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
Query 1,000+ global classification systems (NAICS, ISIC, NACE, HS, ICD, SOC, ISCO, CPC, UNSPSC, and more) with 1.3M+ nodes and 326K+ crosswalk edges. Classify businesses, products, occupations, diseases, or documents under standard codes. Translate codes across country and system boundaries. Every one of the 434…
Skill Claude CodeCodex
DroidRun Portal HTTP/WebSocket/MCP client. Controls Android devices via HTTP, WebSocket, or MCP server, supporting tap, swipe, screenshot, text input, UI state retrieval and more. Use this skill when the user needs to interact with an Android device running DroidRun Portal.
Skill Claude Code
A planning-mode workflow that makes the coding agent design and submit a plan before changing files.
insodimension/awesome-agent-protocols
Skill Claude CodeCodex
Guide agent harness engineering toward the right AI agent protocol standards (MCP, A2A, ACP, AG-UI, AP2, x402, etc.) instead of reinventing. Analyzes what you're building, recommends protocols, pulls spec details and wire-message examples, checks compliance, and surfaces contribution opportunities. Triggers…
Skill Claude CodeCodex
Reduce avoidable token and API cost through task-aware model selection, context hygiene, concise responses, and disciplined tool use. Apply as an advisory policy on every turn. Actual savings vary by agent, model, provider, cache behavior, and workload; measure results instead of assuming a fixed percentage.
Bastioned-successor320/learn-nanobot
Skill Claude CodeCodex
A code-review procedure for Python, JavaScript, and Go programs. It checks security, performance, maintainability, naming, error handling, and testing.
Skill Claude CodeCodex
Create and verify recurring or one-shot reminders, scripts, agent jobs, reports, and interactive skill launches.
lhpaul/ai-dev-framework-template
Skill Codex
Advance a single workflow item until it reaches a real terminal condition. Use when the user wants Codex to resume or advance one specific development, branch, or PR without scanning the whole portfolio.
ergenekonyigit/cursor-autoresearch
Skill Claude CodeCodex
Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".
aussiegingersnap/cursor-skills
Skill Claude CodeCodex
Use when working with mise - creating/editing mise.toml or .mise.toml files, defining tasks with usage field arguments, managing dev tools and environments, configuring hooks, or when user mentions mise configuration.
Skill Claude CodeCodex
Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.
TheMattBerman/creator-breakout-kit
Skill Claude CodeCodex needs its repo
Run the full Creator Breakout Kit workflow when the user asks for creator strategy or direction — things like "what creator concepts should we test," "what content angles would you start with," or "what is breaking out in this category." Use when the user needs the creator angles, hooks, and concept directions most…
Skill Claude CodeCodex
Prepare a release summary and suggest release commands from repository history.
Skill Claude CodeCodex
Generate, parse, and compile a unified DESIGN.md (33 categories, 519 tokens) that compiles to CSS, Tailwind v4, and W3C JSON. Use when creating a new design reference, extracting tokens from an existing site (sigil design extract), switching a project's visual identity, generating compiled token output, or auditing a…
Skill Codex
A code-refactoring skill that makes overly indirect code more direct by removing unnecessary helpers, wrappers, adapters, temporary variables, and similar layers.
1ikeadragon/awesome-offsec-claude
Skill Claude CodeCodex
Elite AI/LLM exploitation specialist - prompt injection, jailbreaking, agent exploitation, RAG poisoning, multi-modal attacks, model extraction, and system prompt leakage for CTF and red team engagements.
Skill Codex
Integrate Univer (spreadsheet/doc/presentation) into React, Vue 3, HTML, or Node.js. Use when embedding Sheets/Docs/Slides, initializing instances, registering plugins, configuring themes/locales, or manipulating data via the Facade API (FUniver, FWorkbook, FWorksheet, FRange). Triggers: 'embed spreadsheet'…
Skill Claude CodeCodex
Set up and evolve Astro content collections with typed schemas and reliable querying patterns.
cubetribe/openclaw-godmode-skill
Skill Claude CodeCodex
Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW.
Skill Claude CodeCodex
A reference skill for quantitative investing factors—measurable signals such as momentum or volatility used to build trading strategies. It covers factor collections from Qlib and WorldQuant.
wenyi-li/awesome-agent-kernel-skills
Skill Claude CodeCodex
Step-by-step tutorial for adding new CUDA kernels to FlashInfer.
Skill Claude CodeCodex
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
Skill Claude Code needs its repo
Single-source-of-truth drift auditor for documentation-heavy repos. Use when asked to "check for drift," "find copies of this number," "audit the docs for stale facts," or "set up an SSOT manifest." Finds facts hand-copied across files, builds a manifest of canonical locations, and verifies every copy still matches.
runyuan-wang/book-to-skill-distillation
Skill Claude CodeCodex
End-to-end workflow for rewriting a book, long PDF, EPUB, manual, course, guideline library, same-domain multi-book source pack, large database, or methodology into an agent-native LingTai / Agent Skill structure. Use when the task is not a summary, but a reusable skill/knowledge system: source triage…
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: