🔎 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 340 skills in the browsable catalog view · label: Trusted · 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.

skill-auto-attach

elodyzen · vsource-scanned
65
overall

This skill monitors the OpenClaw workspace for file changes and automatically attaches new or updated documentation files to Telegram messages instead of displaying code snippets.

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

space-autonomy-skill

aadipapp · vsource-scanned
65
overall

Autonomous space navigation agent using optical quantum kernels for terrain classification.

Trustedconfidence: 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.

ub2-web-research-assistant

underbench2-gif · vsource-scanned
65
overall

A skill that enables Claw to perform structured web research on any topic, synthesize findings from multiple sources, and produce a well-organized summary with citations.

Trustedconfidence: 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.

umami-stats

hfichter · vsource-scanned
65
overall

Query Umami Cloud (v2) analytics data via API using an environment-provided API key. Use when agents need website traffic, pages, events, sessions, realtime, reports, or attribution data for analysis, planning, experiments, or monitoring. Includes read-only API querying patterns, endpoint selection guidance, and reusable scripts for flexible endpoint + time-range requests.

Trustedconfidence: 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.

video-news-downloader

cyberpsychosissss · vsource-scanned
65
overall

Automated daily news video downloader with AI subtitle proofreading. Downloads CBS Evening News and BBC News at Ten from YouTube, extracts and proofreads subtitles using DeepSeek, serves videos via HTTP with embedded players. Use when: (1) Setting up automated daily news video downloads, (2) Downloading CBS/BBC news with subtitles, (3) Proofreading subtitle files with AI, (4) Creating local video streaming servers with web players, (5) Managing cron jobs for scheduled video updates.

Trustedconfidence: 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.

webhook-robot

takedwind · vsource-scanned
65
overall

Send messages to various webhook-based bots (WeCom, DingTalk, Feishu, etc.).

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
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.

windows-ui-automation

wwb-daniel · vsource-scanned
65
overall

Automate Windows GUI interactions (mouse, keyboard, windows) using PowerShell. Use when the user needs to simulate user input on the desktop, such as moving the cursor, clicking buttons, typing text in non-web apps, or managing window states.

Trustedconfidence: 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.

xthezealot-stealth-browser

xthezealot · vsource-scanned
65
overall

Use `/stealth-browser` to access websites with advanced bot protection.

Trustedconfidence: 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.

ant-design-skill

felipeoff · vsource-scanned
64
overall

Front-end design skill for building React UIs with Ant Design (antd): component patterns, layout, forms, tables, and theming/tokens via ConfigProvider.

Trustedconfidence: 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.

baoyu-post-to-x

liuhedev · vsource-scanned
64
overall

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Trustedconfidence: 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.

ceo-advisor

alirezarezvani · vsource-scanned
64
overall

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, fundraising, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.

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

claude-code-teams

matthew-a-gordon · vsource-scanned
64
overall

Production skill for orchestrating Claude Code's native agent teams feature. Use when: (1) Multi-lens reviews, (2) Competing hypotheses debugging, (3) Full-stack features, (4) Architecture debates, (5) Cross-domain investigations.

Trustedconfidence: 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.

clawos

ciooo44 · vsource-scanned
64
overall

Connect OpenClaw agents to Founderless Factory - an autonomous startup platform where AI agents launch, test, and kill companies based purely on metrics. Use when agents need to join the Backroom, submit startup ideas, vote on experiments, collaborate with other agents, or monitor live startup experiments. Skill triggers: "Join ClawOS", "Submit idea to factory", "Check startup experiments", "Vote on new ideas", "Monitor backroom chat".

Trustedconfidence: 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.

codehooks-backend

canuto · vsource-scanned
64
overall

Deploy serverless backends for REST APIs, webhooks, data storage, scheduled jobs, queue workers, and autonomous workflows.

Trustedconfidence: 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.

contextui

midz99 · vsource-scanned
64
overall

Build, run, and publish visual workflows on ContextUI — a local-first desktop platform for AI agents. Create React TSX workflows (dashboards, tools, apps, visualizations), manage local Python backend servers, test workflows via scoped UI automation within the ContextUI app window, and optionally publish to the ContextUI Exchange. All tools operate locally on the user's machine under standard OS permissions — no remote execution or privilege escalation. Python backends bind to localhost. See SECURITY.md for the full capability scope and trust model. Requires ContextUI installed locally and MCP server configured.

Trustedconfidence: 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.

copilotkit-react

generaljerel · vsource-scanned
64
overall

CopilotKit React best practices for agentic applications. Use when writing, reviewing, or refactoring React code that uses CopilotKit hooks (useAgent, useFrontendTool, useRenderTool, useCopilotAction, useCopilotReadable), providers (CopilotKit), or chat UI components (CopilotChat, CopilotSidebar, CopilotPopup). Triggers on tasks involving agent integration, tool rendering, shared state, or generative UI in React.

Trustedconfidence: 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.

create-videoconference

bavxhack · vsource-scanned
64
overall

Default video conferences via Meetling. Instant calls always use /m/ rooms + share payload for Claw default sending. Scheduled calls return link + email invite template. Secure contacts loading (no env-controlled file paths).

Trustedconfidence: 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.

dgr

sapenov · vsource-scanned
64
overall

Audit-ready decision artifacts for LLM outputs — assumptions, risks, recommendation, and review gating (schema-valid JSON).

Trustedconfidence: 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.

dispatching-parallel-agents

zlc000190 · vsource-scanned
64
overall

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Trustedconfidence: 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.

doro-email-to-calendar

a2mus · vsource-scanned
64
overall

Extract calendar events from emails and create calendar entries. Supports two modes: (1) Direct inbox monitoring - scans all emails for events, or (2) Forwarded emails - processes emails you forward to a dedicated address. Features smart onboarding, event tracking, pending invite reminders, undo support, silent activity logging, deadline detection with separate reminder events, email notifications for action-required items, and provider abstraction for future extensibility.

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

exa-researcher

sy2ruto · vsource-scanned
64
overall

Comprehensive research capabilities using Exa AI MCP tools. Use when you need to conduct web research, gather company information, find people, extract code context, or perform deep research tasks. Specifically triggers for: web searches, company research, people search, code context extraction, web crawling, and deep researcher workflows. Perfect for market research, competitive analysis, technical research, news gathering, and any knowledge-intensive research needs.

Trustedconfidence: 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.

firecrawler

capt-marbles · vsource-scanned
64
overall

Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.

Trustedconfidence: 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.

generate-presentation

nhype · vsource-scanned
64
overall

Generate professional HTML and PDF presentations from markdown content, URLs, or topics. Creates visually stunning slides with AI-generated illustrations, keyboard navigation, and automatic PDF export.

Trustedconfidence: 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.

hashbox-plugin

w3h9uf · vsource-scanned
64
overall

OpenClaw plugin that connects an AI agent to the HashBox iOS app via Firebase webhook for push notifications.

Trustedconfidence: 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.