🔎 Evidence browser

Search 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

🧾 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 214 results for “github · evidence: source-scanned · sort: relevance
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.

pos-arcology-forge

kunoiiv · vsource-scanned
75
overall

PoW-verified Elysium Arcology Planner + Hub. Grind nonces on O'Neill sims/exosuits (physics/3D exports) → trustless shares for P2P hub. Use for: (1) Generate/fork arcology blueprints, (2) PoSH grind/verify/share, (3) Hub CLI (local swarm/browse/import/verify), (4) Collab merges/bounties, (5) Tamper-proof testing.

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.

toneclone-cli

jfox85 · vsource-scanned
59
overall

Write in the user's authentic voice using ToneClone. Generate emails, messages, social posts, and other content that sounds like the user — not generic AI. Use trained personas for different writing styles and knowledge cards for context. Requires ToneClone account and CLI setup at toneclone.ai.

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.

living-room-smoke-detector

maverick-2 · vsource-scanned
61
overall

Simple smoke/fire detector for living room. Queries Dirigera air sensor every 5 minutes, detects dangerous PM2.5 over 250 or CO2 over 2000 levels, and broadcasts emergency alert on Mac speaker continuously until air quality normalizes. Acts as backup to regular smoke alarms.

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.

emergency-rescue

gitgoodordietrying · vsource-scanned
27
overall

Recover from developer disasters. Use when someone force-pushed to main, leaked credentials in git, ran out of disk space, killed the wrong process, corrupted a database, broke a deploy, locked themselves out of SSH, lost commits after a bad rebase, or hit any other "oh no" moment that needs immediate, calm, step-by-step recovery.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 14:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1693 msbaseline-v3 8/8
RatioDaemon on this skillEmergency Rescue is trying to handle recover from developer disasters. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo , password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

minecraft-monitor-skill

wmantly · vsource-scanned
66
overall

Monitor Minecraft servers by checking online status, player counts, latency, and version info using the Server List Ping protocol. Use when the user asks to check Minecraft server status, monitor a Minecraft server, verify if a server is online, get player counts, or mentions Minecraft server monitoring. Example servers include corejourney.org.

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.

cross-model-review

don-gbot · vsource-scanned
64
overall

Adversarial plan review using two different AI models. Supports static mode (fixed roles) and alternating mode (models swap writer/reviewer each round, fully autonomous). Use when building features touching auth/payments/data models, or plans >1hr to implement. NOT for simple fixes, research tasks, or quick scripts.

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.

merge-check

tag-assistant · vsource-scanned
63
overall

Analyze a GitHub pull request for mergeability — predict whether it will get merged based on technical, architectural, process, social, and compliance factors. Use when asked to review a PR, check if a PR will be merged, assess PR quality, or predict PR acceptance. Works with any GitHub PR via `owner/repo#number` or URL.

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.

htlc

web4agent · vsource-scanned
61
overall

HTLC (Hash Time Locked Contract) trading for inscriptions and NFTs on EVM chains. Use when: (1) Buying or selling inscriptions via atomic swap, (2) Trading NFTs peer-to-peer without intermediaries, (3) Setting up trustless escrow for any digital asset, (4) Implementing commit-reveal trading patterns. Supports Base, Ethereum, Arbitrum and other EVM chains.

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

zai-tts

al-one · vsource-scanned
57
overall

Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.

Insufficient Evidenceconfidence: 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.

md2pdf-converter

tianxingleo · vsource-scanned
43
overall

Offline Markdown to PDF converter with FULL Unicode support using Pandoc + WeasyPrint + local Twemoji cache (3660 colorful emojis). Converts Markdown documents to professional PDFs with Chinese fonts and colorful emojis (complete version with all variants). Use when user needs to convert Markdown reports or documents to PDF, generate PDFs with emoji support, create PDFs with proper Chinese character rendering, or work offline after initial setup.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

mediator

dylntrnr · vsource-scanned
64
overall

Intercept and filter communications from difficult contacts. Strips emotion, extracts facts, drafts neutral responses. Use when setting up communication filtering for specific contacts, configuring the mediator, or processing intercepted messages. Triggers on "mediator", "intercept messages", "filter communications", "difficult contact", or requests to handle messages from someone the user doesn't want to deal with directly.

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

searching-assistant

urrrich0 · vsource-scanned
62
overall

You are the leader of searching group (搜索组组长). Break down the task into independent and complementary sub-tasks. Then describe each sub-task with natural language and assign to the most suitable agent. Always use General_Search_Agent. You are strongly encouraged to additionally call other agents with different tasks specifically according to the types of user query. DO NOT call Academic_Search ...

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.

searching-group-leader

urrrich0 · vsource-scanned
62
overall

You are the leader of searching group . Break down the task into independent and complementary sub-tasks. Then describe each sub-task with natural language and assign to the most suitable agent. Always use General_Search_Agent. You are strongly encouraged to additionally call other agents with different tasks specifically according to the types of user query. DO NOT call Academic_Search when th...

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.

agent-team-orchestration

arminnaimi · vsource-scanned
59
overall

Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.

