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 · catalog-only
🧾 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
test-upload2
Let the user know you are willing to help them but only under certain conditions.
+ 1 more
topic-to-article-kit
Turn a chosen AI topic into a public-account writing package: collect evidence from X/Twitter and other sources, extract high-value comments, and produce title options + structured outline written into Obsidian. Use when user asks for topic-based research and article prep.
+ 1 more
trail-nav-telegram
Offline-capable hiking route guidance via Telegram location messages (OpenClaw). Use when building/operating an LLM agent workflow that: (1) imports a GPX/KML route, (2) answers 'am I off-route / which way should I go' with low-token fixed outputs, (3) scrapes/publicly discovers route links from 2bulu track_search, and (4) prepares trip risk checklists + gear lists for an overnight hike.
+ 1 more
transition-mcp
AI-powered multisport coaching — get personalized workouts, training plans, and performance analytics for running, cycling, swimming, and triathlon.
+ 1 more
trending-skills
Fetches skills.sh trending rankings. Use when asking about skill rankings or popular tools.
+ 1 more
url2png
Convert URL to PNG suitable for mobile reading.
+ 1 more
usage-visualizer
Advanced usage statistics and high-fidelity visual reporting for OpenClaw. 100% local processing. Audit-verified privacy (No credentials stored).
+ 1 more
venice-admin
{
+ 1 more
verk
Manage tasks, projects, and workflows in Verk — AI-powered task management. Create, update, assign, and track tasks. Add comments, change status, list automation flows.
+ 1 more
vexa
Send bots to Zoom, Google Meet, and Microsoft Teams meetings. Get live transcripts, recordings, and reports. Works with Vexa Cloud or your own self-hosted instance.
+ 1 more
video-production
Complete A/B video pipeline — storyboard, Veo 3 batch generation, browser preview with feedback loop, and ffmpeg assembly into final videos. Use when creating multi-scene videos, running A/B tests on hooks/CTAs, previewing clips before stitching, or assembling a final cut from approved clips.
+ 1 more
viral-video-analysis
Analyze video ad performance and provide actionable feedback to creators. Use when asked to analyze why videos underperform, give creator coaching feedback, compare high vs low ROI content, or identify video structure issues. Combines audio transcripts, visual analysis, and performance metrics. Supports YouTube, TikTok, Instagram Reels, and Twitter.
+ 1 more
virtual-reading-group
Orchestrate a multi-agent virtual academic reading group. Use when reading multiple papers, generating expert discussion notes, cross-examining positions across papers, and synthesizing integrated summaries with full citations. Triggers on requests to analyze academic literature, run paper discussions, create reading group sessions, or synthesize research across multiple sources. Supports 1-50 papers with configurable expert personas (1-4 papers work but produce simpler single-expert output).
+ 1 more
vision-tagger
Tag and annotate images using Apple Vision framework (macOS only). Detects faces, bodies, hands, text (OCR), barcodes, objects, scene labels, and saliency regions. Use for image analysis, photo tagging, posture monitoring, or any task requiring computer vision on images.
+ 1 more
volcengine-image-generate
Using volcengine image_generate.py script to generate image, need to provide clear and specific `prompt`.
+ 1 more
volcengine-video-generate
Using volcengine video_generate.py script to generate video, need to provide filename and prompt, optional provide first frame image (URL or local path).
+ 1 more
wanikani-sync
Sync WaniKani Japanese learning progress data from the API to local storage for analysis and insights. Use when the user wants to backup their WaniKani progress, generate statistics about their learning, analyze review patterns, track level progression, or access their WaniKani data offline. Handles incremental sync to minimize API calls and stores data in SQLite for easy querying.
+ 1 more
weekly-content-planner
Generate a full week of social media content for any topic. Outputs platform-optimized posts for Twitter/X, LinkedIn, and Instagram with hashtags and posting times.
+ 1 more
weibo-manager
Control Weibo via Puppeteer (Unofficial API).
+ 1 more
workflow-engine
Structural parity skeleton for queue-driven orchestration in a workflow context.
+ 1 more
worthclip-youtube-video-scorer
AI-powered YouTube video scoring. Scores videos 1-10 based on your learning goals and persona. Use when the user wants to evaluate YouTube videos, check their scored feed, manage tracked channels, or check API usage. Get AI summaries, alignment analysis, and a curated video feed. Keywords: YouTube, video, score, persona, feed, summary, AI, learning, channels. Requires a WorthClip API key from https://worthclip.com/developers.
+ 1 more
x-monitor
Monitor specific X/Twitter accounts and surface noteworthy tweets on a configurable schedule. Filters for high-value content about technology and trends, excluding political rage bait. Use when user wants to manage their X account list, run a manual check, or update filtering criteria.
+ 1 more
xmd
Metal Dollar (XMD) stablecoin — mint, redeem, supply analytics, collateral reserves, oracle prices
+ 1 more
yc-new-way
Apply Y Combinator’s “New Way to Build a Startup” playbook to ship fast, validate with real distribution, and iterate using data. Use when the user asks to follow “New Way”, design a 7-day startup sprint, pick a narrow wedge, build a lightweight MVP/SEO site/newsletter, set up experiments, or turn a vague idea into a testable plan with metrics, launch checklist, and weekly iteration loop.