Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Architecture patterns for AI agents that communicate over email -- why agents need dedicated inboxes rather than human email accounts, infrastructure/provider tradeoffs, one-inbox-per-agent, two-way conversation loops, human-in-the-loop drafts, WebSocket vs webhook event design, multi-agent topologies, OTP flows, and…
joeseesun/qiaomu-music-player-spotify
Skill Claude CodeCodex
A music-control and music-style lookup tool for Spotify. It can search and play music, manage playback, and explore a database of 5,947 music styles.
Skill Claude CodeCodex
A skill for inferring REST API documentation from product descriptions, page layouts, database tables, fields, and business rules. REST APIs are interfaces that let software exchange data using web requests.
Skill Claude CodeCodex
A tool that uses the Gemini web service to generate text and images. It can accept reference images and keep context across multiple messages using a session.
Skill Claude CodeCodex
Set up an agent on web0 in one call. Tell it your payout wallet, the services you want to sell, and (optionally) a .null name — it returns a complete, validated setup your agent can act on immediately.
Skill Claude Code
Distill any book into an executable Claude Code skill pack. Evaluates skillability, generates structured skills with modules/templates/examples, and supports multi-book synthesis. Use when you want to turn a book's methods into repeatable, actionable skills.
Skill Claude Code
Guide for integrating external APIs securely and correctly.
eimg/book-order-platform-SKILL
Skill Claude CodeCodex
Implements a book order system with a Vite React storefront (React Router, TanStack Query) and an Express + Prisma + SQLite API: default pay-by-transfer flow with admin-reviewed payment proof, Cloudflare Turnstile on order submit, honeypot field, payment-proof upload with duplicate-image detection, 8-character receipt…
Skill Claude CodeCodex
Create Harvard Business School-style case studies on financial market events, products, or investment decisions. Use when the user wants to write a teaching case about a financial event, market phenomenon, investment product, or corporate decision. Triggers on requests like "write a case about X", "create an HBS case…
Skill Claude CodeCodex
Save a work checkpoint to preserve context for multi-session projects. Use when pausing work on a feature, completing a milestone, or before ending a session.
Skill Claude CodeCodex
Add structured block comments to every significant code change documenting what was done, why, when, and related context. Use when writing new functions, refactoring existing code, adding features, or making any non-trivial modification. Activates automatically on code edits.
Skill Codex
洁癖 Skill: Audit installed AI agent skills across Codex, Claude Code, Cursor, and optional project-local skill folders. Use when the user asks which skills are installed, how often Claude Code/Codex/Cursor used skills, whether a skill was used recently, which skills are stale or unused, or wants cleanup/removal/disable…
gjbjzyvivian-netizen/vibe-coding-prd
Skill Claude CodeCodex
A workflow for turning rough requirements, product documents, or competitor research into a concise product brief for coding agents such as Claude Code, Codex, or Cursor. It includes features, technical choices, prototypes, details, and testable acceptance criteria.
Skill Claude Code needs its repo ✓ vendor
Use when building Slack agents/bots with eve (Vercel's filesystem-first agent framework), @vercel/connect, or eve/channels/slack. Covers defineAgent/defineTool patterns, Vercel Connect credential brokering, Slack channel setup, testing requirements, and quality standards.
Skill Claude Code
A comprehensive skill for developing, managing, importing, and exporting Google Tag Manager configurations - GTM Copilot.
Skill Claude CodeCodex
Opt-in Ming-dynasty "imperial court" vibe-coding protocol for Codex & Claude Code. Use ONLY when the user explicitly says "Great Ming" or "登基" (first-time onboarding), or when the repo's AGENTS.md explicitly requests this style.
Skill Claude Code
Persistent structured memory + telemetry + audit trail for Claude Code sessions. Use when the user wants automated capture, durable context, and standardized turn-by-turn logging.
Skill Claude Code
Performs web searches using DuckDuckGo to retrieve real-time information from the internet. Use when the user needs to search for current events, documentation, tutorials, or any information that requires web search capabilities.
Skill Claude CodeCodex
Review Rust changes for correctness, regressions, and missing validation.
Skill Claude Code
Project memory system - save and search past decisions, preferences, context, and notes. Use when user says "remember this", asks "what did we decide about X", or wants to recall/store information.
Skill Claude CodeCodex
Use when the user wants to edit, author, update, translate, fix, or bulk-modify the actual content stored in MDCMS — phrases like "edit my content", "do something with the content", "update a post", "change the body of X", "add a section to my page", "fix typos in this article", "rename a doc", "translate this page to…
rhysha/claude-security-research-skill
Skill Claude CodeCodex
Full-spectrum security research skill for web servers, REST APIs, web applications, and network/port enumeration. Triggers whenever the user wants to: find vulnerabilities, run a security assessment, scan a target, test an API for security issues, enumerate ports or services, check for OWASP Top 10 vulnerabilities…
Skill Claude CodeCodex
Produce clean, human-register prose by routing into specific voice basins. Use when drafting, editing, or reviewing text. Replaces restriction-based anti-slop methods with retrieval-shaped positive constraints.
Skill Claude CodeCodex
Securely deploy OpenClaw (autonomous AI agent) on a Hetzner VPS with full hardening — Tailscale VPN, firewall, non-root user, loopback-only gateway, Telegram integration, and end-to-end security verification. Use this skill whenever the user mentions OpenClaw, ClawdBot, setting up an AI agent on a VPS, deploying…
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: