PR description, preparing a pull request for review, or documenting code changes for teammates.
teixasalone/UnrealEngine5-Skills/skills/ue5-debug-validation Skill
20★ repoUE5.6/UE5.7 debugging and validation workflow for logs, asset checks, and regression triage. Use when requests involve troubleshooting why gameplay does not work, validating expected output, narrowing minimal repro, and producing concrete fix steps.
galyarderlabs/galyarder-framework/integrations/antigravity/adversarial-reviewer Skill
20★ repoUse when a plan, feature, or launch needs an explicit adversarial pass to find weak assumptions, abuse cases, or strategic blind spots before execution.
galyarderlabs/galyarder-framework/integrations/antigravity/code-review-expert Skill
20★ repoUse when legacy prompts or older framework flows reference `code-review-expert` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/antigravity/code-reviewer Skill
20★ repoUse when legacy prompts or older framework flows reference `code-reviewer` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/antigravity/contract-review Skill
20★ repoAnalyze and red-flag contracts systematically, identifying risks, unfavorable terms, and negotiation opportunities
galyarderlabs/galyarder-framework/integrations/antigravity/doc-maintenance Skill
20★ repoAudit top-level documentation (README, SPEC, PRODUCT) against recent git history to find drift shipped features missing from docs or features listed as upcoming that already landed. Proposes minimal edits, creates a branch, and opens a PR. Use when asked to review docs for accuracy, after major feature merges, or on a periodic schedule.
Finishing a development branch
galyarderlabs/galyarder-framework/integrations/antigravity/finishing-a-development-branch Skill
20★ 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
galyarderlabs/galyarder-framework/integrations/antigravity/galyarder-cto Skill
20★ repoAssume the role of Galyarder CTO (Chief Technology Officer). Technical guardian. Enforce technical integrity, architectural determinism, self-healing formal verification, and planetary computational leverage.
galyarderlabs/galyarder-framework/integrations/antigravity/pr-review-expert Skill
20★ repoUse when legacy prompts or older framework flows reference `pr-review-expert` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/antigravity/receiving-code-review Skill
20★ 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
galyarderlabs/galyarder-framework/integrations/antigravity/requesting-code-review Skill
20★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
galyarderlabs/galyarder-framework/integrations/antigravity/review Skill
20★ repoReview Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".
galyarderlabs/galyarder-framework/integrations/antigravity/security-reviewer Skill
20★ repoUse when legacy prompts or older framework flows reference `security-reviewer` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/antigravity/using-git-worktrees Skill
20★ repoUse when legacy prompts or older framework flows reference `using-git-worktrees` and you need the modern runtime to resolve that capability cleanly.
Verification before completion
galyarderlabs/galyarder-framework/integrations/antigravity/verification-before-completion Skill
20★ 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
galyarderlabs/galyarder-framework/integrations/claude-code/skills/adversarial-reviewer Skill
20★ repoUse when a plan, feature, or launch needs an explicit adversarial pass to find weak assumptions, abuse cases, or strategic blind spots before execution.
galyarderlabs/galyarder-framework/integrations/claude-code/skills/code-review-expert Skill
20★ repoUse when legacy prompts or older framework flows reference `code-review-expert` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/claude-code/skills/code-reviewer Skill
20★ repoUse when legacy prompts or older framework flows reference `code-reviewer` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/claude-code/skills/contract-review Skill
20★ repoAnalyze and red-flag contracts systematically, identifying risks, unfavorable terms, and negotiation opportunities
galyarderlabs/galyarder-framework/integrations/claude-code/skills/doc-maintenance Skill
20★ repoAudit top-level documentation (README, SPEC, PRODUCT) against recent git history to find drift shipped features missing from docs or features listed as upcoming that already landed. Proposes minimal edits, creates a branch, and opens a PR. Use when asked to review docs for accuracy, after major feature merges, or on a periodic schedule.
Finishing a development branch
galyarderlabs/galyarder-framework/integrations/claude-code/skills/finishing-a-development-branch Skill
20★ 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
galyarderlabs/galyarder-framework/integrations/claude-code/skills/pr-review-expert Skill
20★ repoUse when legacy prompts or older framework flows reference `pr-review-expert` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/claude-code/skills/receiving-code-review Skill
20★ 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
galyarderlabs/galyarder-framework/integrations/claude-code/skills/requesting-code-review Skill
20★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
galyarderlabs/galyarder-framework/integrations/claude-code/skills/review Skill
20★ repoReview Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".
galyarderlabs/galyarder-framework/integrations/claude-code/skills/security-reviewer Skill
20★ repoUse when legacy prompts or older framework flows reference `security-reviewer` and you need the modern runtime to resolve that capability cleanly.
galyarderlabs/galyarder-framework/integrations/claude-code/skills/using-git-worktrees Skill
20★ repoUse when legacy prompts or older framework flows reference `using-git-worktrees` and you need the modern runtime to resolve that capability cleanly.
Verification before completion
galyarderlabs/galyarder-framework/integrations/claude-code/skills/verification-before-completion Skill
20★ 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
galyarderlabs/galyarder-framework/integrations/codex/skills/adversarial-reviewer Skill
20★ repoUse when a plan, feature, or launch needs an explicit adversarial pass to find weak assumptions, abuse cases, or strategic blind spots before execution.
galyarderlabs/galyarder-framework/integrations/codex/skills/code-review-expert Skill
20★ repoUse when legacy prompts or older framework flows reference `code-review-expert` and you need the modern runtime to resolve that capability cleanly.