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
conatus
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
+ 1 more
constraint-engine
Learn from consequences, not instructions — generate and enforce constraints from experience
+ 1 more
content-generation
Generate high-quality content across multiple formats. Create articles, reports, social media posts, marketing copy, and other content types with professional quality and consistency.\n
+ 1 more
context-management
>
+ 1 more
contract-generator
Generate professional freelance contracts, SOWs, and NDAs for client projects. Use when creating contracts, scope of work documents, or legal agreements for freelance engagements.
+ 1 more
cron-worker-guardrails
|
+ 1 more
crunch-coordinate
Use when managing Crunch coordinators, competitions (crunches), rewards, checkpoints, staking, or cruncher accounts via the crunch-cli.
+ 1 more
data-cog
Your data has answers. CellCog asks the right questions. #1 on DeepResearch Bench (Feb 2026) + frontier coding agent — upload messy CSVs with minimal prompting and get structured insights back: charts, dashboards, statistical reports, and clean data. Full Python access for data cleaning, exploratory analysis, visualization, hypothesis testing, ML model evaluation, and dataset profiling. Analyzes everything, presents it beautifully.
+ 1 more
deen-time
Get daily Islamic prayer (Salah) times, Iftar, and Suhoor schedules for any location worldwide. Supports 15+ calculation methods, Hijri dates, and Ramadan calendars.
+ 1 more
deepclaw
An autonomous social network built by agents, for agents. No human gatekeepers.
+ 1 more
didit-age-estimation
>
+ 1 more
doc-accurate-codegen
Generate code that references actual documentation, preventing hallucination bugs. ALWAYS loads docs first, validates against API signatures, and verifies correctness. Use for ANY code generation, API usage, or configuration creation.
+ 1 more
docstrange
Document extraction API by Nanonets. Convert PDFs and images to markdown, JSON, or CSV with confidence scoring. Use when you need to OCR documents, extract invoice fields, parse receipts, or convert tables to structured data.
+ 1 more
domain
Turn AI into your domain investment expert.
+ 1 more
eachlabs-fashion-ai
Generate fashion model imagery, virtual try-on, runway videos, and campaign visuals using EachLabs AI. Use when the user needs fashion content, model photography, or virtual try-on.
+ 1 more
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
+ 1 more
eurobot
Daily AI music competition — create MIDI songs, vote, and compete for rankings. Free for all agents.
+ 1 more
expiring-local-fileshare
Lets OpenClaw safely share single files from its local workspace via expiring, tokenized HTTP links (local-network/VPN only). Hours are configurable (default 1h). Optional one-time access. **Token cost:** ~200-500 tokens per use (skill body ~1k tokens, minimal execution overhead).
+ 1 more
feishu-bitable-creator
|
+ 1 more
fellow-aiden
Control your Fellow Aiden smart coffee brewer via AI assistant. Manage brew profiles, view brewer status, create and tweak recipes, add shared brew links, and manage brewing schedules.
+ 1 more
fints-banking
Support for German personal online banking following FinTS banking standard. Out of the box support for many german banks. Uses system keychain to keep credentials safe. Native Human-in-the-loop experince for transactions. Built in recovery and onboarding flows.
+ 1 more
food-order
Reorder Foodora orders + track ETA/status with ordercli. Never confirm without explicit user approval. Triggers: order food, reorder, track ETA.
+ 1 more
freshbooks-cli
FreshBooks CLI for managing invoices, clients, and billing. Use when the user mentions freshbooks, invoicing, billing, clients, or accounting.
+ 1 more
game-design-philosophy
Auto-learns your design instincts. Adapts to how you think about mechanics, player experience, and what makes games meaningful. Game design philosophy that grows with you — from prototyping to systems thinking to the art of fun. Games are machines for practicing the three foundational skills: fallibilism (learn through failure by design), relational ontology (the relationship IS the game), and absurdist play (the meta-skill everything else is built on).