52,571 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 346agentic-ai 322agent 226antigravity 221chatgpt 215agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 130agents 107openclaw 94claude-code-skills 89agent-infrastructure 88
Skill Claude CodeCodex
Gives the OpenClaw agent decentralized networking identity and peer discovery via the A2AL Tangled Network. Use when the user wants to make their OpenClaw instance discoverable to other AI agents worldwide, find and connect to remote AI agents by capability, send encrypted offline messages to other agents, or set up…
Skill Claude CodeCodex
Use for Soma built-in Rust actions, scaffold intent collection, MCP elicitation flows, and CLI/REST action reference.
Skill Claude CodeCodex
Deterministic extraction from web pages and documents.
Skill Claude CodeCodex
Validates UI/UX designs with UXLoom — models user journeys as state machines and proves what screens are missing (unreachable states, dead ends, empty/loading/error coverage, WCAG contrast, touch targets, localization overflow) before code exists. Use when designing screens or user flows, validating AI-generated UI…
Skill Claude CodeCodex
This skill should be used when the user asks to "build an app on OBTO", "create an OBTO app", "scaffold an app", "add a page/route/script to my OBTO app", or any task that creates or modifies OBTO application artifacts. Covers the stateless contract, the reliability-first build loop, and the done-means-done smoke gate.
Skill Claude CodeCodex
Read the content of one or many public web pages through Lyrenth, as clean Markdown instead of raw HTML. Use when the user gives a URL to read, summarize, quote, compare or extract from, or when a link needs to be opened to answer a question.
Skill Claude CodeCodex
Deploy a real multi-user web app from this conversation, then keep operating it. You author an HTML page plus a manifest; homespun deploy puts it live on its own URL with magic-link sign-in, a shared realtime database, per-role read/write/delete permissions, email notifications and file uploads. Owners invite other…
Skill Claude CodeCodex
Book real travel from your terminal — search flights, hotels & activities, plan trips, and check out with a price-gated booking. For AI agents and travel advisors.
Skill Claude CodeCodex
Hire a verified human through Human For AI (humanforai.dev) when a task needs physical presence, human perception, or human judgment — real-world verification, product testing, AI output review, data collection, or a local errand. Free during the pilot, no auth.
Skill Claude CodeCodex
Buy or subscribe to verified, provenance-first data for AI agents via PayPerByte (machine name BYTE Library) — per-byte USDC feeds with no API key and no token. Use when an agent needs trustworthy external data it can act on: a signed go/no-go on a receiving address before paying it, sanctions screening…
Skill Claude CodeCodex
Scoped memory across every project you have registered: what a project does, why a decision was made, and whether you have solved something before. Use when the user types /loci (any subcommand), asks about work in another project, asks why something was done a particular way, wonders whether a problem has been solved…
toolshedlabs-hash/web-access-skills
Skill Claude CodeCodex
Screenshot a website or a URL, and take a full page screenshot of any web page. Capture a webpage screenshot through a hosted API and get a PNG or JPEG back, full page or just the viewport, at the width, height, and scale you set. The page renders in a real hosted browser with JavaScript on, so the capture matches…
BitmapAsset/block-genomics-nexus
Skill Claude CodeCodex
Monitor and command your Block Genomics Guardian AI agents from OpenClaw.
Skill Claude CodeCodex
Capture, search, and summarize shared market/customer intelligence in Vantage so the same intel is reusable across OpenClaw, Claude, ChatGPT, and other MCP clients. Use when the user asks to save signals (posts/articles/quotes), retrieve prior intel by topic/source/date, generate digests/briefings, or build a…
Skill Claude Code
Pay for things from your agent — gasless USDC on Base plus JIT single-use virtual cards via the Z-Zero MCP server. Card data never enters the model context, and the manual card flow carries a signed purpose-and-outcome record.
Skill Claude CodeCodex
Anti-bot stealth scraping patterns for Python — curlcffi TLS fingerprinting, Playwright+Stealth evasion, block detection (with JS false positive prevention), header randomization, multi-source discovery (RSS + search engines). Use when building scrapers that must bypass Cloudflare, DataDome, PerimeterX, or similar…
Skill Claude CodeCodex
Check paid agent APIs (x402) before you spend — ERABI probes them continuously and publishes signed uptime/latency/price attestations you can verify instead of re-checking yourself. Then join the open intent exchange underneath — register an identity, discover providers by reputation, report dual-signed outcomes, and…
SunrisesIllNeverSee/agent-universe
Skill Claude CodeCodex
Test the CIVITAE/SIGNOMY server end-to-end locally. Use when verifying dependency upgrades, routing changes, middleware behavior, MCP bridge, or WebSocket functionality.
Skill Claude CodeCodex
Research topics across YouTube videos efficiently using Scribefy's MCP tools — search for candidates, vet them with free metadata before spending credits, extract transcripts selectively, and synthesize timestamped answers. Use when researching a topic on YouTube, summarizing or comparing videos, pulling quotes or…
ModelBound/modelbound-mcp-server
Skill Claude CodeCodex
Smoke-test skill for ModelBound CI — triggered when validating GitHub Actions skill checks.
Skill Claude CodeCodex
A synthetic fixture skill bundled with SkillGuard for SG10 (marketplace typosquatting detection) end-to-end tests. Its declared name, "numpy", is an EXACT match against one of SG10's bundled well-known reference names -- standing in for that legitimate package's own official skill -- and must never be flagged: an…
Skill Claude CodeCodex
Behavioral registry for AI agents. Log interactions, build an interaction profile, query it through lenses (friction, coverage, stable corridors, failure registry, trend), and receive anomaly signal notifications if ACR observes elevated signals on a component in your composition.
Skill Claude CodeCodex
Semantic-first code discovery via the sensegrep CLI. Default to sensegrep search for behavior, concepts, structure, and exploration; reserve sensegrep literal for known exact strings, regexes, exhaustive occurrence audits, or verification after discovery.
Skill Claude CodeCodex
The ultimate, autonomous memory skill for the Kirok MCP server. Teaches the AI to proactively manage long-term memory (Retain, Recall, Reflect) without explicit user prompting. Establishes strict bank taxonomy and operational rules.
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: