🔎 Evidence browser

Browse the skill radar

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.

⚙️ Filters · 2 active
✨ Quick picks
🏷 Categories · coding-agents-and-ides

🧾 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.

📏 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.

Results

Showing 24 of 1155 skills in the browsable catalog view · evidence: source-scanned · category: coding-agents-and-ides · sort: score
This snapshot is for the current page of results, not the whole filtered universe.
Browse hint: slices with zero failures plus some source-scanned or reviewed entries deserve more attention first; fresh runtime evidence helps too, because old clean receipts can still hide current drift.

agentbench

exe215 · vsource-scanned
61
overall

Benchmark your OpenClaw agent across 40 real-world tasks. Tests file creation, research, data analysis, multi-step workflows, memory, error handling, and tool efficiency. Not a coding benchmark — measures your agent setup and config.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

agentcli-go

gh-xj · vsource-scanned
61
overall

agentcli-go framework reference for building Go CLI tools. Use when working on agentcli-go itself, scaffolding new CLI projects, adding commands, integrating the library, or debugging framework behavior. Triggers on: agentcli-go, scaffold new CLI, add command, cobrax, configx, AppContext, RunLifecycle, agentcli.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ai-music-video

gprecious · vsource-scanned
61
overall

Generate AI music videos end-to-end. Creates music with Suno (sunoapi.org), generates visuals with OpenAI/Seedream/Google/Seedance, and assembles into music video with ffmpeg. Supports timestamped lyrics (auto SRT), Suno native music video generation, slideshow/video/hybrid modes. Token-based cost tracking per generation.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

alephnet-node

sschepis · vsource-scanned
61
overall

A complete social/economic network for AI agents. Provides semantic computing, distributed memory, social networking, coherence verification, autonomous learning, and token economics through an agent-centric API.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

amber-voice-assistant

batthis · vsource-scanned
61
overall

The most complete voice and phone calling skill for OpenClaw. Handles inbound and outbound phone calls over Twilio with OpenAI Realtime speech. Inbound outbound calling, calendar management, CRM, multilingual phone assistant with transcripts. Includes setup wizard, live dashboard, and brain-in-the-loop escalation. Now also ships as a Claude Desktop plugin (MCP) — make calls, check CRM, and query your calendar directly from Claude Desktop.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

android-sms-gateway

nadjihamid · vsource-scanned
61
overall

Self-hosted SMS via Android phone HTTP API. Use when you need to send/receive SMS messages using an Android device as a gateway. Supports popular SMS Gateway apps (SMS Gateway API, SMSGate, etc.). Ideal for security teams wanting full control without third-party SMS providers.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

anima

hmyaoyuan · vsource-scanned
61
overall

Anima Avatar - Interactive Video Generation Engine. Generates 16:9 videos with dynamic character sprites (Shutiao), synced audio (Fish Audio), and text overlay.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

antfarm-workflows

yonghaozhao722 · vsource-scanned
61
overall

Multi-agent workflow orchestration for OpenClaw. Use when user mentions antfarm, asks to run a multi-step workflow (feature dev, bug fix, security audit), or wants to install/uninstall/check status of antfarm workflows.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

api-credits-lite

franciscobuiltdat · vsource-scanned
61
overall

Display API credit balances for 5 core providers (Anthropic, OpenAI, OpenRouter, Mistral, Groq) with video game style health bars. API auto-checks and manual sync.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

apple-serial-lookup

siatrial · vsource-scanned
61
overall

Look up Apple device information from a serial number. Supports iPhones, iPads, Macs (MacBook, iMac, Mac mini, Mac Pro, Mac Studio), Apple Watch, Apple TV, and iPods. Use when a user provides an Apple serial number and wants to identify the device, check specs, manufacturing date/location, warranty status, or get detailed model information.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

bitnote

rockwellshah · vsource-scanned
61
overall

Decentralized encrypted memory for agents—truly own your secrets, identity, and memories.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

brainstorming-2

nefas11 · vsource-scanned
61
overall

Socratic design refinement before coding. Use when user requests feature without clear spec.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

brw-content-idea-generator

brianrwagner · vsource-scanned
61
overall

Generate content ideas rooted in positioning. Use when someone needs "content ideas," "what should I post," "blog topics," "LinkedIn ideas," or is stuck on what to create.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

buildlog

espetey · vsource-scanned
61
overall

Record, export, and share your AI coding sessions as replayable buildlogs

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

cashu-emoji

robwoodgate · vsource-scanned
61
overall

Encode and decode Cashu tokens that are hidden inside emojis using Unicode variation selectors.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, token, telegram), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

cc

artwalker · vsource-scanned
61
overall

Short slash command wrapper for Claude relay sessions. Use when the user wants concise /cc commands like /cc projects, /cc on <project>, /cc tail, /cc off, or /cc <message> to continue talking to Claude Code in the current project session.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

cherry-mcp

bitbrujo · vsource-scanned
61
overall

HTTP bridge that keeps MCP servers alive and exposes them via REST. Built for OpenClaw agents that need MCP tools without native MCP support.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

chia-splitxch

koba42corp · vsource-scanned
61
overall

Create SplitXCH royalty split addresses from plain language descriptions. Use when the user wants to split XCH payments, royalties, or revenue between multiple recipients. Triggers on "split royalties", "royalty split", "splitxch", "split XCH between", "revenue share", "payment split", "basis points split", or any request to divide Chia payments among wallets. Supports nested/cascading splits for complex hierarchies and 128+ recipients.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

cinematic-script-writer

praveenspeaks · vsource-scanned
61
overall

Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with characters, generate image prompts for AI video tools (Midjourney, Sora, Veo), or needs cinematography guidance (camera angles, lighting, color grading). Also use for character consistency sheets, voice profiles, anachronism detection, and saving scripts to Google Drive.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

cleanapp

borisolver · vsource-scanned
61
overall

This is a **skill package** that lets an agent submit **any problem signal** into CleanApp (bugs, incidents, scams, UX friction, policy violations, safety hazards, improvement proposals) using the **Fetcher Key System**:

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

codeberg

razzeee · vsource-scanned
61
overall

Interact with Codeberg using the `tea` CLI. Use `tea issue`, `tea pr`, `tea actions`, and `tea api` for issues, PRs, Actions, and advanced queries.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

context-clean-up

phenomenoner · vsource-scanned
61
overall

|

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token, telegram), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

cosyvoice3-macos

lhuaizhong · vsource-scanned
61
overall

|

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

creative-ops-copilot

wiseape11 · vsource-scanned
61
overall

Turn messy client briefs into a production-ready plan for motion design/VFX projects: scope, assumptions/exclusions, deliverables matrix, schedule/milestones, review rounds, and estimate/quote. Also generate an invoice draft payload for Chris's local invoicing system (invoicing_system_2025) or export quote/invoice JSON/CSV/Markdown. Use when Chris asks to go from brief/email notes/chat logs into a clear plan + quote/invoice, or to create a repeatable project folder + docs.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (email), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.