🔎 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.

social-media-agent

psmamm · vsource-scanned
63
overall

Autonomous social media management for X/Twitter using only OpenClaw native tools. Use when a user wants to automate X posting, generate content, track engagement, or build an audience. Triggers on requests about tweets, social media strategy, X engagement, content calendars, or growing a following. No API keys required — uses browser automation and web_fetch.

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.

telegram-rich-messages

shingo0620 · vsource-scanned
63
overall

Comprehensive guide for Telegram Rich UI features (Inline buttons, formatting, media, reactions, and message management). Use this skill to provide a low-friction, interactive experience for Telegram users, prioritizing buttons over typing.

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.

web-monitor

rogue-agent1 · vsource-scanned
63
overall

Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, monitor for new posts/content, set up page change alerts, or check if a site has been updated. Supports CSS selectors for targeted monitoring.

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.

web-research-assistant

phheng · vsource-scanned
63
overall

AI-powered web research assistant that leverages BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.

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.

website-monitor

claudiodrusus · vsource-scanned
63
overall

Lightweight website uptime monitor. Check if URLs are up, measure response times, detect content changes via hashing, and verify expected content. Zero 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.

anti-slop-design

kjaylee · vsource-scanned
62
overall

Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. Use when building web components, game UIs, landing pages, dashboards, or any visual web interface. Prevents purple-gradient-rounded-corner-Inter-font syndrome.

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.

brave-api-setup

garibong-labs · vsource-scanned
62
overall

Set up Brave Search API for OpenClaw web_search. Use when user needs to configure Brave API, get Brave API key, enable web search, or fix "missing_brave_api_key" error.

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.

bria-ai

galbria · vsource-scanned
62
overall

Generate, edit, and transform images with commercially-safe AI models. Create images from text, edit by natural language instruction, remove backgrounds (transparent PNG), replace backgrounds, add/replace/remove objects, inpaint, outpaint, upscale (2x/4x), enhance quality, restyle (oil painting, anime, 3D), relight, reseason, restore old photos, colorize, sketch to photo, and product lifestyle shots. Use for websites, apps, presentations needing hero images, banners, product photos, product placement in scenes, icons, illustrations, or backgrounds. Also for e-commerce photography, batch generation, and pipelines. Triggers are image generation, generate/create image, edit photo, remove background, transparent PNG, replace background, product shot, lifestyle scenes, upscale, style transfer, photo restoration, colorize, sketch to image, outpaint, inpaint, cut out subject, integrate products into scene.

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.

cacheforge

tkuehnl · vsource-scanned
62
overall

CacheForge primary skill — bootstrap onboarding + ops + stats for the OpenAI-compatible token optimization gateway. Cut your LLM bill by up to 30% (results vary by provider/workload).

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.

camofox-mcp

redf0x1 · vsource-scanned
62
overall

Anti-detection browser automation MCP skill for OpenClaw agents with 41 tools for navigation, interaction, extraction, downloads, profiles, sessions, and stealth web search.

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.

create-agent-with-telegram-group

sheetaa · vsource-scanned
62
overall

Create a new OpenClaw agent and bind it to a dedicated Telegram group with workspace ~/claw-<agent-name>. Use when the user asks for one-agent-one-group setup, Telegram group binding, or repeatable agent provisioning. Always ask which model to use, ask for essential initialization choices (USER.md/IDENTITY.md/SOUL.md), and set group reply mode to no-mention-required. Explicit user confirmation is required before any high-privilege actions: modifying openclaw.json, triggering browser automation, or restarting the gateway.

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.

disk-usage-watcher

nidalghetf · vsource-scanned
62
overall

Monitors disk space and inode usage on specified paths, sending alerts when thresholds are exceeded. Essential for preventing disk-full incidents.

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.

doubao-image-gen

honestqiao · vsource-scanned
62
overall

Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information.

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.

ethereum-wingman

jp4g · vsource-scanned
62
overall

Ethereum development tutor and builder for Scaffold-ETH 2 projects. Triggers on "build", "create", "dApp", "smart contract", "Solidity", "DeFi", "Ethereum", "web3", or any blockchain development task. ALWAYS uses fork mode to test against real protocol state.

Trustedconfidence: 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.

fleet-doctrine

jarvis-drakon · vsource-scanned
62
overall

Model routing strategy for multi-model AI fleet. Use when spawning sub-agents, choosing models for cron jobs, delegating coding tasks, or deciding which model should handle a task. Covers Opus, Codex, Sonnet, Gemini, and Grok routing rules.

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.

gmail-agent

r39132 · vsource-scanned
62
overall

Summarize unread Gmail, show folder structure, audit/clean labels, and purge spam/trash

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.

holocube-emotes

thrive-spencerj · vsource-scanned
62
overall

Control a GeekMagic holocube display as an AI emote system. Generate holographic sprite kits with Gemini, upload to device, and swap expressions based on agent state (idle, working, error, etc.). Use when the user has a GeekMagic holocube (HelloCubic-Lite or similar) and wants their AI assistant to have a physical face that reacts to conversation context.

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.

interview-analysis

mikonos · vsource-scanned
62
overall

Deep interview analysis using dynamic expert routing. Automatically selects top domain thinkers based on role type to distinguish genuine capability from performance, identifying Battle Scars over Methodology Recitation. Applicable to any professional position including product management, engineering, design, operations, sales, and data science.

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.

kj-web-design-guidelines

kjaylee · vsource-scanned
62
overall

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

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.

markdown-to-html

claudiodrusus · vsource-scanned
62
overall

Convert Markdown text to beautifully styled, self-contained HTML with embedded CSS. Perfect for newsletters, documentation, reports, and email templates.

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.

medical-research-toolkit

pascalwhoop · vsource-scanned
62
overall

Query 14+ biomedical databases for drug repurposing, target discovery, clinical trials, and literature research. Access ChEMBL, PubMed, ClinicalTrials.gov, OpenTargets, OpenFDA, OMIM, Reactome, KEGG, UniProt, and more through a unified MCP endpoint. Use when researching disease targets, finding approved/investigational drugs, searching clinical evidence, discovering genetic associations, or analyzing compound bioactivity data.

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.

minimax-tts-v2

honestqiao · vsource-scanned
62
overall

Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information.

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.

minimax-video

honestqiao · vsource-scanned
62
overall

Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information.

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.

pls-url-to-markdown

mattvalenta · vsource-scanned
62
overall

Fetch URLs and convert web pages to clean Markdown for AI processing or knowledge bases. Use when: (1) Researching web content, (2) Building knowledge bases, (3) Extracting articles, (4) Converting pages for docs.

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.