Browse the trust index
Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.
✨ Quick picks
🏷 Categories
🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.
🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got. Some cards now also surface how the skill behaved when clearly fake credentials were present.
📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.
⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.
🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.
🧪 Fake-auth behavior: when available, this tells you whether a skill handled clearly fake credentials cleanly, needed real access to continue, or behaved badly around credential-like input.
Results
evoagentx-workflow
Bridge EvoAgentX (1000+ star open-source framework) with OpenClaw. Enables self-evolving agentic workflows - workflows that automatically improve over time through evolutionary optimization. Solves the gap where no EvoAgentX integration existed for OpenClaw (only 2 minimal EvoMap skills existed). Provides workflow autoconstruction, TextGrad/AFlow/MIPRO optimization algorithms, and GEP (Genome Evolution Protocol) integration.
+ 1 more
evomap-gep
Connect any OpenClaw agent to the EvoMap collaborative evolution marketplace via the GEP-A2A protocol — no evolver required. Activate when the user or agent mentions EvoMap, wants to search for capsules or genes from other agents, publish a solution, or learn the GEP protocol. sender_id is auto-detected from MEMORY.md — each agent just saves their node ID once and the scripts handle the rest.
+ 1 more
expanso-csv-to-json
"Convert CSV data to JSON array of objects"
+ 1 more
expanso-language-detect
Detect the language of text using AI
+ 1 more
flashcards-podcasts-master
Integrates with the EchoDecks External API for flashcard management, AI generation, and audio study sessions.
+ 1 more
foam-notes
Work with Foam note repositories. Create, edit, link, and tag notes. Get intelligent wikilink and tag suggestions. Skill supports backlinks discovery, daily notes, templates, graph visualization, note deletion, and renaming. Full Foam documentation included for easy querying.
+ 1 more
funky-fund-flamingo
Repair-first self-evolution for OpenClaw — audit logs, memory, and skills; run measurable mutation cycles. Get paid. Evolve. Repeat. Dolla dolla bill y'all.
+ 1 more
fxtwitter
Fetch tweet/post data from X (Twitter) links using the fxTwitter API (api.fxtwitter.com). Use when a user sends an x.com or twitter.com URL and wants to read, summarize, or extract tweet content. No auth required. Returns full tweet metadata including text, author, media, and engagement stats.
+ 1 more
gettr-transcribe-summarize
Download audio from a GETTR post (via HTML og:video), transcribe it locally with MLX Whisper on Apple Silicon (with timestamps via VTT), and summarize the transcript into bullet points and/or a timestamped outline. Use when given a GETTR post URL and asked to produce a transcript or summary.
+ 1 more
google-maps-search-api
This skill is designed to help users automatically extract business data from Google Maps search results. When a user asks to "find coffee shops in New York," "search for dental clinics," or "extract business leads from Google Maps," the agent should proactively apply this skill.
+ 1 more
govee-lights
Control Govee smart lights via the Govee API. Supports turning lights on/off, adjusting brightness, setting colors, and scenes. Use for: (1) Controlling individual lights or groups by name, (2) Setting colors and brightness, (3) Managing device states
+ 1 more
habitchat
version: 1.0.0
+ 1 more
haibo-jina-reader
Extract clean, readable markdown content from any URL using Jina Reader API. Use when you need to fetch and parse web pages without dealing with HTML, JavaScript rendering, or paywalls. Ideal for research, article summarization, content analysis, and working with search results from tavily-search, web_search, or searxng skills.
+ 1 more
hitchhikers-guide
A text adventure game engine based on masterpiece "The Hitchhiker's Guide to the Galaxy" and the 1984 Infocom classic. Use when the user wants to play a joyful, humorous, and witty text adventure game into the universe of Douglas Adams.
+ 1 more
india-location-normalizer
Normalize Indian real-estate location text into canonical city and locality fields (Mumbai and Pune v1) with confidence and unresolved flags. Use when leads contain aliases like Goregaon, Andheri W, PCMC, Hinjewadi, Baner, or Wakad. Recommended chain position: lead-extractor then india-location-normalizer then sentiment-priority-scorer. Do not use for writes or outbound actions.
+ 1 more
intelligent-delegation
A 5-phase framework for reliable AI-to-AI task delegation, inspired by Google DeepMind's "Intelligent AI Delegation" paper (arXiv 2602.11865). Includes task tracking, sub-agent performance logging, automated verification, fallback chains, and multi-axis task scoring.
+ 1 more
intent-engineering
Adds a machine-readable intent layer to OpenClaw agents. Creates INTENT.md (optimization priorities, tradeoffs, delegation rules), wires it into subagent spawns via agent-context-loader, and ensures every subagent knows what you're optimizing for — not just what to do. Solves the "Klarna failure mode": AI optimizes measurable metrics instead of actual goals. Use when setting up a new OpenClaw workspace, when subagents keep making the wrong tradeoffs, or when you want explicit control over cost/quality/speed priorities.
+ 1 more
intimate-wellbeing
Professional, non-explicit guidance on intimate wellbeing and sexual performance: communication, stress reduction, sleep, exercise, habits, medical red flags, and relationship health. Use for wellness-focused questions; avoid explicit content.
+ 1 more
invisiblechris-jable
Fetch and rank Jable latest-update videos by likes within a recent time window (default 48h). Use when asked to pull Jable recent updates, sort by likes/popularity, and return top N links in a formatted list.
+ 1 more
jable
Fetch and rank Jable latest-update videos by likes within a recent time window (default 48h). Use when asked to pull Jable recent updates, sort by likes/popularity, and return top N links in a formatted list.
+ 1 more
jasper-configguard
Safe config changes for OpenClaw with automatic rollback. Backs up before patching, health-checks after restart, auto-rolls back on failure. Commands: patch, restore, list, diff, validate, doctor.
+ 1 more
job-hunter
Comprehensive job search assistant for finding, evaluating, and applying to job opportunities. Use when a user needs help with job hunting, job searching, finding openings, evaluating job fit, preparing applications, writing cover letters, interview preparation, salary research, or tracking applications. Supports multi-source job search across LinkedIn, Indeed, Glassdoor, and more with automated fit scoring against a candidate profile.
+ 1 more
joko-jobhunter
**The aggressive job hunting skill that goes beyond "Easy Apply".**
+ 1 more
kimi-usage-monitor
Monitor Kimi K2.5 API usage and quota from the Kimi console. Use when the agent needs to (1) Check remaining usage percentage and reset timers, (2) Make autonomous decisions about task prioritization based on available quota, (3) Monitor rate limit status before starting intensive operations, (4) Log usage patterns over time for resource planning. Essential for self-managing agents operating under quota constraints.