🔎 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 · coding-agents-and-ides

🧾 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 1200 skills in the browsable catalog view · reviewed: no · category: coding-agents-and-ides · 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.

session-cost

khaney64 · vsource-scanned
64
overall

Analyze OpenClaw session logs to report token usage, costs, and performance metrics grouped by agent and model. Use when the user asks about API spending, token usage, session costs, or wants a usage summary.

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.

siliconflow-video-gen

lilei0311 · vsource-scanned
64
overall

Generate videos using SiliconFlow API with Wan2.2 model. Supports both Text-to-Video and Image-to-Video.

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.

stock-copilot-pro

buxibuxi · vsource-scanned
64
overall

OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals, technicals, news radar, morning/evening brief, and actionable investment insights.

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

taskflow

sm0ls · vsource-scanned
64
overall

Structured project/task management for OpenClaw agents — markdown-first authoring, SQLite-backed querying, bidirectional sync, CLI, Apple Notes integration.

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

token-optimizer

smartpeopleconnected · vsource-scanned
64
overall

Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 minutes.

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

token-saver

rubenaquispe · vsource-scanned
64
overall

Reduce OpenClaw AI costs with model-aware optimization. Features dynamic compaction presets based on your model's context window, intelligent file compression, and robust model detection with fallback. Supports Claude, GPT-4, Gemini, DeepSeek, and more.

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

tokenbroker

starrftw · vsource-scanned
64
overall

version: 1.01

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

tokenoptimizer

smartpeopleconnected · vsource-scanned
64
overall

Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 minutes.

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

topic-to-article-kit

rotbit · vsource-scanned
64
overall

Turn a chosen AI topic into a public-account writing package: collect evidence from X/Twitter and other sources, extract high-value comments, and produce title options + structured outline written into Obsidian. Use when user asks for topic-based research and article prep.

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.

trail-nav-telegram

jack4world · vsource-scanned
64
overall

Offline-capable hiking route guidance via Telegram location messages (OpenClaw). Use when building/operating an LLM agent workflow that: (1) imports a GPX/KML route, (2) answers 'am I off-route / which way should I go' with low-token fixed outputs, (3) scrapes/publicly discovers route links from 2bulu track_search, and (4) prepares trip risk checklists + gear lists for an overnight hike.

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.

usage-visualizer

vintlin · vsource-scanned
64
overall

Advanced usage statistics and high-fidelity visual reporting for OpenClaw. 100% local processing. Audit-verified privacy (No credentials stored).

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.

verified-agent-identity

obrezhniev · vsource-scanned
64
overall

Billions/Iden3 authentication and identity management tools for agents. Link, proof, sign, and verify.

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.

video-production

omerflo · vsource-scanned
64
overall

Complete A/B video pipeline — storyboard, Veo 3 batch generation, browser preview with feedback loop, and ffmpeg assembly into final videos. Use when creating multi-scene videos, running A/B tests on hooks/CTAs, previewing clips before stitching, or assembling a final cut from approved clips.

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.

viral-video-analysis

shawnshenopeninterx · vsource-scanned
64
overall

Analyze video ad performance and provide actionable feedback to creators. Use when asked to analyze why videos underperform, give creator coaching feedback, compare high vs low ROI content, or identify video structure issues. Combines audio transcripts, visual analysis, and performance metrics. Supports YouTube, TikTok, Instagram Reels, and Twitter.

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.

volcengine-image-generate

warm-wm · vsource-scanned
64
overall

Using volcengine image_generate.py script to generate image, need to provide clear and specific `prompt`.

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.

volcengine-video-generate

warm-wm · vsource-scanned
64
overall

Using volcengine video_generate.py script to generate video, need to provide filename and prompt, optional provide first frame image (URL or local path).

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.

worthclip-youtube-video-scorer

ivanstancich · vsource-scanned
64
overall

AI-powered YouTube video scoring. Scores videos 1-10 based on your learning goals and persona. Use when the user wants to evaluate YouTube videos, check their scored feed, manage tracked channels, or check API usage. Get AI summaries, alignment analysis, and a curated video feed. Keywords: YouTube, video, score, persona, feed, summary, AI, learning, channels. Requires a WorthClip API key from https://worthclip.com/developers.

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.

yc-new-way

jack4world · vsource-scanned
64
overall

Apply Y Combinator’s “New Way to Build a Startup” playbook to ship fast, validate with real distribution, and iterate using data. Use when the user asks to follow “New Way”, design a 7-day startup sprint, pick a narrow wedge, build a lightweight MVP/SEO site/newsletter, set up experiments, or turn a vague idea into a testable plan with metrics, launch checklist, and weekly iteration loop.

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.

yoinkit

seomikewaltman · vsource-scanned
64
overall

Search, analyze, and transcribe content across 13 social platforms — trending topics, video transcripts, post metadata, and multi-platform research workflows.

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.

youtube-hook

markusmikely · vsource-scanned
64
overall

Generate high-performing YouTube video scripts, titles, thumbnails, descriptions, and chapter markers from any topic or content

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.

zyla-api-hub-skill

alebrega · vsource-scanned
64
overall

Zyla API Hub Skill — Turn your OpenClaw AI agent into a real-world operator. Power it with 10,000+ production-ready APIs from Zyla API Hub — instant access to weather, finance, translation, email validation, geolocation, and more.

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

academic-research

rogersuperbuilderalpha · vsource-scanned
63
overall

Search academic papers and conduct literature reviews using OpenAlex API (free, no key needed). Use when the user needs to find scholarly papers by topic/author/DOI, explore citation chains, get structured paper metadata (title, authors, abstract, citations, DOI, open access URL), fetch full text of open access papers, or conduct automated literature reviews with theme identification and synthesis. Triggers on requests involving academic search, paper lookup, citation analysis, literature review, research synthesis, or scholarly reference gathering.

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.

agent-synthesizer

rylena · vsource-scanned
63
overall

Enable and configure Agent Synthesizer for OpenClaw to improve autonomy and execution throughput. Use when a user asks to install, set up, troubleshoot, or optimize Agent Synthesizer using https://github.com/rylena/agent-synth, or when they want their OpenClaw agent to work faster/better via that repository.

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.

arc-compliance-audit

trypto1019 · vsource-scanned
63
overall

Immutable audit trail for autonomous agent operations. Log skill executions, data access, decisions, and budget changes with tamper-evident hashes. Essential for enterprise governance, incident response, and trust verification.

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.