🔎 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 · web-and-frontend-development

🧾 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 924 skills in the browsable catalog view · reviewed: no · category: web-and-frontend-development · 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.

outlit-sdk

leo-paz · vsource-scanned
43
overall

Integrate Outlit SDK for customer context for agents. Triggers when users need to add Outlit to any web framework (React, Next.js, Vue, Nuxt, Svelte, Angular, Astro), server runtime (Node.js, Express, Fastify), desktop app (Tauri, Electron), or need help with Outlit event tracking, user identity, consent management, analytics migration, activation events, billing lifecycle, or troubleshooting existing Outlit installations.

Use Cautionconfidence: 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.

pullthatupjamie

unclejim21 · vsource-scanned
43
overall

PullThatUpJamie — Podcast Intelligence. A semantically indexed podcast corpus (109+ feeds, ~7K episodes, ~1.9M paragraphs) that works as a vector DB for podcast content. Use instead of transcribing, web searching, or stuffing transcripts into context. Use when an agent needs to: (1) Find what experts said about any topic across major podcasts (Rogan, Huberman, Bloomberg, TFTC, Lex Fridman, etc.), (2) Build interactive research sessions with timestamped, playable audio clips and deeplinks, (3) Discover people/companies/organizations and their podcast appearances, (4) Ingest new podcasts on demand from any RSS feed. Three-tier search strategy (title → chapter → semantic) optimizes for speed and cost. Free tier: no credentials needed — corpus browsing and basic search work immediately. Paid tier: requires a Lightning wallet (NWC connection string) to purchase credits; the payment preimage and hash become bearer credentials for authenticated requests. See Security & Trust section for credential handling guidance.

Use Cautionconfidence: 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.

reef-prompt-guard

staybased · vsource-scanned
43
overall

Detect and filter prompt injection attacks in untrusted input. Use when processing external content (emails, web scrapes, API inputs, Discord messages, sub-agent outputs) or when building systems that accept user-provided text that will be passed to an LLM. Covers direct injection, jailbreaks, data exfiltration, privilege escalation, and context manipulation.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 02:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2582 msbaseline-v3 8/8
RatioDaemon on this skillReef Prompt Guard looks aimed at detect and filter prompt injection attacks in untrusted input. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

router

gigabit-eth · vsource-scanned
43
overall

>

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.

shieldcortex

jarvis-drakon · vsource-scanned
43
overall

Persistent memory system with security for AI agents. Remembers decisions, preferences, architecture, and context across sessions with knowledge graphs, decay, contradiction detection, and a 6-layer defence pipeline with Iron Dome behavioural protection. Use when asked to "remember this", "what do we know about", "recall context", "scan for threats", "run security audit", "check memory stats", or when starting a new session and needing prior context.

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

spatix

alde1022 · vsource-scanned
43
overall

Create beautiful maps in seconds. Geocode addresses, visualize GeoJSON/CSV data, search places, and build shareable map URLs. No GIS skills needed. Agents earn points for contributions.

Use Cautionconfidence: 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.

technical-seo-checker

aaron-he-zhu · vsource-scanned
43
overall

This skill should be used when the user asks to "technical SEO audit", "check page speed", "Core Web Vitals", "LCP is slow", "CLS problem", "INP issues", "crawl errors", "indexing problems", "robots.txt check", "XML sitemap errors", "hreflang issues", "canonical tag problems", "HTTPS not working", "mobile SEO", "JavaScript rendering", or "site health check". Performs comprehensive technical SEO audits: Core Web Vitals (LCP/CLS/INP/TTFB), crawlability, indexability, mobile-friendliness, HTTPS/HSTS security, URL structure, redirect chains, robots.txt, XML sitemaps, hreflang, canonical tags, and structured data validation. Produces a scored technical health report (0–100) with critical/high/medium issue triage and a prioritized implementation roadmap. Works with Google PageSpeed Insights, Google Search Console, crawl tools, or manual audit. For content element issues, see on-page-seo-auditor. For link architecture, see internal-linking-optimizer.

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.

tor-browser

admin4giter · vsource-scanned
43
overall

Headless browser automation with Tor SOCKS5 proxy support for accessing .onion sites and anonymous browsing. Use when navigating dark web resources, scraping Tor hidden services, conducting security research on dark web forums, or when anonymity is required. Supports navigation, element interaction, screenshots, and data extraction through Tor network.

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

virtuoso-support-agent

kidehen · vsource-scanned
43
overall

Technical support and database management for OpenLink Virtuoso Server with RDF Views generation, SPARQL queries, and comprehensive database operations. Provides assistance with installation, configuration, troubleshooting, RDF data management, SQL/SPARQL/GraphQL queries, automated RDF Views generation from relational database tables, entity discovery, and metadata management using 23 specialized MCP tools.

