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
User manual for the mind-mem persistent memory CLI (mm). Use when an agent needs to recall prior decisions, tasks or project facts from a mind-mem workspace, pack memory into context, check workspace health, review governed proposals, install or troubleshoot mind-mem, or answer questions about how mind-mem works …
Skill Claude CodeCodex
Triggers when a user invokes /consulting or asks for a consultation on an ambiguous change: to be interviewed one question at a time while one living, clickable prototype of the whole thing is built as the answers arrive, have decisions saved across sittings, and end with a gap-finding review, a final "is this the…
Skill Claude CodeCodex
Install and use theAuth (@glinr/theauth), the TypeScript auth SDK for AI agents and humans. Use when adding agent identity, scoped permissions, delegation, audit logs, human sign-in plugins, or an MCP OAuth 2.1 authorization server to a Node, Bun, Deno or edge project.
Skill Claude CodeCodex
Which Valhuntir MCP tool or SIFT tool to use for a question, file, IOC or artifact, and the step-by-step workflows that combine them (IOC investigation, threat actor research, detection engineering, malware analysis, disk, memory, timeline and network). Use when choosing tools or planning a multi-step analysis.
joaquimscosta/arkhe-claude-plugins
Skill Claude CodeCodex
Creates context-aware git commits with smart pre-commit checks, submodule support, and conventional commit message generation. Use when user requests to commit changes, stage and commit, check in code, save work, save changes, push my code, finalize changes, add to git, create commits, run /commit command, or mentions…
Skill Claude CodeCodex
A structured learning method that guides someone from researching a subject to practising and checking their understanding. It uses several viewpoints and roles, including teacher, examiner, and resource curator.
Skill Claude CodeCodex
Before cloning or installing any package or repo, stop, inspect it, report what it is and what it does, give a verdict, and wait for the human.
Skill Claude CodeCodex
Converts Markdown to PDF with the rayomd command-line tool (one small binary, no browser, TeX or Pandoc), with formulas, Mermaid diagrams, highlighted code, tables, tables of contents, page numbers, books of several files, PDF/A and PDF/UA. Use when the user wants a PDF of Markdown the agent wrote or was given (a…
Skill Claude Code
Measure capshelf latency and Git process counts, and prove that two capshelf binaries give the same results. Use for any change that moves a Git read, batches reads, or changes startup, and to compare a branch with a release.
Skill Claude CodeCodex
Keep a DECISIONS.md log of the analytical choices made during data work (which observations to keep, how a variable is defined, which method, which chart), so the researcher can review the reasoning before trusting results. Use whenever cleaning data, building a sample, defining variables, choosing a method or…
Skill Claude CodeCodex ✓ vendor
Audit MCP tool definitions to identify naming collisions, description overlaps, and ambiguities that may confuse agent decision-making.
Skill Codex
Local open-source Agent Skill for authorized web application, API, browser, business-logic, and supporting server-integrity penetration testing. Use for scoped OWASP WSTG, ASVS, and API Security assessments; authenticated and multi-role validation; attack-surface mapping; bounded DAST; evidence-backed findings…
Vorim-AI-Labs/vorim-openclaw-skill
Skill Claude CodeCodex
AI agent identity, permissions, trust scores, and audit trails via Vorim AI. Gives your OpenClaw agent a cryptographic identity so every action is verified, permissioned, and logged.
zja0011/edgesentinel-visionops
Skill Codex
Investigate bounded object-removal events with exact event details and evidence integrity checks. Use when a user asks what was removed, whether an item was taken, who took an item, or requests investigation of an OBJECTREMOVED event.
Skill Claude CodeCodex
Read complex or JavaScript-rendered web pages cleanly. When a plain URL fetch returns an empty shell, garbled HTML, or "enable JavaScript", re-fetch the page through Jina Reader (https://r.jina.ai/) to get rendered, LLM-ready Markdown. Keyless, no setup. Use whenever a fetched page looks broken or you need the real…
efeunalmedia-lab/efeunal-website-seo
Skill Claude CodeCodex
Modern web design trends, principles, and implementation patterns for 2024-2025. Use this skill when designing websites, creating interactive experiences, implementing design systems, ensuring accessibility, or building performance-first interfaces. Triggers on tasks involving modern design trends, micro-interactions…
vigorX777/wechat-article-formatter
Skill Claude CodeCodex
A formatter that turns Markdown into HTML designed for WeChat Official Accounts, a publishing platform in China.
Skill Claude CodeCodex
A job-search assistant that first builds a profile of the job seeker. The profile includes technical experience, English ability, location and time zone, preferred employment type, minimum income, and tolerance for night shifts.
Skill Claude CodeCodex
Generate short-form videos (YouTube Shorts, TikTok, Reels) from text prompts.
Skill Claude CodeCodex
Build and maintain OpenIslands data dashboards — typed manifests of visual islands bound to local files (CSV / JSON / Parquet / SQLite / markdown), edited safely over the OpenIslands MCP server in Code Mode (one execute tool you drive with JavaScript). Use whenever a project has apps/ /manifest.json or an .mcp.json…
Skill Claude CodeCodex
Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.
johnlarkin1/claude-code-extensions
Skill Claude CodeCodex
Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical…
Skill Claude CodeCodex needs its repo
Analyze authorized video content from a local video file, a public direct HTTP(S) video URL, or—with --allow-platform—a single public video on a platform page (e.g. Bilibili/YouTube watch links, fetched via yt-dlp without login or cookies). Use this skill whenever the user asks to read, understand, summarize…
Skill Claude CodeCodex
Use this skill when working inside an OpenClaw installation, workspace, or source tree to set up or modify skills, cron jobs, channels, providers, files, or integrations. Inspect the current state first, use official OpenClaw docs and CLI commands when available, make the smallest safe change, and validate the result…
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: