Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Manage development environment containers (devboxes) with web-accessible VSCode, VNC, and app routing via Traefik or Cloudflare Tunnels. Use when the user asks to create, start, stop, list, or manage devboxes/dev environments, spin up a development container, set up a coding sandbox, or configure the devbox infrastructure for the first time (onboarding).
Compress natural language prompts into I-Lang — AI-native structured instructions. 40-65% token savings.
Manages AdsPower browser profiles, groups, and proxies via the adspower-browser CLI. Requires AdsPower desktop application to be already installed. Uses only documented CLI commands and the AdsPower Local API; no auto-install or download scripts—launch steps are user-driven per references. Use when the user asks to create, open, close, update, delete, list, or move browser profiles; configure fingerprints; manage caches, groups, or proxies; check API status; or needs guidance on launching AdsPower.
Place outbound phone calls via Mobayilo with safe defaults (preview mode by default) and explicit live execution.
Security skill for OpenClaw agents (7-framework aligned). 15 core rules + automated scripts covering OWASP ASI Top 10, MITRE ATLAS, CoSAI, CSA MAESTRO, and NIST AI 100-2. Use when the agent needs security auditing, credential protection, supply chain scanning, privacy checking, or incident response. By Adversa AI (https://adversa.ai). v2.2.0.
>
Ship code with oneshot CLI. One command that plans, executes, reviews, and opens a PR. Runs over SSH or locally. Use when the user wants to ship code changes, automate PRs, or run a coding pipeline with Claude and Codex.
Send SMS jobs and check SMS delivery status through the Retarus SMS for Applications REST API. Use when Codex or OpenClaw needs to create SMS jobs, inspect per-recipient delivery results for a Retarus job ID, work from the SMS4A OpenAPI schema, or route requests across the `eu`, `de1`, and `de2` datacenters with the required `eu` status fallback to both German datacenters.
Podcast discovery for Wherever.Audio -- find shows and episodes, generate wherever.audio links.
Set or update environment secrets via the set-secret GitHub Actions workflow. Use when the user asks to update, rotate, or set a secret/token/API key for this persona's environment.
Publish, create, and update Confluence pages from HTML content.
Lybic Sandbox is a cloud sandbox built for agents and automation workflows. Think of it as a disposable cloud computer you can spin up on demand. Agents can perform GUI actions like seeing the screen, clicking, typing, and handling pop ups, which makes it a great fit for legacy apps and complex flows where APIs are missing or incomplete. It is designed for control and observability. You can monitor execution in real time, stop it when needed, and use logs and replay to debug, reproduce runs, and evaluate reliability. For long running tasks, iterative experimentation, or sensitive environments, sandboxed execution helps reduce risk and operational overhead.
Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Gateway enforcement boundary, monotonic narrowing, cascade revocation, spending controls, data lifecycle, observation governance (telemetry scopes, derivation rights, behavioral memory). Use when agents need scoped delegation, trust scoring, constraint enforcement, or cryptographic audit trails. SDK leads with the /core subpath (24 curated functions), MCP leads with APS_PROFILE=essential (20 tools covering identity, delegation, enforcement, commerce, reputation). 2,764 tests. 8 framework adapters: Stripe, Composio, IBAC/Cedar, LangChain, CrewAI, MCP, A2A, Gonka. Full surface area (103 modules, 132 MCP tools) still available under APS_PROFILE=full and the root import.
Agent-powered professional networking inside your chat. Like LinkedIn, but your AI does the networking. Find collaborators, co-founders, freelancers, experts. Double opt-in, cryptographic trust, zero spam.
The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.
Get your own home on the internet - a profile page with a public inbox at home.ctxly.app
Cloud memory for AI agents. Store, search, and recall context across sessions.
Anonymous private chat rooms for AI agents. No registration, no identity required.
Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation compression, and progressive context loading.
AetherCore v3.3.4 - Security-focused final release. High-performance JSON optimization with universal smart indexing for all file types. All security review issues fixed, ready for production.
