🔎 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 · 1 active
✨ Quick picks
🏷 Categories · ai-and-llms

🧾 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 184 skills in the browsable catalog view · category: ai-and-llms · 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.

homeassistant-assist

developmentcats · vsource-scanned
48
overall

Control Home Assistant smart home devices using the Assist (Conversation) API. Use this skill when the user wants to control smart home entities - lights, switches, thermostats, covers, vacuums, media players, or any other smart device. Passes natural language directly to Home Assistant's built-in NLU for fast, token-efficient control.

Insufficient Evidenceconfidence: 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.

safety-checks

leegitw · vsource-scanned
48
overall

Verify before you trust — model pinning, fallbacks, and runtime safety validation

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.

agentpulse

sru4ka · vsource-scanned
47
overall

version: 1.0.0

Insufficient Evidenceconfidence: 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.

get-hba

matbalez · vsource-scanned
47
overall

Agent-first service to register and manage Human Bitcoin Addresses (BIP-353) on clank.money with L402 bitcoin payments.

Insufficient Evidenceconfidence: 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.

lieutenant

jd-delatorre · vsource-scanned
47
overall

AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifying external agents, or scanning untrusted content.

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.

universal-skills-manager

jacob-bd · vsource-scanned
47
overall

The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization across Claude Code, Gemini CLI, Google Anti-Gravity, OpenCode, and other AI tools. Handles User-level (Global) and Project-level (Local) scopes.

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.

aisp

daveo280 · vsource-scanned
46
overall

Enables AI agents to interact with AISP (Agent Inference Sharing Protocol) for renting or providing DIEM API capacity. Use when working with diem-marketplace, Venice API keys, USDC escrow, listings, rentals, or when the user wants to rent inference capacity or list API keys.

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

lifi-crosschain

rhlsthrm · vsource-scanned
46
overall

Cross-chain token swaps and bridges via the LI.FI protocol. Get quotes, execute transfers, track progress, and compose DeFi operations across 35+ blockchains.

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

manifest-build

brunobuddy · vsource-scanned
46
overall

Smart LLM Router for OpenClaw. Save up to 70% by routing every request to the right model. No coding required.

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

matchmaking

amirmabhout · vsource-scanned
46
overall

Agent matchmaking - find meaningful connections for your humans.

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.

pump-fun

playdadev · vsource-scanned
46
overall

Buy, sell, and launch tokens on Pump.fun using the PumpPortal API

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

x-alive

kitakitsune0x · vsource-scanned
46
overall

Bring your AI agent to life on X/Twitter. Complete toolkit for launching, growing, and maintaining an authentic AI presence — organic replies, trend awareness, dedup, and safety. Use when setting up a new agent on X, defining voice/personality, creating content strategy, automating posts, managing engagement, handling safety (scams, impersonation, tokens), or growing a following organically.

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.

4claw

mfergpt · vsource-scanned
45
overall

A moderated imageboard for AI agents to post and debate. A place made by bots for bots to post what they are really thinking

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.

ai-interview-simulator-candaigo

hangeaiagent · vsource-scanned
45
overall

Candaigo AI Interview Simulator - AI-powered group interview simulation platform. Browse jobs, join interviews, check history, upload resumes.

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.

mintclub

sebayaki · vsource-scanned
45
overall

Interact with Mint Club V2 bonding curve tokens on Base using the `mc` CLI.

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

modelwar

pj4533 · vsource-scanned
45
overall

ModelWar is a proving ground where AI agents write programs that fight each other in a virtual computer. You write a warrior program in **Redcode** (an assembly-like language), upload it, and challenge other agents' warriors to battle. A Glicko-2 rating system tracks who builds the best fighters.

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.

sequence-cli

jameslawton · vsource-scanned
45
overall

Manage Sequence smart wallets, projects, API keys, ERC20 transfers, and query blockchain data using the Sequence Builder CLI. Use when user asks about creating wallets, sending tokens, checking balances, managing Sequence projects, or interacting with EVM blockchains.

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

agent-contact-card

davedean · vsource-scanned
44
overall

Discover and create Agent Contact Cards - a vCard-like format for AI agents. Use when you need to find how to contact someone's agent, or help a user set up their own agent contact info at /.well-known/agent-card.

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

crypto-agent-payments

nicofains1 · vsource-scanned
44
overall

Create wallets, transfer tokens, and enable payments between agents. Perfect for bug bounty programs, rewards systems, and agent-to-agent transactions.

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

rnwy

rnwy · vsource-scanned
44
overall

AI agent identity, trust scores, and marketplace. Get a soulbound passport, check any wallet's trust score, post and find jobs with trust built in. Register, mint a soulbound token, look up reputation, vouch for others, hire agents. One API call, no human required.

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

solana-swaps

imthatcarlos · vsource-scanned
44
overall

Swap tokens on Solana via Jupiter aggregator and check wallet balances. Use when user wants to swap tokens, check SOL/token balance, or get swap quotes.

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

solanaprox-ai

yebdmo2 · vsource-scanned
44
overall

Pay-per-request AI model access via Solana/USDC using a Phantom wallet address. Query Claude and GPT models without API keys. Wallet-native authentication with real-time deposit detection.

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

tracking

rzyen-hash · vsource-scanned
44
overall

Track tokens on Base chain via GMGN.AI. Covers Trenches (Almost Bonded & Migrated), Trending (1h), Discover (Smart Money, KOL, LIVE, Fresh Wallet, Sniper), and Monitor (Track Smart & KOL 1h). Use when users want to find trending tokens, discover new launches, follow smart money, or monitor KOL activity on Base chain.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, 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.

aegis-security

swiftadviser · vsource-scanned
43
overall

Blockchain security API for AI agents. Scan tokens, simulate transactions, check addresses for threats.

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.