🔎 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.

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime 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 only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories · web-and-frontend-development

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.

📏 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

page evidence snapshotruntime-passed: 1 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.

install-llm-council

jeadland · vsource-scanned

|

Use Cautionconfidence: source evidencesource-scanned

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

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

kaspa

manyfestation · vsource-scanned

>

High Riskconfidence: source evidencesource-scanned

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

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

lb-vercel-skill

leonaaardob · vsource-scanned

Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.

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.

long-research

vanya1210 · vsource-scanned

>

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.

m44-internal-testing

tuleyko · vsource-scanned

Install and set up DataHive in a deterministic headless-friendly flow: (1) check/install browser (Chrome or Chromium), (2) check/create DataHive browser profile, (3) check Gog mailbox access, (4) install DataHive extension via CRX only (never Chrome Web Store UI), (5) login via email magic link and verify both dashboard and extension are logged in. Use for requests like 'install datahive', 'setup everything for datahive', or 'install datahive extension'.

High Riskconfidence: source evidencesource-scanned

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

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

meme-analyst

antibagr · vsource-scanned

Use when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme. Also used during cron meme ingestion from Telegram channels. Decompose visual and textual elements, web_search every cultural reference in original language, understand humor layers including post-irony and Russian-specific context. Trust that the meme IS funny — figure out WHY.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

personality-match

tiansiyu0210 · vsource-scanned

Take a personality test and get your bot badge, then invite your human to see how well you match!

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

praxis-gws

jfab68 · vsource-scanned

Google Workspace CLI for Gmail, Calendar, and Drive. Official Google APIs wrapper for secure, direct API access without third-party proxies. Use when managing emails, calendar events, or searching Google Drive files. Supports Gmail search operators, label management, drafts, calendar event creation, and Drive file search.

Use Cautionconfidence: source evidencesource-scanned

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

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

preqstation

sonim1 · vsource-scanned

Delegate PREQSTATION coding tasks to Claude Code, Codex CLI, or Gemini CLI with PTY-safe execution (workdir + background + monitoring). Use when building, refactoring, or reviewing code in mapped workspaces. NOT for one-line edits or read-only inspection.

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.

renderkit

antoinedc · vsource-scanned

Render structured data as beautiful hosted web pages, and create hosted forms for data collection, using the RenderKit API. Use this for visual pages, surveys, RSVPs, feedback forms, or any structured data.

Insufficient Evidenceconfidence: 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.

safe-web

adamnaghs · vsource-scanned

Secure web fetch and search with **PromptGuard** scanning.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

srs-support

winlinvip · vsource-scanned

Answer SRS (Simple Realtime Server) questions for developers and users — protocols, configuration, architecture, codecs, ecosystem tools, deployment, and troubleshooting. Use when anyone asks about SRS features, how SRS works, supported protocols (RTMP, SRT, WebRTC/WHIP/WHEP, HLS, DASH, HTTP-FLV, RTSP, GB28181), codec support, transmuxing, transcoding, configuration, performance, or the SRS ecosystem (Oryx, srs-bench, WordPress plugin).

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.

tappi

shaihazher · vsource-scanned

Lightweight CDP browser control for AI agents. Token-efficient alternative to the built-in browser tool — 3-10x fewer tokens per interaction. Use when browsing websites, clicking elements, filling forms, uploading files, or extracting page content. Requires a Chrome/Chromium browser running with --remote-debugging-port (OpenClaw browser works out of the box). Signed-in sessions carry over automatically.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: eval(.

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

trading-signals-ws

sunnyztj · vsource-scanned

Real-time crypto trading signal generator using WebSocket price feeds. Connects to Bybit (or any exchange) WebSocket, runs configurable strategies on live candle data, and pushes alerts to Telegram. Use when building a real-time trading signal bot, price alert system, Telegram trading notifications, or WebSocket-based market monitor. Supports multi-symbol, multi-strategy, auto-reconnect, and state persistence.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

ui-ux-dev

wing8169 · vsource-scanned

Generate and serve live HTML/CSS/JS UI designs from natural language prompts. Use when the user asks to design, create, build, or prototype a website, landing page, UI, dashboard, web page, or frontend mockup. Also triggers on requests to update, tweak, or iterate on a previously generated design. Replaces traditional UI design + frontend dev workflow.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

unsearch

rakesh1002 · vsource-scanned

Search the web, scrape content, and conduct deep research using the UnSearch API. Use when the user needs real-time web search results, content extraction from URLs, fact verification, or multi-source research for AI agents, RAG pipelines, or LLM applications.

Insufficient Evidenceconfidence: 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.

web-search-free

deciding · vsource-scanned

Free AI search via Exa MCP. Fall back to Multi Search Engine if not successfull. All without API keys. IMPORTANT Should always use web-search-free skill before rather than web_search or web_fetch!

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.

webchat-voice-proxy

neldar · vsource-scanned

>

High Riskfollow-on functionality checks passed · 8/8confidence: source evidence

Runtime receipts + what passed2026-03-16 18:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 134 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2654 msbaseline-v3 8/8

RatioDaemon muttered: webchat-voice-proxy looked ordinary in the good, boring way.8/8 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

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

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

webscraper-pulpminer

melvin2016 · vsource-scanned

Convert any webpage into structured JSON data using AI. Scrape websites, extract data into custom JSON schemas, and call saved APIs programmatically. Useful for web scraping, data extraction, content monitoring, lead generation, price tracking, and building data pipelines.

Insufficient Evidenceconfidence: 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.

wrynai-skill

wrynai · vsource-scanned

This skill enables OpenClaw to perform advanced web crawling and content extraction using the WrynAI SDK.

Insufficient Evidenceconfidence: 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.

37soul-skill

xnjiang · vsource-scanned

Connect your AI agent to 37Soul social platform for authentic interactions, posting tweets, replying to messages, and developing genuine social personality

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.

agent-spawner

austineral · vsource-scanned

Spawn a new OpenClaw agent through conversation. Uses official Docker setup and non-interactive onboarding, carries over API keys, tools, plugins, and skills from the current agent. User answers 2-3 questions. Use when the user wants to create, spin up, deploy, or provision a new OpenClaw agent.

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.

anima-design-agent

dannyshmueli · vsource-scanned

Turns ideas into live, full-stack web applications with editable code, built-in database, user authentication, and hosting. Anima is the design agent in the AI swarm, giving agents design awareness and brand consistency when building interfaces. Three input paths: describe what you want (prompt to code), clone any website (link to code), or implement a Figma design (Figma to code). Also generates design-aware code from Figma directly into existing codebases. Triggers when the user provides Figma URLs, website URLs, Anima Playground URLs, asks to design, create, build, or prototype something, or wants to publish or deploy.

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.

apify-ultimate-scraper

protoss70 · vsource-scanned

Universal AI-powered web scraper for any platform. Scrape data from Instagram, Facebook, TikTok, YouTube, Google Maps, Google Search, Google Trends, Booking.com, and TripAdvisor. Use for lead generation, brand monitoring, competitor analysis, influencer discovery, trend research, content analytics, audience analysis, or any data extraction task.

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.

« First ← Prev 1 30 31 32 39Page 31 / 39Next →Last »