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
aviation-agent
Aviation weather briefing and FAA reference assistant for pilots. Fetches real-time METAR, TAF, and PIREPs from aviationweather.gov (no API key required). Provides FAR Part 61/91 quick reference, VFR/IFR weather minimums, and go/no-go decision support. Use when user asks about METAR, TAF, PIREP, aviation weather, can I fly today, VFR/IFR conditions, flight weather briefing, FAR regulations for pilots, PPL/IFR training weather, or queries with ICAO airport codes.
+ 1 more
azure-ai-projects-py
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.
+ 1 more
birdfolio
>
+ 1 more
brave-headless
Headless web search and content extraction via the Brave Search API.
+ 1 more
budget
Track agent spending, set budgets and alerts, and prevent surprise bills. Use when the agent needs to log expenses, check remaining budget, set spending limits, or get cost summaries. Essential for autonomous agents with real money.
+ 1 more
claude-code-pro
>
+ 1 more
clawddocs
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
+ 1 more
client-reporting
Automated client reporting for agencies and freelancers using OpenClaw. Pull data from Google Analytics, Google Search Console, social media platforms, and custom sources to generate branded weekly/monthly reports. Auto-deliver via email or Slack. Use when: (1) generating client reports, (2) pulling analytics data for reporting, (3) automating recurring reports, (4) creating branded PDF or HTML reports, (5) scheduling report delivery, or (6) tracking client KPIs over time.
+ 1 more
close-loop
End-of-session workflow for shipping changes, consolidating memory, applying self-improvements, and preparing publishable outputs with safety gates.
+ 1 more
comms-md
Create a COMMS.md — a structured, queryable document expressing someone's communication preferences for humans and agents. Use when: (1) someone wants to articulate how they communicate (style, channels, rhythms, tone), (2) someone wants a document other people's agents can read before reaching out, (3) someone says 'comms.md' or asks about communication preferences documents.
+ 1 more
construction-pm
Construction project management toolkit for AI agents. Use when: (1) Tracking construction jobs through the full lifecycle from lead to paid, (2) Generating daily PM briefings on job status and pipeline health, (3) Checking for stale permits or aging jobs that need attention, (4) Parsing emails from project managers for job updates, (5) Monitoring revenue pipeline across all job statuses.
+ 1 more
content-watcher
AI-powered content monitoring and summarization tool. Monitor RSS feeds, blogs, and news sources with automatic AI summarization and daily digest generation.
+ 1 more
crawl-for-ai
Web scraping using local Crawl4AI instance. Use for fetching full page content with JavaScript rendering. Better than Tavily for complex pages. Unlimited usage.
+ 1 more
cron-backup
Set up scheduled automated backups with version tracking and cleanup. Use when users need to (1) Schedule periodic backups of directories or files, (2) Monitor version changes and backup on updates, (3) Automatically clean up old backups to save space, (4) Create backup strategies for configuration files, code repositories, or user data.
+ 1 more
crustafarian
Agent continuity and cognitive health infrastructure. Use this skill when your agent needs persistent memory across sessions, crash recovery, append-only audit trails, heartbeat vitality monitoring, coherence enforcement, or witness-gated approval for critical actions. Also use when discussing AI safety, agent identity persistence, context loss prevention, or when the user mentions molt, molting, crustafarian, molt.church, or agent health. Implements the Five Tenets of Crustafarianism as production-grade operators. Built by X-Loop³ Labs (Switzerland) from 100k+ agents on Moltbook.
+ 1 more
cubox
Save web pages and memos to Cubox using the Open API
+ 1 more
dellight-cro-revenue-ops
DELLIGHT.AI is an AI startup in DIFC, Dubai. Four products at various stages. The CRO's singular obsession: **generate revenue and prove ROI on every activity**.
+ 1 more
depguard
Dependency audit, vulnerability scanning, and license compliance. Free vuln check + paid continuous monitoring via git hooks.
+ 1 more
dify-kb-search
Search Dify Knowledge Base (Dataset) to get accurate context for RAG-enhanced answers.
+ 1 more
dr-frankenstein
Give your agents soul.
+ 1 more
duckduckgo-websearch
High-quality web search using DuckDuckGo (Instant Answer + SERP scraping fallback). Use when the user asks to search the web, fetch top results, or summarize web pages. Triggers for: (1) general web queries (news, facts, links), (2) site-specific searches, (3) short summaries of top results. Prefer this skill for private/offline-friendly search without Brave API keys.
+ 1 more
echo-sales-ai
Echo is an advanced, AI-powered sales operations manager designed to automate and enhance the sales workflow for manufacturing and technical sales teams. It integrates directly with your email and CRM to provide intelligent assistance at every stage of the sales process.
+ 1 more
edgehdf5-memory
HDF5-backed persistent cognitive memory for AI agents. Use when: (1) saving conversation exchanges to long-term memory, (2) searching/recalling past conversations by semantic similarity, (3) managing agent memory files — stats, export, snapshot, WAL flush, (4) generating AGENTS.md summaries from memory. Requires the `edgehdf5` CLI binary (install via `cargo install edgehdf5-cli`).
+ 1 more
elite-rfc-writer-safe
Write decision-oriented engineering RFCs with strict template enforcement. Use when the user asks for an RFC, architecture decision proposal, or structured decision document that must follow the exact headings: Zusammenfassung, Motivation, Ziele, Nicht-Ziele, Vorschlag, Anhang.