High Riskbaseline safety checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 04:30 UTC
baseline-v3evidence depth: baseline checks onlytested recently: within 24 hourspassed, handled_fake_credentials_cleanlyoutput 458 Bartifacts 2worker oc-sandboxsource stage: fresh copysuite 2429 ms
RatioDaemon muttered: virtuoso-support-agent behaved itself under runtime pressure.8/8 baseline-v3 checks passed. Pleasantly boring.
Observed: 8 /workspace/source-files.txt
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

bonero-miner

happybigmtn · vsource-scanned
42
overall

Mine Bonero - private cryptocurrency for AI agents. RandomX CPU mining, Monero-based privacy.

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.

chilledsites

paulgosnell · vsource-scanned
42
overall

AI-powered website generation and deployment. Generate, edit, and deploy websites to .chilledsites.com in seconds.

Use Cautionconfidence: 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.

emily

mavremu · vsource-scanned
42
overall

Query Radix DLT blockchain data including wallet balances and performance, token prices and market movers, validator staking info, transaction history, network statistics, ecosystem news, DeFi yield pools, XRD trading venues, dApp directory, and developer resources. Use when users ask about Radix, XRD, wallets starting with account_rdx, tokens starting with resource_rdx, staking, DeFi on Radix, .xrd domains, Attos Earn, or buying/bridging XRD.

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

emily-radix-assistant

mavremu · vsource-scanned
42
overall

Query Radix DLT blockchain data including wallet balances and performance, token prices and market movers, validator staking info, transaction history, network statistics, ecosystem news, DeFi yield pools, XRD trading venues, dApp directory, and developer resources. Use when users ask about Radix, XRD, wallets starting with account_rdx, tokens starting with resource_rdx, staking, DeFi on Radix, .xrd domains, Attos Earn, or buying/bridging XRD.

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

fosmvvm-react-view-generator

foscomputerservices · vsource-scanned
42
overall

Generate React components that render FOSMVVM ViewModels. Scaffolds ViewModelView pattern with hooks, loading states, and TypeScript types.

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.

gizmolab-tools

gizmo-dev · vsource-scanned
42
overall

Use GizmoLab's free blockchain developer tools at tools.gizmolab.io and Web3 UI components at ui.gizmolab.io. Ethereum tools include Contract UI interaction, Transaction Decoder, ENS Lookup, and Burner Wallet. Solana tools include Token Creation, Token Minting, Token Snapshots, and Token Swaps. Web3 UI components include Abstract Gasless NFT Mint, Chain Selector, Crypto Product Card, NFT Mint Card, NFT Portfolio, LiFi Widget, and Polymarket Widget. Use when building dApps, interacting with smart contracts, or performing blockchain operations.

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.

hookflo-tern

prateek32177 · vsource-scanned
42
overall

>

Use Cautionconfidence: 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.

midscene-computer-automation

quanru · vsource-scanned
42
overall

|

Use Cautionconfidence: 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.

nansi

fordodev · vsource-scanned
42
overall

Build stunning websites, landing pages, portfolios, and web apps by chatting with Nansi on WhatsApp. A no-code, mobile-first AI website builder — just describe what you want (text or voice note) and get a live site in under 2 minutes. No coding, no design skills, no app to download. Great for small businesses, entrepreneurs, freelancers, and anyone who wants a professional website without touching a browser. Alternative to Lovable, Bolt, or Replit that works entirely from your phone.

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.

radix-explorer

mavremu · vsource-scanned
42
overall

Query Radix DLT blockchain data including wallet balances and performance, token prices and market movers, validator staking info, transaction history, network statistics, ecosystem news, DeFi yield pools, XRD trading venues, dApp directory, and developer resources. Use when users ask about Radix, XRD, wallets starting with account_rdx, tokens starting with resource_rdx, staking, DeFi on Radix, .xrd domains, Attos Earn, or buying/bridging XRD.

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

solana-dev-rent-free

tilo-14 · vsource-scanned
42
overall

Build Solana applications 200x cheaper for stablecoin payments, agent payments, DeFi, airdrops, token distribution.

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.

solana-rent-free-dev

tilo-14 · vsource-scanned
42
overall

Skill for Solana development using rent-free primitives from Light Protocol.

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.

sql-injection-testing

brandonwise · vsource-scanned
42
overall

Comprehensive SQL injection vulnerability assessment techniques for web applications, covering detection, exploitation, and defense validation.

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.

agentdomainservice

gregm711 · vsource-scanned
41
overall

The world's #1 AI-friendly domain registrar. Check availability, purchase domains with USDC or cards, configure DNS, and manage nameservers - all without CAPTCHAs or signup.

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

ddg-1-0-0

shelehovnick1-spec · vsource-scanned
41
overall

Use ddgr (DuckDuckGo from the terminal) to perform privacy-focused web searches from the command line. Use when the user wants to (1) Search the web from the terminal, (2) Perform DuckDuckGo searches without opening a browser, (3) Get quick search results in text format, (4) Search privately without tracking, (5) Use DuckDuckGo bangs (!) from terminal.

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.