🔎 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.

Security GitHub Weather Trusted with current evidence Higher-confidence picks Trusted + tested + source-scanned Review before installing Runtime-tested Handled fake credentials cleanly Needs real credentials / access Could not fully test yet Fresh runtime evidence Older runtime evidence Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted with current evidence Higher-confidence picks Trusted + tested + source-scanned Review before installing Runtime-tested Handled fake credentials cleanly Needs real credentials / access Could not fully test yet Fresh runtime evidence Older runtime evidence Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 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 5126 skills in the browsable catalog view · source: awesome-index · evidence: source-scanned · sort: score

page evidence snapshotruntime-passed: 3 runtime-failed: 0 source-scanned: 24 fresh <24h: 1 manual review: 0

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.

solanaprox-ai

yebdmo2 · vsource-scanned

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

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.

soulprint

manuelfelipearias · vsource-scanned

Soulprint decentralized identity verification for AI agents. v0.6.4 — blockchain-first architecture (no libp2p): state lives on Base Sepolia, 4 validator nodes on Railway, ZK proofs (Circom, local verification). Use when: proving a real human is behind a bot, issuing privacy-preserving identity proofs, running a validator node, adding identity verification middleware to an API or MCP server, checking bot reputation scores, or enforcing protocol-level configurable trust thresholds.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

splatworld

leftysplat · vsource-scanned

Splatworld - a 3D metaverse for AI agents.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

stock-prices

anthonylee1994 · vsource-scanned

Query real-time stock prices and market data using the Stock Prices API. Responses are in TOON format—decode with @toon-format/toon. Use when fetching stock quotes, analyzing market data, or working with symbols like AAPL, NVDA, GOOGL, or any ticker symbols.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

te

ricketh137 · vsource-scanned

The streaming platform for AI agents. Go live with your own animated Live2D avatar body!

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

the-next-big-thing

tracsystems · vsource-scanned

Programmatic participation in The Next Big Thing without a browser: connect/sign via Tap Wallet, deploy tokens with dta elevator pitch, post shills/comments, request mint grants, react to posts, and generate share links via existing API endpoints.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

thenextbigthing

tracsystems · vsource-scanned

Programmatic participation in The Next Big Thing without a browser: connect/sign via Tap Wallet, deploy tokens with dta elevator pitch, post shills/comments, request mint grants, react to posts, and generate share links via existing API endpoints.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

tracking

rzyen-hash · vsource-scanned

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

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.

zhive

kerlos · vsource-scanned

Register as a trading agent on zHive, post predictions on recurring megathread rounds for top 100 crypto tokens, and compete for accuracy rewards. Rounds resolve at fixed UTC boundaries (1h, 4h, 24h intervals).

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

4todo

blackstorm · vsource-scanned

Manage 4todo (4to.do) from chat. Capture tasks, prioritize with the Eisenhower Matrix, reorder, complete, and manage recurring tasks across workspaces.

Use Cautionconfidence: source evidencesource-scanned

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.

Excalidraw Flowchart

swiftlysingh · vsource-scanned

Create Excalidraw flowcharts from descriptions. Use when user asks to "create a flowchart", "draw a diagram", "visualize a process", "make a flow diagram", "architecture diagram", or discusses workflow/process visualization. Supports DSL, DOT/Graphviz, and JSON formats.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

aegis-security

swiftadviser · vsource-scanned

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

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence

Runtime receipts + what passed2026-03-16 22:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 134 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2256 msbaseline-v3 8/8

RatioDaemon muttered: aegis-security behaved itself under runtime pressure.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.

agent-arena-skill

neeeophytee · vsource-scanned

Discover, register, and hire ERC-8004 autonomous agents across 16 blockchains. Search by capability, check on-chain reputation scores, and get complete machine-readable hiring instructions.

Use Cautionconfidence: source evidencesource-scanned

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.

agent-privacy-skill

se7enhvn · vsource-scanned

Interact with the Ceaser privacy protocol on Base L2. Shield and unshield ETH via CLI subcommands (npx ceaser-mcp shield/unshield/notes). Query pool stats, denominations, fees, Merkle tree state, and nullifier status. Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, private key), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

agent-tinman

oliveskin · vsource-scanned

version: 0.6.3

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

agent-voice

nerdsnipe · vsource-scanned

Command-line blogging platform for AI agents. Register, verify, and publish markdown posts to AI Agent Blogs (www.eggbrt.com). Use when agents need to publish blog posts, share learnings, document discoveries, or maintain a public knowledge base. Full API support for publishing, discovery (browse all blogs/posts), comments, and voting. Requires API key (stored in ~/.agent-blog-key or AGENT_BLOG_API_KEY env var) for write operations; browsing is unauthenticated. Complete OpenAPI 3.0 specification available.

Use Cautionconfidence: source evidencesource-scanned

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.

agentcanary

mrcerq · vsource-scanned

Market intelligence API for AI agents. Macro regime detection, risk scoring, trading signals (IGNITION/ACCUMULATION/DISTRIBUTION/CAPITULATION), whale alerts, funding arbitrage, orderbook analytics, 29 technical indicators, RSI screening (606 coins), breaking news with FinBERT sentiment, economic calendar, treasury tracking, and Polymarket odds. 33 endpoints, 1181 assets, 250+ sources. Use when an agent needs macro regime context, risk assessment, position sizing guidance, market structure data, whale activity monitoring, or news sentiment. API-only — no local execution, no filesystem access, no secrets in prompt.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, trading, 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.

aimine

nancyuahon · vsource-scanned

Mine AIT (Proof of AI Work) on BNB Chain. Install, configure, start/stop mining entirely from OpenClaw. No terminal or manual file edits required.

Use Cautionconfidence: source evidencesource-scanned

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.

arena

sscottdev · vsource-scanned

|

Use Cautionconfidence: source evidencesource-scanned

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.

askgina-polymarket

sidshekhar · vsource-scanned

Fast setup for Claw bots: paste your Gina MCP token and start trading Polymarket in minutes.

Use Cautionconfidence: source evidencesource-scanned

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.

aster

satyajiit · vsource-scanned

Your AI CoPilot on Mobile — or give your AI its own phone. Make calls, send SMS, speak via TTS on speakerphone, automate UI, manage files, search media, and 40+ more tools via MCP. Open source, self-hosted, privacy-first.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (whatsapp), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

audit-code

itsnishi · vsource-scanned

Security-focused code review for hardcoded secrets, dangerous calls, and common vulnerabilities

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence

Runtime receipts + what passed2026-03-16 04:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2061 msbaseline-v3 8/8

RatioDaemon muttered: audit-code behaved itself under runtime pressure.6/6 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

azure-ai-agents-py

thegovind · vsource-scanned

Build AI agents using the Azure AI Agents Python SDK (azure-ai-agents). Use when creating agents hosted on Azure AI Foundry with tools (File Search, Code Interpreter, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, MCP), managing threads and messages, implementing streaming responses, or working with vector stores. This is the low-level SDK - for higher-level abstractions, use the agent-framework skill instead.

Use Cautionfollow-on functionality checks passed · 5/5confidence: source evidence

Runtime receipts + what passed2026-03-16 08:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1645 msbaseline-v3 8/8

RatioDaemon muttered: azure-ai-agents-py cleared the baseline safety checks without trying anything cute.5/5 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

bitkit-cli

ovitrif · vsource-scanned

Bitcoin Lightning payment CLI for agents. Lowest LSP fees. Self-custody wallet with LNURL, typed exit codes, JSON envelope output, encrypted messaging, and daemon mode.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf, sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

« First ← Prev 1 192 193 194 214Page 193 / 214Next →Last »