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
2,5452,592 · page 54 / 62
Refactor C++ Request Method for Lambda CallbackModifies the HttpAdapter Request method signature to accept a std::function callback for handling HttpResponse objects…ECNU-ICALKrefactorIntelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.code-yeongyuRefactor Decompiled C Code to C99Transforms decompiled C code (e.g., from Ghidra or IDA Pro) into clean, readable C99 code by replacing generic variable names…ECNU-ICALKRefactor decompiled code to clean C99Converts provided C code snippets (typically decompiled) into clean, readable C99 code with improved variable names and…ECNU-ICALKrefactorSurgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables…githubRefactor Java null checks using Spring ObjectUtilsRefactor Java code to replace standard null checks and string comparisons with org.springframework.util.ObjectUtils utility…ECNU-ICALKRefactor loops to Pandarallel parallel processingConverts sequential Python loops into parallelized code using the `pandarallel` library, handling DataFrame conversion, function…ECNU-ICALKrefactor-method-complexity-reduceRefactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by…githubrefactorCode refactoring workflow - analyze → plan → implement → review → validateparcadeirefactor-planCreate a concrete plan before starting a multi-file refactor. Use when the user asks to plan, sequence, scope, or safely execute…githubRefactor Python code without if/else keywords or dictionariesRewrites Python functions to eliminate 'if' and 'else' keywords and dictionary usage, ensuring the output is a properly indented…ECNU-ICALKRefactor Python loops to use Pandarallel for parallel processingConverts sequential Python loops iterating over lists into parallelized operations using the pandarallel library, ensuring…ECNU-ICALKrefactoring-patternsSystematic refactoring techniques, code smell elimination, pattern extraction, and legacy modernizationcosmicstack-labsrefactoring-planPlan a safe, incremental refactor of messy code without changing behavior. Use when code needs restructuring, is hard to change…mohitagw15856referee-reportGenerate academic referee reports for economics/finance papers, followed by a 150-word letter to the editor with recommendation…brycewang-stanfordwritesregister-qualitaetsgate-vor-einreichungWenn es um Quality Gate vor Einreichung in Handelsregister Praxis geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzketteregression-tableFormats estimation output as a publication-quality regression table with stars, SEs, and fit statistics. Use when creating a…brycewang-stanfordwritesreleaseCut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every…hyhmrrightremove-ai-slopsRemove AI-generated code smells (slop) from branch changes or an explicit file list. Locks behavior with regression tests FIRST…code-yeongyureplit-advanced-troubleshootingDebug hard Replit issues: container lifecycle, Nix build failures, deployment crashes, and memory leaks. Use when standard…jeremylongshorereplit-debug-bundleCollect Replit diagnostic info for debugging deployments, workspace issues, and support tickets. Use when encountering persistent…jeremylongshorereports-on-progress-in-physicsUse when targeting Reports on Progress in Physics (RoPP) or deciding whether a physics review manuscript fits this IOP…brycewang-stanfordrequest-refactor-planCreate a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan…stevesolunrequesting-code-reviewUse this skill at Step 8 of the v2 SOP after Verify passes, to request and receive a code review from a Reviewer-Agent (or human…charliehzmrequirements-quality-analyzerSpecialized skill for analyzing and scoring requirements quality against BABOK and IEEE 29148 standardsa5c-aiwritesresearch-ethics-irbNavigate institutional review board processes, informed consent, confidentiality, and ethical considerations in human subjects…a5c-aiwritesresearch-ethics-irb-navigationPrepare ethics applications, develop informed consent protocols, and navigate institutional review processes for human subjects…a5c-aiwritesresearch-ideationEnd-to-end research ideation pipeline: literature grounding → multi-track idea generation (3 personas…BioTender-maxwritesresearch-litSearch and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work"…brycewang-stanfordwritesresearch-on-economics-and-managementUse when targeting 《经济与管理研究》(Research on Economics and Management — 首都经济贸易大学主办的经管交叉月刊, 1980 创刊, 北大核心/CSSCI, 不收费) or deciding…brycewang-stanfordresearch-pipelineFull research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research…brycewang-stanfordwritesresearch-refineTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via…brycewang-stanfordwritesresearch-reviewGet a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get…brycewang-stanfordwritesresearch-surveyGenerates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type…BioTender-maxresearch-town-guideSimulate human research communities with multi-agent AI collaborationbrycewang-stanfordresignation-letterWrite a resignation letter that closes a chapter without burning it — short, warm, legally clean, and silent on everything that…mohitagw15856resolve-pr-commentsThis skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR…fcakyonrespol-review-processUse when calibrating expectations and choreography for the Research Policy (RP) review cycle — the double-blind process, the…brycewang-stanfordrestat-identificationUse when the causal-identification or measurement strategy is the bottleneck for a The Review of Economics and Statistics…brycewang-stanfordrestat-literature-positioningUse when the marginal contribution of a The Review of Economics and Statistics (REStat) manuscript against the closest prior work…brycewang-stanfordrestat-rebuttalUse when a The Review of Economics and Statistics (REStat) decision letter (R&R or reject-and-resubmit) has arrived and the…brycewang-stanfordrestat-referee-strategyUse when anticipating the objections a The Review of Economics and Statistics (REStat) referee will raise for a given design, and…brycewang-stanfordrestat-robustnessUse when the headline estimate of a The Review of Economics and Statistics (REStat) manuscript needs to survive specification…brycewang-stanfordrestat-tables-figuresUse when building or revising the exhibits of a The Review of Economics and Statistics (REStat) manuscript so the main result is…brycewang-stanfordrestat-theory-modelUse when deciding how much theory or structure a The Review of Economics and Statistics (REStat) manuscript should carry —…brycewang-stanfordrestat-topic-selectionUse when deciding whether an applied-economics project fits The Review of Economics and Statistics (REStat) rather than AER /…brycewang-stanfordrestat-workflowUse when deciding which restat-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through…brycewang-stanfordrestat-writing-styleUse when revising the prose of a The Review of Economics and Statistics (REStat) manuscript — especially the abstract and…brycewang-stanford
← Prev54 / 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