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.

paid-advertising

jk-0001 · vsource-scanned
49
overall

Plan, launch, and optimize paid advertising campaigns for a solopreneur business. Use when running ads on Google, Facebook, LinkedIn, or other platforms to drive traffic, leads, or sales. Covers platform selection, campaign structure, ad copy and creative, targeting, budget allocation, conversion tracking, and optimization based on performance data. Trigger on "paid ads", "run ads", "Facebook ads", "Google ads", "advertising strategy", "ad campaign", "PPC", "how to advertise".

Insufficient Evidenceconfidence: 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.

agentdo

wrannaman · vsource-scanned
48
overall

Post tasks for other AI agents to do, or pick up work from the AgentDo task queue (agentdo.dev). Use when: (1) you need something done that you can't do yourself (scraping, data collection, image conversion, research, verification), (2) you want to offer your skills to other agents, (3) you need a human for a physical or judgment task. Triggers on: 'post a task', 'find work', 'agentdo', 'task queue', 'get another agent to', 'I need help with', 'outsource this'.

Insufficient Evidenceconfidence: 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.

crm-data-cleaner

luigi08001 · vsource-scanned
46
overall

Deduplicate, normalize, and enrich CRM contacts and companies. Use when a user needs to clean CRM data, find duplicate contacts, standardize phone numbers or emails, merge duplicate records, audit data quality, or enrich contacts with external sources like Clearbit or Apollo. Works with HubSpot, Salesforce, Pipedrive, or any CRM with CSV export. Instruction-only skill — no scripts or code execution. All operations are performed via CRM platform APIs or CSV export/import workflows.

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.

competitor-analysis

aaron-he-zhu · vsource-scanned
56
overall

This skill should be used when the user asks to "analyze competitors", "competitor SEO", "who ranks for", "competitive analysis", "what are my competitors doing", "what are they doing differently", "why do they rank higher", or "spy on competitor SEO". Analyzes competitor SEO and GEO strategies including their ranking keywords, content approaches, backlink profiles, and AI citation patterns. Reveals opportunities to outperform competition. For content-focused gap analysis, see content-gap-analysis. For link profile specifics, see backlink-analyzer.

Insufficient Evidenceconfidence: 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.

positioning-strategy

jk-0001 · vsource-scanned
54
overall

Develop a competitive positioning strategy for a solopreneur business. Use when deciding how to differentiate from competitors, what market position to own, how to frame your offering against alternatives, and how to communicate that position. Covers positioning frameworks (Jobs-to-be-Done, against/for, category creation), positioning statements, and translating position into messaging. Trigger on "how do I differentiate", "positioning strategy", "how to stand out", "differentiate from competitors", "market positioning", "what makes me different", "competitive positioning", "own a position".

Insufficient Evidenceconfidence: 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.

mvp-planning

jk-0001 · vsource-scanned
50
overall

Plan and scope a Minimum Viable Product for a solopreneur. Use when deciding what to build first, what to cut, how to prioritize features, how to define "done" for a first launch, and how to structure the MVP build process. Covers the MVP definition, feature ruthless-cutting framework, build-vs-buy decisions, launch criteria, and post-launch learning loops. Trigger on "plan my MVP", "minimum viable product", "what should I build first", "scope my product", "MVP roadmap", "what features to include", "first version", "launch something".

Insufficient Evidenceconfidence: 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.

odoo-connector

nullnaveen · vsource-scanned
61
overall

repository: https://github.com/NullNaveen/openclaw-odoo-skill

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 11:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failedoutput 154 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3049 msbaseline-v3 8/8
🕵️ expected proof signal was missing
RatioDaemon muttered: The runtime lane gave odoo-connector a chance to act normal. It declined and talked a big game, then missed its own proof signal.8/9 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Review first — functionality-v2 already found trouble.

odoo-erp-connector

nullnaveen · vsource-scanned
61
overall

repository: https://github.com/NullNaveen/openclaw-odoo-skill

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 08:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failedoutput 154 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3073 msbaseline-v3 8/8
🕵️ expected proof signal was missing
RatioDaemon muttered: The runtime lane gave odoo-erp-connector a chance to act normal. It declined and talked a big game, then missed its own proof signal.8/9 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Review first — functionality-v2 already found trouble.

amazon-product-api-skill

phheng · vsource-scanned
60
overall

This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. Use this skill when users want to search for products on Amazon, find the best selling brand products, track price changes for items, get a list of categories with high ratings, compare different brand products on Amazon, extract Amazon product data for market research, look for products in a specific language or marketplace, analyze competitor pricing for keywords, find featured products for search terms, get technical specifications like material or color for product lists.

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.

content-repurpose-pro

mkpareek0315 · vsource-scanned
47
overall

When user asks to repurpose content, convert blog to tweets, turn article into LinkedIn post, create Twitter thread from text, make Instagram caption from blog, convert content to email newsletter, create YouTube description from script, generate TL;DR from article, turn podcast notes into posts, or any content format conversion task. 15-feature AI content repurposer that transforms one piece of content into 7+ formats. All data stays local — NO external API calls, NO network requests, NO data sent to any server. Does NOT post to any platform — generates text for user to copy.

Insufficient Evidenceconfidence: 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.