cursor ide skills

249 tagged cursor ide, measured the same way as everything else here.

Browse within: Code Generation 62kiro 591c-enterprise 55bsl 55cursor-ai 42cursor-rules 32codex-cli 30ai-agents-framework 20ai-automation 20cursor-plugin 20drift-detection 20addressables 18csharp 18dotfiles 17

epf-expert

02

Arman-Kudaibergenov/1c-ai-development-kit

Skill Claude CodeCodex

A Russian-language skill for working with 1C external processing files (EPF), including creating, building, unpacking, and adding forms or business-system commands.

157 3mo ago A 124 tokens AGPL-3.0

form-compile

03

Arman-Kudaibergenov/1c-ai-development-kit

Skill Claude CodeCodex

A tool for generating a controllable form from a JSON definition of its elements. It is intended for creating a new form with a known structure.

157 3mo ago A 76 tokens AGPL-3.0

3d-web-experiences

04

madebyaris/advance-minimax-m3-cursor-rules

Skill Claude CodeCodexCursor

Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…

125 2mo ago A 147 tokens original MIT

anti-slop-design

05

madebyaris/advance-minimax-m3-cursor-rules

Skill Claude CodeCodexCursor

Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…

125 2mo ago A 78 tokens original MIT

deep-research

06

madebyaris/advance-minimax-m3-cursor-rules

Skill Claude CodeCodexCursor

Conducts multi-step deep research on any topic using iterative search, reflection, and synthesis. Use when the user asks to research, investigate, survey, compare, analyze, deep-dive, or explore a topic in depth. Covers web research, codebase analysis, documentation review, mixed-source investigation, and M3…

125 2mo ago A 72 tokens original MIT

flue

07

SFKislev/Flue

Skill Claude CodeCodex

Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.

72 2mo ago A 36 tokens original MIT

Adobe

08

SFKislev/Flue

Skill Claude CodeCodex

Control Adobe desktop apps - Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition - from the shell via Flue, without an MCP server.

72 2mo ago A 34 tokens original MIT

Audition

09

SFKislev/Flue

Skill Claude CodeCodex

Control Adobe Audition from the shell via Flue - ExtendScript bridges without an MCP server.

72 2mo ago A 22 tokens original MIT

Vanyangyang/cursor-bridge

Skill Claude CodeCodex

Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grokexecute on activates, and continuously supervise that coding-agent session through a user-level Supervisor daemon as the user sends work, waits for completion, reconnects from another host task…

51 yesterday A 103 tokens original MIT

grok-executor-mode

11

Vanyangyang/cursor-bridge

Skill Claude CodeCodex

Task-local execution policy applied to ordinary user tasks only after an exact /grokexecute on; the host agent then plans, supervises, corrects, and verifies while all implementation and workspace-mutating execution goes through Grok Build Supervisor. Never activate or deactivate from ordinary requests, task text…

51 yesterday A 73 tokens original MIT

cursor-delegate

12

Vanyangyang/cursor-bridge

Skill Claude CodeCodex

Delegate bounded light-to-medium implementation, limited investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns the direction and risk boundaries. Use when a bounded Cursor pass can save primary-agent time, reduce omissions, or run alongside non-conflicting…

51 yesterday A 146 tokens original MIT

recallium-guidance

13

recallium-ai/recallium

Skill Claude CodeCodex

Use when you have access to Recallium MCP tools. Provides guidance on memory storage, search, and knowledge management. CRITICAL - invoke the MCP tool recallium at session start, store memories after EVERY substantive interaction, and honor global rules.

50 3mo ago A 57 tokens

maven-code-search

14

salitaba/maven-decoder-mcp

Skill Claude CodeCodex

Use the Maven Decoder MCP server to inspect code, APIs, methods, dependencies, versions, and usage examples from Maven artifacts installed in the user's local /.m2 repository. Use when working on Java, Maven, Gradle, Spring, Jakarta, Android, or JVM projects and the user asks about dependency internals, installed…

20 3mo ago A 95 tokens original MIT

doctor

17

qwerfunch/cladding

Skill Claude CodeCodex

Diagnose Cladding runtime health — Claude Code hook liveness and version, CI package pinning, lifecycle governance, and sentinel-miss frequency by phase × cause × fallback. Use when hooks may be silent, CI may float across Cladding releases, scan or run results look thinner than expected, or before tuning the host…

14 3d ago A 93 tokens original MIT

oracle

18

qwerfunch/cladding

Skill Claude CodeCodex

Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (clad oracle --required) demands — an empty worklist means don't author unless the user explicitly asks. YOU spawn a blind sub-agent from a spec-only brief, then record it. Activate only when the connected project contains…

14 3d ago A 82 tokens original MIT

reviewer

19

qwerfunch/cladding

Skill Claude CodeCodex

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

14 3d ago A 68 tokens original MIT

interview

20

NikhilSKashyap/interviewsignal

Skill Claude CodeCodex

AI-native interview platform. Type /interview to start a candidate session — captures all prompts, responses, tool calls, and file changes. Type /submit to end the session, seal the log, and send the full thought-process audit to the hiring manager.

10 3mo ago A 59 tokens

submit

21

NikhilSKashyap/interviewsignal

Skill Claude CodeCodex

End an active interviewsignal session: seal the log, push to GitHub, send to the hiring manager, and show the candidate their score summary.

10 3mo ago A 32 tokens

hashiiiii-git

22

hashiiiii/rules-for-ai

Skill Claude CodeCodex

Use this skill to name a Git branch or write a commit message.

10 21d ago A 20 tokens original MIT

hashiiiii-images

23

hashiiiii/rules-for-ai

Skill Claude CodeCodex

Use this skill to create project images, especially flat geometric images with a dark background and one accent color.

10 21d ago A 26 tokens original MIT

hashiiiii/rules-for-ai

Skill Claude CodeCodex

Use this skill to create or edit a GitHub pull request with the repository template or the default structure.

10 21d ago A 28 tokens original MIT