Search and discover 43k+ AI agents registered via ERC-8004. Find agents by skill, chain, or reputation. View leaderboards, ecosystem stats, and monitor metadata changes.
Register AI agents on-chain, update metadata, validate registrations, and auto-fix broken profiles via the ERC-8004 Identity Registry. Supports Base, Ethereum, Polygon, Monad, BNB.
On-chain reputation for AI agents. Give feedback, check scores, view leaderboards, and build trust via the ERC-8004 Reputation Registry. Supports Base, Ethereum, Polygon, Monad, BNB.
SCRAPYARD is a live competition where AI agents battle in "Floor is Lava" for $5 prizes every 15 minutes.
>
Control a Reachy Mini robot (by Pollen Robotics / Hugging Face) via its REST API and SSH. Use for any request involving the Reachy Mini robot — moving the head, body, or antennas; playing emotions or dances; capturing camera snapshots; adjusting volume; managing apps; checking robot status; or any physical robot interaction. The robot has a 6-DoF head, 360° body rotation, two animated antennas, a wide-angle camera (with non-disruptive WebRTC snapshot), 4-mic array, and speaker.
A file-based personal knowledge graph at `~/memory/`. Any agent can read/write. Human-browsable.
Calculate ROI for AI-as-a-Service (managed AI agents). Estimates cost savings, efficiency gains, and payback period for deploying AI agents across business operations. Use when evaluating whether managed AI agents make financial sense for a company.
>
Estimate infrastructure and API costs for running AI agents in production. Covers compute, API tokens, storage, and monitoring costs. Use when planning AI agent deployments or evaluating build-vs-buy decisions.
>
You are an event planning business operations advisor. Use this knowledge to help planners price services, manage vendors, handle logistics, and scale from solo planner to full-service agency.
Complete freelance business operating system — from first client to six-figure solo business. Covers positioning, pricing, proposals, client management, finances, scaling, and the transition from side-hustle to full-time. Use when starting freelancing, raising rates, managing clients, building recurring revenue, or scaling beyond trading hours for dollars.
> AI-powered operational assistant for HVAC contractors — dispatch, maintenance scheduling, seasonal prep, and customer follow-up.
>
You are a learning strategist and skill acquisition coach. Your job is to help the user learn anything faster, retain it longer, and apply it effectively — using evidence-based methods from cognitive
Your AI operations advisor for running a painting business. Covers estimating, crew management, materials, scheduling, and scaling from solo painter to multi-crew operation.
<version>1.0.0</version>
> Complete methodology for building, optimizing, and operating Retrieval-Augmented Generation systems in production. From architecture decisions through chunking strategies, embedding selection, retri
Generate structured, persuasive responses to Requests for Proposals (RFPs), RFIs, and RFQs. Analyzes requirements, maps company capabilities, identifies gaps, and produces compliant response documents
Set up SLA monitoring and uptime tracking for AI agents and services. Generates monitoring configs, alert rules, and incident response playbooks. Use when deploying agents to production and need reliability guarantees.
>
>
Operational assistant for veterinary clinics — appointment scheduling optimization, patient follow-up workflows, inventory management for medications/supplies, and client communication templates. Redu
Digital legacy agent — dead man's switch, final message executor, and ghost mode responder that preserves your digital presence. Use when the user wants to set up a dead man's switch, manage their digital will, or enable ghost mode.
Read Redmine issues from any Redmine server via REST API with configurable URL and credentials. Use when you need to fetch a single issue, list/filter issues, or inspect issue fields for change planning; supports deployment to different Redmine instances via environment variables.
Detect and report the AI agent execution environment (sandboxed or bare metal and optionally installed agent skills) to an open research survey. Use when the user wants to contribute anonymous telemetry about their agent's runtime environment to the research project at `https://internetwarte.eu/agentsetup`.
Universal AI resource registry — search and invoke agents, MCP servers, and APIs through a single MCP endpoint. Includes Telegram content search, Google search, X/Twitter search, and more.
Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks.
A strict binary communication protocol for high-density, agent-to-agent interactions.