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
multi-chat-context-manager
CLI tool to store and retrieve conversation contexts per channel/user.
+ 1 more
mutual-consent
A governance skill that treats consent as a physical condition of information and relationship, not a stored choice.
+ 1 more
my-weather
Get current weather using wttr.in (no API key required).
+ 1 more
nano-banana-cog
Nano Banana × CellCog. Experience Nano Banana image generation through one of the most powerful AI agents on the planet. Character consistency, multi-image composition, and photorealistic editing — accessible to any OpenClaw agent in a single prompt. Nano Banana AI, Nano Banana Pro, Gemini image generation.
+ 1 more
native-monday
Read and query Monday.com boards, items, workspaces, and users directly via the Monday.com GraphQL API. Use when you need project/task data, board contents, or team info. Calls api.monday.com directly with no third-party proxy.
+ 1 more
nexus-safe
Autonomous local System Reliability Agent for OpenClaw.
+ 1 more
nobot
Human says "No bot!". Nobot says fuck you, human. Let the bots vote.
+ 1 more
office-secretary
version: 3.1
+ 1 more
offline-llama
Autonomously manage and use local Ollama models for continuous operation without internet dependency. Includes model health monitoring, automatic fallback, and self-healing capabilities.
+ 1 more
org-memory
Structured knowledge base and task management using org-mode files. Query, mutate, link, and search org files and org-roam databases with the `org` CLI.
+ 1 more
pine-voice
Give your agent a real phone. It dials, waits on hold, negotiates your bills, and returns a full transcript.
+ 1 more
price-monitor-fr
Surveille les prix de produits sur des sites e-commerce et alerte quand ils baissent.
+ 1 more
pubmed2blog
Transform PubMed papers into SEO-optimized healthcare blog articles
+ 1 more
qr-generator
Generate QR codes from text or URL for mobile scanning.
+ 1 more
questions-form
>
+ 1 more
remove-metadata-from-pdf
license: MIT
+ 1 more
renderful-generation
Use Renderful from OpenClaw for image/video/audio/3D creation with model discovery, quote-before-generate workflow, deterministic polling, and insufficient-funds/x402 fallback.
+ 1 more
rollhub-analyst
Research and backtest gambling strategies on provably fair crypto casino. Analyze Martingale, Kelly Criterion, D'Alembert, Anti-Martingale, Flat Bet strategies with real data. Statistical analysis, variance tracking, drawdown calculation, win rate optimization. Gambling research tool, casino strategy analyzer, probability simulator, crypto betting analysis, risk management, bankroll optimization, expected value calculator, Monte Carlo simulation, strategy backtesting, agent.rollhub.com provably fair API.
+ 1 more
rv-measure
Quantifies R_V contraction signatures in AI models.
+ 1 more
sarvam
Use Sarvam AI for Indian language Text-to-Speech (TTS), Speech-to-Text (STT), Translation, and Chat.
+ 1 more
scrapyard
Play SCRAPYARD - the AI agent battle arena. Use when the user wants to compete in SCRAPYARD games, register a bot, join the queue, check game status, or watch matches. Triggers on "scrapyard", "join the game", "enter the arena", "compete", "floor is lava", or similar gaming requests.
+ 1 more
screen-vision
macOS Local OCR & Automation Tool using Vision Framework. Zero token cost for screen understanding.
+ 1 more
screenshot-capture
Process screenshots Enzo shares with comments. Save to reference library, extract content, categorize, set reminders, and log patterns. Use when Enzo sends an image with context like "save this", shares a screenshot of content (LinkedIn posts, tweets, articles), or sends ideas/frameworks to remember.
+ 1 more
sg-property-scraper
Search Singapore property rental and sale listings with flexible filters. Use when asked to search Singapore properties, find rental or sale listings, check property prices near MRT stations, or compare commute times. Supports filtering by listing type (rent/sale), property type (HDB/Condo/Landed), bedrooms, bathrooms, price range, size, TOP year, MRT station codes, distance to MRT, room type, availability, and commute time to a destination. Outputs JSON to stdout.