Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
2,3052,352 · page 49 / 62
nodejs-keccak256Prevent Ethereum hashing bugs in JavaScript and TypeScript. Node's sha3-256 is NIST SHA3, not Ethereum Keccak-256, and silently…mturacnote-itCapture implementation notes after code implementation and review/fix. Records design decisions, deviations, tradeoffs, and open…smallnestnsdi-review-processUse when interpreting where an NSDI submission stands — the per-deadline PC pipeline, the three-way outcome space of accept…brycewang-stanfordobsidian-cliInteract with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also…kepanoobsidian-cliUse the Obsidian CLI to read, create, search, and manage vault content, or to develop and debug Obsidian plugins and themes from…sickn33oee-calculatorOverall Equipment Effectiveness calculation and analysis skill with availability, performance, and quality trackinga5c-aiwritesoffer-letterDraft a job offer — the written offer letter and a verbal-offer script. Use when asked to write an offer letter, a job offer, an…mohitagw15856officecli-pitch-deckUse this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE…iOfficeAIoma-docsVerify documentation references against the current codebase, propose updates for diff-affected docs, detect i18n translation…first-flukeone-reportRun the full One-Report pipeline from one input file through grounding, research, evidence-rich report drafting, final review…gaotiexinquoopsla-review-processUse when explaining or strategizing around OOPSLA's two-round review machinery — double-anonymous multi-stage reviewing, the four…brycewang-stanfordopenclaw-parallels-smokeEnd-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex…SafeAI-Lab-Xopenclaw-pr-maintainerMaintainer workflow for reviewing, triaging, preparing, closing, or landing OpenClaw pull requests and related issues. Use when…SafeAI-Lab-Xopencode-gpt-reviewRun the `review-full-pr` skill on another model (github-copilot/gpt-5.4) via opencode, then thoroughly investigate and vet the…dyoshikawaopenspec-plus-designMANDATORY skill that activates whenever the OpenSpec design phase begins. Triggers: /opsx-new, /opsx-ff, or /opsx-continue runs…sudokaropenspec-plus-proposalMANDATORY skill that activates whenever the OpenSpec proposal phase begins. Triggers: /opsx-new, /opsx-ff, or /opsx-continue…sudokaropenspec-plus-specMANDATORY skill that activates whenever the OpenSpec specification phase begins. Triggers: /opsx-new, /opsx-ff, or /opsx-continue…sudokaropenspec-plus-tasksMANDATORY skill that activates whenever the OpenSpec tasks phase begins. Triggers: /opsx-new, /opsx-ff, or /opsx-continue runs…sudokaropenspec-verify-changeUse this skill at Step 7 of the v2 SOP to verify that all tasks in the active OpenSpec change are implemented and align with…charliehzmops-mergeAutonomous PR merge pipeline. Scans all repos for open PRs, dispatches subagents to fix CI, resolve conflicts, address review…davepoonwritesOrganizational Analysis and Design Report GeneratorGenerates a comprehensive organizational analysis report following a specific 9-step framework, including literature review…ECNU-ICALKorgsci-review-processUse when you want to understand how Organization Science review and decisions work before or after submitting — the decentralized…brycewang-stanfordorgstud-review-processUse when calibrating expectations for the Organization Studies (OS) review cycle — desk-screen odds, the developmental…brycewang-stanfordors-review-processUse when navigating the Operations Research (OR) editorial process — the departmental area-editor routing, the soft…brycewang-stanfordosdi-review-processUse when reasoning about how an OSDI paper is reviewed and decided — the double-blind HotCRP PC pipeline with no author-response…brycewang-stanfordosdi-workflowUse when planning or managing a full OSDI cycle — the December title-registration and submission deadlines on HotCRP, the silent…brycewang-stanfordoutlier-detection-and-quality-assessment执行全面的异常值检测与数据质量评估,利用 IQR 方法识别异常值并结合偏度、峰度分析数据分布特征,适用于非正态分布数据的预处理阶段。OpenSenseNovaoutline-before-proseOutline documents before drafting them — the argument skeleton that gets alignment cheaply, the one-line-per-section discipline…mohitagw15856page-seo-analysisAnalyze SEO for a single page. Use when: auditing on-page signals, schema, content quality, E-E-A-T, or AI search readiness.indranilbanerjeepalantir-debug-bundleCollect Palantir Foundry debug evidence for support tickets and troubleshooting. Use when encountering persistent Foundry issues…jeremylongshorepaper-critique-frameworkStructured framework for writing peer review reports and paper critiquesbrycewang-stanfordpaper-figureGenerate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"generate figures\"…brycewang-stanfordwritespaper-illustrationGenerate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams…brycewang-stanfordwritespaper-planGenerate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"paper…brycewang-stanfordwritespaper-polish-guideReview and polish LaTeX research papers for clarity and stylebrycewang-stanfordpaper-rebuttalGuides writing effective rebuttals after receiving peer review feedback. Covers review diagnosis (score-driven color-coding)…BioTender-maxpaper-self-reviseRevise an academic paper based on internal review comments. Reads review report or annotated manuscript, then applies revisions…brycewang-stanfordwritespaper-summarizerAgents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review…waybarriosparsifal-slr-guidePlan and manage systematic literature reviews with Parsifal platformbrycewang-stanfordpartner-performance-reviewWenn es um Partner Performance Review in Kanzlei Management geht: rechnet Schwellen, Beträge, Varianten und Kontrollannahmen…Klotzkettepatentlizenzvertrag-drafting-reviewWenn es um Patentlizenzvertrag DE/EN in patentrecht geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…Klotzkettepatentlizenzvertrag-reviewWenn es um Patentlizenzvertrag prüfen in patentrecht geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…Klotzkettepedagogy-reviewRun holistic pedagogical review on lecture slides. Checks narrative arc, student prerequisites, worked examples, notation…brycewang-stanfordwritespeer-reviewSystematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting…brycewang-stanfordwritespeer-review-guideConduct thorough, constructive peer reviews and evaluate research papersbrycewang-stanfordpeer-review-simulatorSkill for simulating peer review feedback on manuscriptsa5c-aiwritespercom-review-processUse when reasoning about how an IEEE PerCom research submission is evaluated, covering double-blind review, the three-TPC-member…brycewang-stanfordPerformance Appraisal Comment WriterGenerates professional self-assessment comments for performance appraisals based on specific goals or responsibilities provided…ECNU-ICALK
← Prev49 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going