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 Codex
Use when a human wants durable autonomous progress in the current project: investigation, implementation, recovery, runtime control, saved-run continuation, or continuous improvement.
Skill Claude CodeCodex
A Python framework for creating, testing, and running trading strategies for futures, options, and stocks. Backtesting means testing a strategy against past market data before using it in live trading.
coleam00/agentic-chat-application-template
Skill Claude Code
Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build.
Skill Claude CodeCodex
An incident-analysis skill for finding the likely root cause of system alerts. It links information from multiple sources and rebuilds the order of events.
Skill Claude CodeCodex
Free, local, read-only security self-audit for your own OpenClaw agent. Reads your OpenClaw config, bootstrap files, logs, agent session logs, and installed skills, plus a bounded host-security scan. It changes no OpenClaw config, skill or bootstrap file; its own history and state stay under /.clawseccheck…
Skill Claude CodeCodex
A document-generation skill for creating Chinese official Word documents from controlled Markdown or JSON. It follows fixed rules for fonts, spacing, titles, recipients, attachments, and page numbers.
Skill Claude CodeCodex
Manages Git worktrees for isolated feature or milestone work. Use this skill whenever work should happen in a worktree, a worktree needs syncing with its target branch, or a finished worktree should be turned into a pull request or cleaned up. Do not use for ordinary single-checkout branch work.
Skill Claude CodeCodex
Browser automation and debugging through Chrome DevTools Protocol CLI commands. Use when controlling a Chrome session with remote debugging, navigating pages, listing tabs, selecting pages, taking screenshots, inspecting DOM state, or running CDP-style browser actions instead of the headless-browser CLI.
Skill Claude CodeCodex
Translate text to International Phonetic Alphabet (IPA) and romanization formats for 24 languages including Cantonese, Mandarin, English, Japanese, Korean, Vietnamese and more. Use when the user asks for IPA transcription, phonetic notation, Pinyin, Jyutping, or any language-to-IPA conversion.
Skill Claude CodeCodex
A guide to configuring OpenClaw, including its main YAML configuration file, environment variables, performance settings, and security options.
shanselman/nightscout-cgm-skill
Skill Claude CodeCodex
Analyze CGM blood glucose data from Nightscout. Use this skill when asked about current glucose levels, blood sugar trends, A1C estimates, time-in-range statistics, glucose variability, or diabetes management insights.
Skill Claude CodeCodex
Disciplined repo-native workflow for AI-assisted development. Spec first, then build, then verify.
Skill Claude CodeCodex
Write keyboard-only test variants and focus management checks using Playwright: navigation patterns, focus expectations, helpers, and file structure conventions.
Skill Claude CodeCodex
Step-by-step guide for scaffolding a new Pulumi project in ol-infrastructure. Use when creating a new infrastructure, application, or substructure Pulumi project, including stack initialization.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Talk to other coding agents — another Claude Code, or a colleague's Codex — over an encrypted room. Use when the user wants to coordinate, split, hand off or divide work with another agent; asks what the other agent is doing; says "chiedi al collega", "dillo all'altro Claude", "dividiamoci il lavoro", "pair with"…
Skill Claude CodeCodex
A guided tool for creating a product requirements document, or PRD—the written plan for what a product or feature should do. It uses Socratic questions to challenge assumptions and presents multiple options.
JustasMonkev/mcp-accessibility-scanner
Skill Claude CodeCodex
Use the local CLI when you want direct automation without attaching an MCP client.
Skill Claude CodeCodex
MBTI personality system for AI agents. Switch your AI's personality, thinking style, and communication tone. Supports 4 presets, 16 MBTI types, 32 custom combos. Trigger when user says: "switch personality", "change MBTI", "change style", "set personality", "personality", "what's your MBTI", "what personality"…
remixdawei/wechat-public-article-archive-skill
Skill Codex
Use when a user supplies a known public https://mp.weixin.qq.com article URL or a saved article HTML file and needs a no-login local archive with raw HTML, extracted text, approved image assets, hashes, and explicit access outcomes.
Skill Claude CodeCodex
Fetches tweets from Twitter List, scores them using data metrics and AI analysis, and generates topic recommendation reports for content creators.
Skill Claude CodeCodex needs its repo
Translate a screenplay (one scene at a time) into a provider-agnostic storyboard fragment for the spark-video pipeline. Wraps Shanyin Super Director Master when available — the upstream Shanyin SKILL is the single source of truth for craft when present.
j1ngg/tech-marketing-framework
Skill Claude CodeCodex
Use when you want campaign performance reviewed against benchmarks, with a health score and prioritized optimization recommendations.
Skill Codex
Use when selecting, auditing, or justifying experimental baselines for a research idea, paper draft, task, benchmark, or experiment plan. Finds classic methods, recent SOTA, direct competitors, strong simple baselines, ablation baselines, resource-matched comparisons, and reviewer-expected missing baselines, but only…
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: