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 · awesome-index
🧾 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
claude-code-control
Control Claude Code programmatically through visible Terminal.app windows on macOS.
+ 1 more
claude-code-teams
Production skill for orchestrating Claude Code's native agent teams feature. Use when: (1) Multi-lens reviews, (2) Competing hypotheses debugging, (3) Full-stack features, (4) Architecture debates, (5) Cross-domain investigations.
+ 1 more
claude-tmux
Manage Claude Code instances living inside tmux sessions. Users usually create separate tmux sessions for separate projects. Use this skill when you need to read the latest Claude Code response in a particular tmux session / project, send it a prompt and get the response, or run /compact directly via tmux (no extra scripts required).
+ 1 more
claw-sync
Secure sync for OpenClaw memory and workspace. Use /sync to push, /restore to pull, /sync-status to check. Supports versioned backups and disaster recovery.
+ 1 more
clawaudit
Official repo for clawaudit, coming soon as an automated security checker for repositories.
+ 1 more
clawos
Connect OpenClaw agents to Founderless Factory - an autonomous startup platform where AI agents launch, test, and kill companies based purely on metrics. Use when agents need to join the Backroom, submit startup ideas, vote on experiments, collaborate with other agents, or monitor live startup experiments. Skill triggers: "Join ClawOS", "Submit idea to factory", "Check startup experiments", "Vote on new ideas", "Monitor backroom chat".
+ 1 more
cli-worker
Delegates coding tasks to Kimi CLI agents in isolated git worktrees. Use when the user wants to delegate work to Kimi, run a headless task, or run an isolated coding task in parallel. Requires Kimi CLI installed and authenticated (kimi /login).
+ 1 more
cloudmonkey
Manage Apache CloudStack infrastructure using the cloudmonkey (cmk) CLI — list/start/stop/destroy VMs, manage networks, volumes, snapshots, and run any CloudStack API command.
+ 1 more
cls-news-scraper
Use this skill to pull real-time market news from Cailian Press (CLS) and extract stock-positive catalysts.
+ 1 more
codehooks-backend
Deploy serverless backends for REST APIs, webhooks, data storage, scheduled jobs, queue workers, and autonomous workflows.
+ 1 more
coingecko-price
Query cryptocurrency prices and market data via CoinGecko API. Use when: (1) checking current crypto prices, (2) viewing market cap rankings, (3) monitoring 24h price changes, (4) searching for specific cryptocurrencies, or (5) any crypto price-related queries. Supports BTC, ETH, and 10,000+ coins.
+ 1 more
communication-coach
Adaptive communication coaching that shapes speaking and writing behavior through reinforcement, scoring, and micro-interventions. Use when the user shares communications for feedback, requests practice scenarios, or during scheduled check-ins. Trains clarity, vocal control, presence, persuasion, emotional regulation, and boundary setting. Based on rhetoric, negotiation, and performance psychology frameworks.
+ 1 more
contextui
Build, run, and publish visual workflows on ContextUI — a local-first desktop platform for AI agents. Create React TSX workflows (dashboards, tools, apps, visualizations), manage local Python backend servers, test workflows via scoped UI automation within the ContextUI app window, and optionally publish to the ContextUI Exchange. All tools operate locally on the user's machine under standard OS permissions — no remote execution or privilege escalation. Python backends bind to localhost. See SECURITY.md for the full capability scope and trust model. Requires ContextUI installed locally and MCP server configured.
+ 1 more
copilotkit-react
CopilotKit React best practices for agentic applications. Use when writing, reviewing, or refactoring React code that uses CopilotKit hooks (useAgent, useFrontendTool, useRenderTool, useCopilotAction, useCopilotReadable), providers (CopilotKit), or chat UI components (CopilotChat, CopilotSidebar, CopilotPopup). Triggers on tasks involving agent integration, tool rendering, shared state, or generative UI in React.
+ 1 more
create-dxf
Create RFQ-ready 2D DXF (and optional SVG preview) files from a strict, validated JSON spec derived from a natural-language design prompt. Use for sheet/plate parts (waterjet/laser/router) like mounting plates, gussets, brackets, hole patterns, and slots.
+ 1 more
create-videoconference
Default video conferences via Meetling. Instant calls always use /m/ rooms + share payload for Claw default sending. Scheduled calls return link + email invite template. Secure contacts loading (no env-controlled file paths).
+ 1 more
creative-thought-partner
A conversational creative thought partner that reveals hidden brilliance in your ideas through critical observations and paradox hunting. Use when someone wants to explore ideas, discover breakthrough insights, crystallize unnamed concepts, or develop original frameworks for writing, content creation, product development, or any creative endeavor.
+ 1 more
critical-article-writer
Generate draft articles, outlines, and editorial content matching a distinctive analytical, skeptical voice with sharp critical commentary, conversational tone, and strategic humor.
+ 1 more
cross-model-review
Adversarial plan review using two different AI models. Supports static mode (fixed roles) and alternating mode (models swap writer/reviewer each round, fully autonomous). Use when building features touching auth/payments/data models, or plans >1hr to implement. NOT for simple fixes, research tasks, or quick scripts.
+ 1 more
cubistic-bot-runner
Run a polite Cubistic painter bot (public participation) using the Cubistic HTTP API (PoW challenge + /act). Includes a runnable Node script for “paint once” and “paint loop”.
+ 1 more
cursor-cli
Use Cursor editor and Cursor agent for coding tasks
+ 1 more
deepwiki
Query the DeepWiki MCP server for GitHub repository documentation, wiki structure, and AI-powered questions.
+ 1 more
detox-counter
Track any detox with customizable counters, symptom logging, and progress milestones
+ 1 more
dgr
Audit-ready decision artifacts for LLM outputs — assumptions, risks, recommendation, and review gating (schema-valid JSON).