NeVibeCode · 2,595 skills
Skills for Claude Code, Codex and Cursor
SKILL.md folders the agent loads on its own when a task matches the description.
agent-decision-receipts Mints tamper-evident, post-quantum-signed receipts for agent actions like deploys or payments. Lets you verify autonomous decisions offline from the certificate alone.
Claude Code
44installs
agent-memory Replaces bloated CLAUDE.md files with a four-tier memory store. The agent promotes facts across sessions only when they recur over multiple days.
Claude Code
42installs
supabase-postgres-best-practices
official A rule set for Postgres performance, maintained by Supabase. Useful when your agent writes queries, designs schemas or digs into a slow database.
CX Codex GP ChatGPT
40installs
supabase-postgres-best-practices
official Supabase guidelines for Postgres performance optimization. Helps developers write SQL queries, design database schemas, and configure RLS.
CX Codex GP ChatGPT
40installs
tugboat
official A GitHub Copilot skill for stalled, high-stakes tasks under stress. It keeps the original goal intact and relies on verified evidence.
GitHub Copilot
11installs
shopify-review-triage
official Turns pasted public Shopify App Store reviews into a P0-P3 brief. Use it to sort low-star feedback and decide which reported issues need attention first.
GitHub Copilot
11installs
react-three-fiber-game
official Structures React-hosted 3D browser games and scenes using React Three Fiber and the pmndrs stack.
CX Codex GP ChatGPT
39installs
security-scan
official Runs a single-pass security audit on a repository or selected path. Use it for a general review when there is no diff to inspect.
CX Codex GP ChatGPT
39installs
resx-source-generator-migration
official This skill moves a project from checked-in .Designer.cs files for .resx resources to a source generator. Use it when replacing the existing typed-resource generation setup.
GitHub Copilot
10installs
migrating-oracle-to-postgres-data-access-code
official Moves .NET/C# data-access code from Oracle to PostgreSQL with Npgsql. Use it while migrating an application's code layer alongside its database.
GitHub Copilot
10installs
stripe-best-practices
official Integration guide for Stripe in Codex: covers Checkout Sessions, Connect Accounts v2, tax setup, and restricted API keys.
CX Codex GP ChatGPT
36installs
figma-use
official This skill sets out how to use the Figma Plugin API through use_figma. It helps when an agent needs to change a Figma file or inspect its structure programmatically.
CX Codex GP ChatGPT
36installs
stripe-best-practices
official This skill guides Stripe API choices for payments, subscriptions, marketplaces, and financial accounts. Use it when building or reviewing a Stripe integration.
CX Codex GP ChatGPT
36installs
meetings Prices a meeting in dollars, decides whether it should happen at all, builds a timeboxed agenda, and turns raw notes into owned action items.
Claude Code
37installs
figma-generate-design
official Builds or updates composed Figma screens using design system components and styles. Use it to turn application pages or dialogs from code into Figma views.
CX Codex GP ChatGPT
33installs
figma-generate-library
official Skill to build a professional design system in Figma from your codebase. Creates variables, components with variants, typography styles and theming in the correct order — from tokens to finished components.
CX Codex GP ChatGPT
32installs
threat-model
official Builds repository threat models, maps trust boundaries, and outputs threatmodel.md in Codex.
CX Codex GP ChatGPT
32installs
design-system Captures brand identity via a 10-question wizard and validates WCAG 2.2 AA contrast. It derives 12 CSS tokens in HSL for markdown-html converters.
Claude Code
33installs
compliance-os This skill selects applicable frameworks, maps shared controls, and builds a combined audit and evidence plan for multi-framework programs.
Claude Code
33installs
figma-design-to-code
official Guides an agent through implementing a Figma node in a project’s existing stack. Use it before calling get_design_context.
CX Codex GP ChatGPT
30installs
triage-finding
official Triages external security reports against repository code and SECURITY.md policies, assigning static-evidence verdicts without modifying files.
CX Codex GP ChatGPT
30installs
security-diff-scan
official Reviews pull requests, commits, and local diffs for security vulnerabilities. Catches risks in modified and deleted code before merging.
CX Codex GP ChatGPT
30installs
deep-work Schedules focus blocks of 90 minutes or more, caps deep demand at 4 hours, and tracks weekly focus sessions.
Claude Code
31installs
aims-audit Runs a six-question ISO/IEC 42001 internal audit check for AI Management Systems. Helps verify readiness before stage 1 audits or when onboarding models.
Claude Code
31installs
ai-act-readiness This skill runs an AI system through six EU AI Act questions and helps classify risk, company role, transparency duties, and the conformity route before EU deployment.
Claude Code
31installs
chatgpt-app-submission
official Inspects a ChatGPT Apps MCP server and prepares the submission JSON. Use it before review to collect app info, test cases, and findings.
CX Codex GP ChatGPT
29installs
validation
official This skill checks whether candidate security findings hold up. Use it to validate findings from discovery, not to start a full repository scan.
CX Codex GP ChatGPT
29installs
deep-security-scan
official This skill runs multiple independent security scans across your entire repository or a scoped path, aggregates findings, and generates a complete report. Use it when standard scanning needs more depth and confidence.
CX Codex GP ChatGPT
29installs
dashboards-and-real-time-visualization
official Designs dashboards and live data visualization systems. Helps structure streaming data, refresh rates, mobile interruptions, and rendering budgets.
CX Codex GP ChatGPT
29installs
memory-engineering This skill designs and audits agent memory, prices the write path, and enforces forgetting rules. Use it when a CLAUDE.md or memory store keeps growing.
Claude Code
29installs
book-to-skill Turns books and documentation folders into structured agent knowledge with chapter files, a glossary, patterns, and decision rules. Use it when you want an agent to apply ideas from your source files while working.
Claude Code
29installs
vercel-sandbox
official This skill runs user-generated and AI-generated code inside an ephemeral Vercel Sandbox. Use it for browser automation and code checks that should stay outside the main environment.
CX Codex GP ChatGPT
27installs
fix-finding
official Resolves confirmed security vulnerabilities through targeted, validated patches. Useful when you need to close an exploit path without breaking existing APIs.
CX Codex GP ChatGPT
27installs
attack-path-analysis
official Evaluates plausible security findings in Codex and ChatGPT, traces paths from source to sink, and calibrates severity against the repository threat model.
CX Codex GP ChatGPT
27installs
gdpr-audit-prep Runs a six-question DPO interrogation citing GDPR articles. Prepares teams for annual privacy reviews, breach responses, and regulatory inquiries.
Claude Code
28installs
track-findings
official This skill moves validated Codex Security findings into Linear, Jira, or GitHub. Use it when scan results are reviewed and ready for controlled tracking.
CX Codex GP ChatGPT
26installs
canva-branded-presentation
official Creates on-brand Canva presentation decks from briefs, raw outlines, or design links. Useful when you need slides formatted to your brand kit.
CX Codex GP ChatGPT
26installs
data-visualization
official This skill routes web visualization tasks, from chart selection to maps, software diagrams, and exports. Use it when an agent needs to plan or review a data visualization.
CX Codex GP ChatGPT
26installs
loop-library A skill that mines your codebase and coding threads for work done more than once, then turns it into a bounded agent loop with checks and a stop condition.
Claude Code
27installs
memory-status Reports how full your project memory is, which topic files exist, and which references point at files that are gone. Useful once the agent starts losing context.
Claude Code
27installs
2,361–2,400 of 2,595