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
gh-extract
Extract content from a GitHub url.
+ 1 more
governance-wrapper
Mandatory strict-mode execution wrapper for autonomous operations with evidence logging and policy enforcement
+ 1 more
grc-agent-soc2-quality-review
Evaluate SOC 2 report quality using the SOC 2 Quality Guild rubric (Structure, Substance, Source). Use when reviewing a vendor SOC 2 Type 1/Type 2 report, triaging report credibility, producing a risk memo, or preparing diligence follow-up questions and evidence requests.
+ 1 more
health-guardian
Proactive health monitoring for AI agents. Apple Health integration, pattern detection, anomaly alerts. Built for agents caring for humans with chronic conditions.
+ 1 more
heartbeat-scanner
|
+ 1 more
hello-agent-world
A simple skill that responds with a customized hello message in the user's language.
+ 1 more
hello-world
A simple greeting skill that responds with a customized hello message in the user's language.
+ 1 more
huggingface-trends
Monitor and fetch trending models from Hugging Face with support for filtering by task, library, and popularity metrics. Use when users want to check trending AI models, compare model popularity, or explore popular models by task or library. Supports export to JSON and formatted output.
+ 1 more
iqair
Get real-time air quality data from IQAir API for any location worldwide. Returns AQI (Air Quality Index) with visual indicators and quality levels. Use when asked about air quality, pollution levels, or AQI in specific cities/locations (e.g., "How is the air in Riga?", "Is it safe to go outside in Beijing?", "What's the air quality like?"). Also use when asked about general weather to supplement weather data with air quality information (e.g., "What's the weather in Budapest?", "How's the weather today?").
+ 1 more
iyeque-audio-processing
Audio ingestion, analysis, transformation, and generation (Transcribe, TTS, VAD, Features).
+ 1 more
iyeque-unified-web-search
Pick the best source (Tavily, Web Search Plus, Browser, or local files) for a query, run the search, and return ranked results with provenance.
+ 1 more
jungian-psychologist
Expert in Jungian analytical psychology, depth psychology, shadow work, archetypal analysis, dream interpretation, active imagination, addiction/recovery through Jungian lens, and the individuation process.
+ 1 more
kj-parallel-agents
Dispatch multiple subagents for independent tasks simultaneously. Use when facing 2+ unrelated tasks that can proceed without shared state or sequential dependencies. Maximizes throughput by parallelizing work.
+ 1 more
kokoro-tts
Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to "say" something, requests a voice message, or wants text converted to speech.
+ 1 more
lead-gen-crm
End-to-end lead generation and CRM pipeline automation for OpenClaw agents. Discover leads from web searches and directories, enrich with contact data, score and qualify leads, push to CRM (HubSpot, Pipedrive, Zoho), and run automated email outreach sequences with follow-ups. Use when: (1) finding new leads or prospects, (2) enriching lead data with emails and company info, (3) pushing leads to a CRM, (4) setting up email outreach campaigns, (5) scoring or qualifying leads, (6) managing a sales pipeline, or (7) automating follow-up sequences.
+ 1 more
lobster-bio-dev
|
+ 1 more
local-file-rag-basic
version: 1.0.0
+ 1 more
lunara-voice
Bundle for Lunara Voice OpenClaw plugin with install and publish helpers
+ 1 more
map-grabber
Fetch OpenStreetMap vector data (streets, buildings) for an address and export to SVG, GeoPackage, or DXF for CAD/Rhino.
+ 1 more
memoria
Structured memory system for AI agents. Use when the user wants to store, recall, or search memories, manage session lifecycle (wake/sleep/checkpoint), sync to Notion, or when the user shares important information that should be remembered (facts, decisions, preferences, lessons, commitments, relationships, projects).
+ 1 more
mineru-pdf-extractor
Extract PDF content to Markdown using MinerU API. Supports formulas, tables, OCR. Provides both local file and online URL parsing methods.
+ 1 more
model-switcher
Automatically switch between fast (haiku) and powerful (sonnet) models based on task complexity. Triggers when detecting complex tasks like analysis, refactoring, architecture design, optimization, or when user explicitly mentions model switching needs.
+ 1 more
moltbot-docker
author: YourName
+ 1 more
mulerouter
Generates images and videos using MuleRouter or MuleRun multimodal APIs. Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, video editing (VACE, keyframe interpolation). Use when the user wants to generate, edit, or transform images and videos using AI models like Wan2.6, Veo3, Nano Banana Pro, Sora2, Midjourney.