cursor skills

8,086 tagged cursor, measured the same way as everything else here.

Browse within: copilot 276agentic-ai 251gemini-cli 226claudecode 199claudecode-skills 199ai-coding-assistant 161cjk 160ai-coding 140agent 138skills 107cli 95opencode 93mcp-server 89agents 87

degausai/wonda-slides

Skill Claude CodeCodex needs its repo

Turn notes (Notion, Google Docs, Markdown) into branded 1920×1080 HTML slide decks with PDF and PNG export. Pulls real brand tokens from any URL.

not rated 2 4mo ago A 41 tokens original MIT

explain-codebase

602

suryast/free-ai-agent-skills

Skill Claude CodeCodex

Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points, frameworks, and dependencies — then produces a "start here" guide for new contributors.

not rated 2 29d ago A 42 tokens original MIT

spec-herdr-review

603

stewartcelani/skills

Skill Claude CodeCodex

Run visible multi-agent spec reviews in Herdr through interactive agent CLIs such as Claude, Codex, Copilot/GLM, or Grok/Composer. Supports two modes — a spec review (the design, before implementation) and an implementation review (the implemented diff vs the spec, after the calling model has built it). Ask for…

not rated 2 1mo ago A 88 tokens original MIT

agent-master

604

Surya8991/AgentMaster

Skill Claude CodeCodex

Meta-orchestrator that classifies tasks and routes to the right combination of installed skills across caveman (output compression), superpowers (dev workflow), anthropic-skills (business/domain expertise), and wired tactical libraries (wshobson, davila7, impeccable, anthropic-official). 26 routing categories…

not rated 2 1mo ago A 136 tokens original MIT

browser-qa

605

liatrio-labs/ai-prompts

Skill Codex

Use when you need lightweight browser QA for a web page, local HTML file, or app: inspect console errors, broken assets, keyboard/focus behavior, viewport readability, and publish evidence-backed findings JSON through a local HTML report viewer.

not rated 2 yesterday A 51 tokens original Apache-2.0

coding-standards

606

nnkogift/personal-skills

Skill Claude CodeCodex

Gift's personal coding standards, file structure conventions, and project setup rules. ALWAYS load this skill when starting a new project, scaffolding files, setting up a repo, writing new components, creating hooks, naming functions, structuring folders, composing UI, or any time code organization or architecture is…

not rated 2 1mo ago A 76 tokens

omnirebuttal

607

Iayce/omnirebuttal

Skill Claude CodeCodex

Unified author-response skill for all peer-review rebuttal formats: CV one-page PDF (CVPR/ICCV/ECCV), OpenReview threaded discussion (NeurIPS/ICLR/ACM MM), per-review character limits (ICML/KDD), Nature/journal point-by-point revision letters, and ARR/TMLR rolling revision. Routes by venue artifact family after shared…

not rated 2 3mo ago A 163 tokens original MIT

chinese-dev

608

huafenchi/openclaw-cn

Skill Claude CodeCodex

A development guide for working with Chinese-language requests. It sets conventions for Chinese comments, documentation, error explanations, and English names for Chinese concepts.

not rated 2 6mo ago A 0 tokens original MIT

dora-measurement

609

paruff/uFawkesAI

Skill Claude CodeCodex needs its repo

Compute the four DORA delivery metrics from uFawkesObs (Prometheus + Loki). Use when producing monthly DORA snapshots, validating post-release metric trends, or generating ROI evidence. Requires uFawkesObs running. Implements DORA AI Capabilities 2 and 7.

not rated 2 17d ago A 64 tokens original MIT

skillcraft

610

cloudroad-io/skillcraft

Skill Claude CodeCodex

Skill "skillcraft" from cloudroad-io/skillcraft, covering skillcraft, install, or: pip install skillcraft, commands and how it works.

