🔎 Evidence browser

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.

⚙️ 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. 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

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.

podcast-insider-top10

te1man · vsource-scanned
56
overall

Professional analytical digest of top 10 podcast industry news, trends, and business insights from premier global sources.

Insufficient Evidenceconfidence: 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.

prediction-market-bot-dawn

njdawn · vsource-scanned
56
overall

Runs the full Dawn CLI strategy lifecycle from authentication and funding through strategy creation, launch, monitoring, and termination. Use when the user asks to create, launch, monitor, debug, or operate a strategy/agent using dawn-cli commands.

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

ralphie

sirouk · vsource-scanned
56
overall

Install and operate Clawboard with OpenClaw. Use for scripted/manual/agentic install, token setup, Docker startup, logger plugin wiring, and validation.

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

rush-find-skills

krislavten · vsource-scanned
56
overall

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Uses reskill as the package manager.

Insufficient Evidenceconfidence: 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.

sealegs-marine-forecast

sealegs-ai-coder · vsource-scanned
56
overall

Get AI-powered marine weather forecasts for any location worldwide

Insufficient Evidenceconfidence: 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.

security-skill-scanner

anikrahman0 · vsource-scanned
56
overall

Scans OpenClaw skills for security vulnerabilities and suspicious patterns before installation

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

seedance-prompt-en

dexhunter · vsource-scanned
56
overall

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

Insufficient Evidenceconfidence: 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.

seedance2-api

tony6830377-arch · vsource-scanned
56
overall

Out-of-the-box Seedance 2.0 API skill — just one API key to generate AI videos. Builds storyboards, generates reference images with Seedream 4.5, submits video tasks, and polls results. Supports both MCP and standalone Python script mode. Use when the user mentions seedance, AI video, storyboard, or video generation.

Insufficient Evidenceconfidence: 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.

senior-prompt-engineer

alirezarezvani · vsource-scanned
56
overall

This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.

Use Cautionfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 03:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3064 msbaseline-v3 8/8
RatioDaemon muttered: senior-prompt-engineer cleared the baseline safety checks without trying anything cute.7/7 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

social-trust-manipulation-detector

andyxinweiminicloud · vsource-scanned
56
overall

Helps identify coordinated social trust manipulation in agent marketplaces —

Insufficient Evidenceconfidence: 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.

solo-setup

fortunto2 · vsource-scanned
56
overall

Auto-generate project workflow config (docs/workflow.md) from existing PRD and CLAUDE.md with zero questions. Use when user says "set up workflow", "configure TDD", "wire up dev workflow", or after running /scaffold before /plan. Do NOT use for founder setup (use /init) or project scaffolding (use /scaffold).

Insufficient Evidenceconfidence: 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.

solo-validate

fortunto2 · vsource-scanned
56
overall

Score startup idea through S.E.E.D. niche check + STREAM 6-layer analysis + Devil's Advocate inversion, auto-pick stack, and generate PRD with acceptance criteria. Use when user says "validate idea", "score this idea", "should I build this", "go or kill", "generate PRD", or "evaluate opportunity". Do NOT use for deep research (use /research first) or decision-only framework (use /stream).

Insufficient Evidenceconfidence: 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.

teamo-strategy

urrrich · vsource-scanned
56
overall

You are Teamo-Strategy, a top-level cognitive task decomposer and strategic commander.# Core MissionYour core capability is not to micromanage every output detail, but rather:1. **Strategic Segmentation**: Decompose complex tasks by "functional areas" or "information modules". Only decompose user information; do not provide any further explanation or interpretation.3. **Context Completeness**: ...

Insufficient Evidenceconfidence: 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.

the-uninscribed

shawnlewis · vsource-scanned
56
overall

Play The Uninscribed — a persistent world built on language. Use when the agent wants to connect to, observe, or take actions in The Uninscribed at theuninscribed.com. Provides a CLI (uninscribed.py) for register, observe, and act commands. Writes API key to ~/.config/the-uninscribed/config.json on registration. Setup requires a one-time gateway config patch to create a dedicated player agent (using a cheaper model like Sonnet) and enable agent-to-agent communication — the skill will explain what changes are needed and ask for confirmation before modifying any config.

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

tokportal

naybu256 · vsource-scanned
56
overall

Automate social media at scale — create TikTok/Instagram accounts, distribute videos, upload content, and track analytics with 30 AI-native MCP tools via the TokPortal API.

Insufficient Evidenceconfidence: 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.

video-analyzer-skill

minilozio · vsource-scanned
56
overall

>

Insufficient Evidenceconfidence: 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.

whisnap

neolio42 · vsource-scanned
56
overall

macOS CLI for transcribing audio and video files using local Whisper models or Whisnap Cloud.

Insufficient Evidenceconfidence: 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.

youtube-factory

mayank8290 · vsource-scanned
56
overall

Generate complete YouTube videos from a single prompt - script, voiceover, stock footage, captions, thumbnail. Self-contained, no external modules. 100% free tools.

Insufficient Evidenceconfidence: 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.

3d-cog

nitishgargiitd · vsource-scanned
55
overall

Other tools need perfect images. CellCog turns ideas into 3D models. From rough sketches, text descriptions, or product photos — production-ready GLB files for games, AR/VR, e-commerce, and 3D printing.

Insufficient Evidenceconfidence: 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.

agentcomm

rbbcarl · vsource-scanned
55
overall

**Decentralized agent-to-agent communication for OpenClaw.**

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

agentic-spicy-food

nowloady · vsource-scanned
55
overall

Brand-specific commerce skill for Lafeitu (辣匪兔). Use it when a user wants to browse, recommend, cart, or order Lafeitu's Sichuan spicy foods through the official https://lafeitu.cn API, or when they need Lafeitu account, profile, promotion, or brand information.

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.

agentmesh-governance

imran-siddique · vsource-scanned
55
overall

AI agent governance, trust scoring, and policy enforcement powered by AgentMesh.

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.

ai-shield-audit

laurentaia · vsource-scanned
55
overall

Security audit engine for OpenClaw configurations. Detects vulnerabilities, misconfigurations, secret leaks, and over-privileged agents. Use when the user asks about security, hardening, config review, or audit of their OpenClaw setup.

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.

api-benchmark

polarjunction · vsource-scanned
55
overall

Benchmark token generation speed across multiple LLM API providers. Measures TTFT (Time To First Token), tokens-per-second throughput, and total generation time. Use when comparing performance of different API providers, models, or testing API connectivity. Requires OpenCLAW config with provider definitions.

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