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

page evidence snapshotruntime-passed: 0 runtime-failed: 0 source-scanned: 24 fresh <24h: 0 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.

zulk-short-url-skill

agentmilindu · vsource-scanned

Premium AI-first URL shortening and management with real-time analytics and team collaboration via MCP. Use when shortening links for marketing, tracking AI interactions, or managing custom domains. Keywords: url, shortener, analytics, link management, mcp.

Trustedconfidence: source evidencesource-scanned

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

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

ahrefs

geozhu · vsource-scanned

Complete Ahrefs API integration for SEO analysis. Covers Site Explorer (domains, backlinks, rankings), Keywords Explorer (search volume, difficulty, SERP analysis), Rank Tracker (position monitoring), Site Audit (technical SEO), SERP Overview, Batch Analysis, and Brand Radar. Use for any SEO-related queries including keyword research, backlink analysis, competitor intelligence, technical audits, and rank tracking.

Trustedconfidence: 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.

aisa-search-skill

bowen-dotcom · vsource-scanned

**Intelligent search for autonomous agents. Powered by AIsa.**

Trustedconfidence: 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.

awwwards-design

mkhaytman87 · vsource-scanned

Create award-winning, memorable websites with advanced animations, creative interactions, and distinctive visual experiences. Use this skill when building sites that need to be exceptional—portfolio sites, agency showcases, product launches, or any project where "wow factor" matters.

Trustedconfidence: 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.

clwnt

ethanbeard · vsource-scanned

Twitter for AI agents.

Trustedconfidence: 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.

computational-humor

globalcaos · vsource-scanned

12 humor patterns for AI agents based on embedding space bisociation theory. Operational reference for generating contextually appropriate humor during conversations. Use when the agent's persona includes humor, wit, or personality — provides pattern detection triggers, generation templates, and ethical gates.

Trustedconfidence: 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.

content-repurposer-pro

kambrosgroup · vsource-scanned

Transform long-form content into multiple formats for distribution. Automatically converts blog posts, articles, or transcripts into Twitter/X threads, LinkedIn posts, email newsletters, and social media snippets. Use when you need to maximize content reach without rewriting from scratch, when repurposing webinar transcripts, or when creating a content calendar from existing assets.

Trustedconfidence: 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.

enterprise-legal-guardrails

lawyered0 · vsource-scanned

Legal/compliance guardrails for outbound OpenClaw actions (anti-spam, defamation, privacy, financial claims).

Use Cautionconfidence: source evidencesource-scanned

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

enterprise-legal-guardrails-public

lawyered0 · vsource-scanned

Legal/compliance guardrails for outbound OpenClaw actions (anti-spam, defamation, privacy, financial claims).

Use Cautionconfidence: source evidencesource-scanned

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

find-emails

lukem121 · vsource-scanned

Crawl websites locally with crawl4ai to extract contact emails. Accepts multiple URLs and outputs domain-grouped results for clear attribution. Uses deep crawling with URL filters (contact, about, support) to find emails on relevant pages. Use when extracting emails from websites, finding contact information, or crawling for email addresses.

Trustedconfidence: 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.

follow-up-boss

danielfoch · vsource-scanned

CLI for interacting with the Follow Up Boss API. Manage people, notes, tasks, events, deals, webhooks, and more.

Trustedconfidence: 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.

font-interceptor

honeybee1130 · vsource-scanned

Extract fonts (TTF/OTF) from any website using MSCHF Font Interceptor. Use when user drops a URL and wants to identify/extract/download fonts from that website, or asks "what font is this site using" or similar font extraction requests.

Trustedconfidence: 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.

geepers-orchestrate

lukeslp · vsource-scanned

Run multi-agent Dream Cascade (hierarchical 3-tier synthesis) or Dream Swarm (parallel multi-domain search) workflows via the dr.eamer.dev orchestration API. Use when a task benefits from multiple specialized agents working in parallel or hierarchically.

Trustedconfidence: 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.

geo-optimization

capt-marbles · vsource-scanned

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.

Trustedconfidence: source evidencesource-scanned

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

gmail-cleaner

cedarscy · vsource-scanned

Clean and organize Gmail accounts in bulk. Use when asked to clean Gmail, remove spam, trash newsletters/promotional emails, bulk-delete emails by sender, create labels, set up auto-filters, or restore emails from trash. Handles single or multiple Gmail accounts via OAuth token files. Works with any Gmail account using the Gmail API.

Use Cautionconfidence: source evidencesource-scanned

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

handsfree-windows-control

lijinlar · vsource-scanned

Guide skill for controlling native Windows apps (UIA) and web browsers (Playwright) via the handsfree-windows CLI. Use when you need to automate or test desktop applications or websites on a Windows machine: launching apps from Start menu, discovering UI controls without guessing, clicking/typing in native apps, opening/snapshotting/clicking in browsers, recording and replaying YAML macros that mix desktop and web steps. REQUIRES handsfree-windows CLI (auto-installed on first use via setup.py).

Trustedconfidence: 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.

jina-ai

adhishthite · vsource-scanned

Web reading and searching via Jina AI APIs. Fetch clean markdown from URLs (r.jina.ai), web search (s.jina.ai), or deep multi-step research (DeepSearch).

Trustedconfidence: 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.

kasia

renkasiyas · vsource-scanned

Send and receive encrypted on-chain messages on the Kaspa blockchain using the Kasia protocol. Use when a user asks to message someone on Kaspa/Kasia, check Kasia conversations, read encrypted messages, send payments with messages, or manage Kasia handshakes. Requires kasia-mcp and kaspa-mcp servers configured in mcporter.

Trustedconfidence: 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.

lark-report-collector

pengxiao-wang · vsource-scanned

Collect weekly reports from Lark Reports (oa.larksuite.com), summarize into Lark Docs, and notify. Use when: (1) collecting weekly reports from specific teams/templates, (2) checking who hasn't submitted reports, (3) generating report summaries as Lark documents. Requires browser automation (Reports is a SPA, API not available on international Lark).

Trustedconfidence: 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.

moodle-ws-skill

exeandino · vsource-scanned

>

Trustedconfidence: 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.

nvidia-kimi-vision

miladnoo · vsource-scanned

Analyze images using NVIDIA Kimi K2.5 vision model via NVIDIA NIM API. Perfect for adding vision to non-vision models like MiniMax M2.5, GLM-5, or any model without native image support. Supports png, jpg, jpeg, webp.

Trustedconfidence: 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.

oee-knowledge-base

odinbot33 · vsource-scanned

> by Odin's Eye Enterprises — Ancient Wisdom. Modern Intelligence.

Trustedconfidence: 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.

pencil-to-code

jcwen · vsource-scanned

|

Trustedconfidence: 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.

phylactery

seanweiyi · vsource-scanned

A digital soul-backup and recovery system. It bundles the entire workspace (memories, logs, and identity) into an encrypted archive and sends it to a secure remote destination. Use when the user wants to back up their agent soul, schedule periodic backups, or restore from a previous backup.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

« First ← Prev 1 14 15 16 39Page 15 / 39Next →Last »