not rated 2 1mo ago A 0 tokens original MIT

code-change-impact

611

mghareeb/code-change-impact

Skill Claude CodeCodex

Trace the impact (blast radius) of a code change in ANY codebase and prove it didn't break anything else — language- and framework-agnostic. Use RIGHT AFTER a fix to a feature, function, module, type, route, API endpoint, schema, or config, before committing, opening a PR, or pushing. Triggers: "did this break…

not rated 2 2mo ago A 238 tokens original MIT

plan

612

HumanDealer/vibeproof

Skill Claude CodeCodex

Turn docs/PRD.md into docs/PLAN.md — an ordered, checkbox build plan with architecture, risk gates, and a test list. Use after /spec, before any code. The plan survives session compaction; conversation context does not.

not rated 2 3mo ago A 52 tokens original MIT

code-agnostic

614

dhvcc/code-agnostic

Skill Claude CodeCodex

Work on code-agnostic, the CLI that centralizes MCP servers, rules, skills, agents, and workspace config, then compiles and syncs them into Codex, Cursor, and OpenCode. Use when editing this repo, explaining how code-agnostic works, or changing its config compiler, import, plan, apply, status, workspace, rule, skill…

not rated 2 26d ago A 87 tokens GPL-3.0

less-is-more

615

oddyblue/Less-Is-More-Skill

Skill Codex

Architecture-first, reduction-first workflow for code changes, debugging, refactoring, and cleanup. Use to trace the owning path, prefer no edit and subtraction before additions, replace obsolete behavior instead of layering around it, keep scope closed, refute your own diagnosis and fix before believing them, verify…

not rated 2 29d ago A 75 tokens original MIT

e2e-tests

616

GlamgarOnDiscord/claude-saas-blueprint

Skill Claude Code needs its repo

Tests E2E Playwright pour SaaS Next.js : setup, Page Object Model, auth state, flows critiques (login, billing, onboarding), CI GitHub Actions.

not rated 2 3mo ago A 40 tokens original MIT

web-shaders

618

owenob1/web-shaders-agent-kit

Skill Claude CodeCodex

Use when writing, debugging, or reviewing shaders for the web — GLSL or WGSL, raw WebGL2/WebGPU, Three.js (ShaderMaterial/RawShaderMaterial/TSL), or React Three Fiber. Covers the language/platform matrix, correct boilerplate, common effects (SDF/raymarching, noise, post-processing), and the pitfalls that make browser…

not rated 2 1mo ago A 83 tokens original MIT

aenv

619

Blevene/aenv

Skill Claude CodeCodex

Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…

not rated 2 3mo ago C 176 tokens original MIT

codereview

620

ivanhoinacki/team-exp-claude-config

Skill Claude Code

Review code quality with all 18 dimensions. Analyzes diff, gathers deep context, checks Known Gotchas, presents findings grouped by severity. If a PR exists, posts inline comments on GitHub. Use when the user says "code review", "review this PR", "review PR", "review", "pre-review", "check quality", or before opening…

not rated 2 1mo ago A 80 tokens original MIT

debug

621

nphausg/ai-agent-skills

Skill Claude Code

Structured debugging assistant. Use /debug to get a guided diagnosis of any bug — Claude will ask the right questions and then pinpoint the root cause.

not rated 2 1mo ago A 31 tokens original Apache-2.0

agent-config-setup

622

ofershap/create-agent-config

Skill Claude CodeCodex

Generate AI agent config files for any project — Cursor, Claude Code, Copilot, Windsurf, Cline, AGENTS.md. Use when setting up a new project for AI agents.

not rated 2 6d ago A 43 tokens original MIT

personetta-set-active

623

EdwardAF-IT/Personetta

Skill Claude CodeCodex

Switches the active Personetta persona via set-active. The target tool is auto-detected from the host agent (Claude Code here), so no --format is needed. Use when the user asks to change recipe, switch persona, or set active role.

not rated 2 10d ago A 56 tokens original MIT

create-mr

624

encoreshao/encore-skills

Skill Claude CodeCodex

Create a GitLab Merge Request — clear title, high-level summary of what was changed and why, explicit confirmation the issue is resolved.

not rated 2 20d ago A 30 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: