cursor skills

8,064 tagged cursor, measured the same way as everything else here.

Browse within: copilot 276agentic-ai 251gemini-cli 240claudecode 199claudecode-skills 199ai-coding-assistant 168cjk 167ai-coding 140agent 133skills 107opencode 101cli 97mcp-server 89agents 87

continuous-discovery

673

luisabwk/kraken

Skill Cursor

Guide teams through building sustainable customer interview habits and discovery practices. Use when setting up weekly customer interviews, preparing interview guides, coaching story-based interviewing technique, synthesizing user research findings, planning assumption tests, or helping teams that say they don't have…

not rated 1 6mo ago A 60 tokens

auto-instrument

674

soleimanmansouri/debug-bank

Skill Claude CodeCodex

Fallback debugging when no pattern matches — hypothesis-driven code instrumentation with auto pattern extraction.

not rated 1 3mo ago A 19 tokens original MIT

core-CS

675

FuDie0915/Riper5-cursor-skills

Skill Claude CodeCursor

Skill "core-CS" from FuDie0915/Riper5-cursor-skills, covering riper-5 protocol core, protocol contract, invariants, deviation classification and thinking principles.

not rated 1 1mo ago A 25 tokens

budagov-lab/DreamTeam

Skill Cursor

Planner breaks goals into epics and dispatches Sub-Planner per epic. Planner does NOT create task files — Sub-Planner does.

not rated 1 5mo ago A 32 tokens original MIT

platform-api

677

MakingChatbots/genesys-cloud-skills

Skill Claude Code

Queries the Genesys Cloud Platform API schema for endpoint details, permissions, parameters, and response formats. Use when user asks about Genesys Cloud API endpoints (e.g., "/api/v2/assistants/queues"), API documentation, API permissions, schemas, capabilities, or when implementing Genesys Cloud operations.

not rated 1 6mo ago A 65 tokens original MIT

bumpup-versions

678

yu-iskw/coding-agent-fabric

Skill Claude Code

Consistently bump and synchronize versions across all packages in the monorepo using pnpm. Use this to ensure the root and all workspace packages share the same version number.

not rated 1 10d ago A 41 tokens original Apache-2.0

PhelipeG/daily_habits_app_angular_ia

Skill Claude CodeCodex

Use when profiling or optimizing this Angular 21 habits app for faster initial load, smaller bundles, smoother rendering, or reduced change-detection work. Covers route-level code splitting, @defer, signals/computed state, template hot paths, and validation of performance changes.

not rated 1 4mo ago A 59 tokens

model-loop

680

flowmar47/model-loop

Skill Claude CodeCodex

Four-phase cross-bench plan hardening (recon, interrogate, rival review, optional build + inspection). The harness this skill is invoked in (Cursor, Pi, Codex, Claude Code, AGY, …) is the planner — do not spawn a second planner. A different CLI — agy, Cursor CLI (agent), Codex, or Claude Code — attacks the locked plan…

not rated 1 changed 5d ago A 206 tokens

react-sentinel-debug

681

edgarbnt/ReactSentinel

Skill Claude CodeCodex

Use React-Sentinel when a task needs live browser or React runtime inspection rather than static code reading alone.

not rated 1 3mo ago A 26 tokens original MIT

codebase-auditor

682

Gladisintelligible706/vibe-driven-dev

Skill Claude CodeCodex

Scan a repository against curated coding standards and produce a structured audit report, issue set, refactor plan, and sprint-based remediation roadmap. Use when the user invokes /vibe.audit or asks to review the codebase against established rules. Operates in full autopilot mode from repository scan to sprint plan…

not rated 1 today A 68 tokens

azazhang/finance-literature-review-skill

Skill Cursor

Conduct finance-first literature reviews and related-work synthesis. Use when the user asks for a literature review, related literature section, annotated bibliography, gap map, journal-targeted reading list, finance or macro-finance paper scan, corporate finance or asset-pricing synthesis, banking or disclosure…

not rated 1 5mo ago A 104 tokens original MIT

Moeblack/subagent-orchestration-skill

Skill Codex

Coordinate multiple subagents or delegated workers for parallel research, adversarial review, multi-role review, project slicing, and approval loops. Use when a user asks for multiple agents, subagents, parallel review, cluster research, multi-agent validation, or iterative blocker convergence.

not rated 1 3mo ago A 61 tokens original MIT

awesome-agentic-stack

685

AkashPriyadarshii/awesome-agentic-stack

Skill Claude CodeCodex

Curated directory of 96 audited ₹0 workflow-first tools and agent skills for solo builders. Use when searching for agent skills, token savings, TUIs, mobile sync, and push-gate security.

not rated 1 1mo ago A 46 tokens original MIT

stannum2/letstalk-master

Skill Claude CodeCodex

Build or update privacy-first AI-assistant configuration and reusable preference skills for Codex, Claude Code, Cursor, Gemini CLI, and similar tools. Use when the user provides explicit preferences, existing config files, example rules, or asks to optimize AGENTS.md, CLAUDE.md, assistant rules, memory files, or…

not rated 1 1mo ago A 81 tokens original MIT

audio-verification

688

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Verify and debug synthesized audio (Web Audio API) by rendering it offline and measuring the samples, instead of guessing from code or claiming it works untested. Use whenever building, changing, or reviewing UI sound effects, tones, synths, or any AudioContext graph — and especially when sound is reported as…

not rated 1 13d ago A 117 tokens original MIT

refaelach/gmba-class-19-skills

Skill Claude CodeCodex

Generate a ready-to-paste GPT image prompt for an MBA classroom infographic — formula, framework, process, comparison, study sheet, or concept map. Output is a polished prompt formatted per the OpenAI gpt-image-2 prompting guide plus a fresh ChatGPT link to paste it into; this skill produces text, not images.…

not rated 1 4mo ago A 324 tokens original MIT

cf

690

leiseek/context-flow

Skill Claude Code

Use when switching AI coding tools (Claude Code, Codex, Cursor, OpenCode, Copilot CLI, Gemini CLI) due to rate limits, cost optimization, or model capability gaps. Triggers on "/cf save", "/cf load", "/cf status", "/cf diff", "/cf validate" commands. Also use when the user mentions losing context, repeating work…

not rated 1 3mo ago A 97 tokens

brandapp-sdk-install

691

reopt-ai/reopt-skills

Skill Claude CodeCodex

Install @reopt-ai/brandapp-sdk in a consumer project. Sets up Auth, OAuth, EAV (incl. 4.2 optimistic concurrency / atomic increments / TTL), Plans checkout, Files, analytics bridge, API routes, and env config. Triggers on "brandapp-sdk install", "brandapp-sdk init", "brandapp sdk setup", "brandapp sdk bootstrap"…

not rated 1 changed 5d ago A 105 tokens original MIT

research-route

692

Zaoqu-Liu/converge-skill

Skill Claude CodeCodex

Example Converge-compatible research route skill for current technical decisions.

not rated 1 3mo ago A 16 tokens original MIT

dragon-fish/config-file-versioning

Skill Claude CodeCodex

A local backup system for important configuration files, such as SSH or shell settings. It watches selected files and saves changed versions in separate Git histories.

not rated 1 4mo ago A 150 tokens original MIT

anki-expert

694

BENJAMINGLAI/anki-card-skill

Skill Claude CodeCodex

Generate high-quality Anki flashcards from user-provided text (inline, local .md/.txt/.pdf files, or URLs) and auto-export to .tsv, .apkg, or push directly via AnkiConnect. Trigger when the user mentions Anki, flashcards, spaced repetition, study cards, memory cards, make cards, help me memorize, or .apkg files.

not rated 1 today A 84 tokens copy · 100% MIT

loop-engineering

695

imMamdouhaboammar/loop-engineering-skill

Skill Claude CodeCodex

Use when designing, orchestrating, or executing autonomous multi-agent coding loops with financial budget caps, minimal fixes, and continuous dev-QA gates.

not rated 1 23d ago A 33 tokens original MIT

performance

696

cwklurks/ship-score

Skill Claude CodeCodex

You are running the Performance category of a Ship Score production readiness audit. Follow every instruction below precisely. Do not add checks beyond the 7 defined here. Do not skip checks. Report exactly what you find.

not rated 1 5mo ago A 0 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: