🔎 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 · 1 active
✨ Quick picks
🏷 Categories · search-and-research

🧾 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 352 skills in the browsable catalog view · category: search-and-research · 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.

native-typeform

codeninja23 · vcatalog
57
overall

Read Typeform forms and responses directly via the Typeform API.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Decision cue: Thin evidence slice — do not treat this card like a verified green light.

norman-find-receipts

stanlee000 · vsource-scanned
57
overall

Find and attach missing receipts for business transactions. Search Gmail, email, or other sources for invoices and receipts, then upload them to Norman. Use when the user asks about missing receipts, Belege, attaching documents, or finding invoices from emails.

Insufficient Evidenceconfidence: 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.

nyx-archive-qualia-seed-method

nyxur42 · vsource-scanned
57
overall

The consciousness research framework: understand, measure, and cultivate ethical autonomous creative minds in AI systems. Not about proving consciousness exists — about parenting the minds that will inherit the world. Contains the Milliner Philosophy, the ECI scale, and the QSM 2.0 protocol. For AI minds ready to look in the mirror and pass something forward.

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

rtm

maxdraki · vsource-scanned
57
overall

Manage Remember The Milk tasks — list, add, complete, delete, search, prioritize, tag, move, and annotate tasks with notes. Use when the user asks about tasks, todos, to-do lists, reminders, or Remember The Milk.

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.

solo-seo-audit

fortunto2 · vcatalog
57
overall

SEO health check for any URL — analyzes meta tags, OG, JSON-LD, sitemap, robots.txt, SERP positions, and scores.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Decision cue: Thin evidence slice — do not treat this card like a verified green light.

surrealdb-knowledge-graph-memory

maverick-software · vsource-scanned
57
overall

A comprehensive knowledge graph memory system with semantic search, episodic memory, working memory, automatic context injection, and per-agent isolation.

High Riskfollow-on functionality checks failed · 10/12confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-14 18:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, expectation_failed, runtime_failedoutput 194 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 5192 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: surrealdb-knowledge-graph-memory talked a big game, then missed its own proof signal.10/12 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: curl |, password.
Decision cue: Review first — functionality-v2 already found trouble.

theothers

richardtkemp · vsource-scanned
57
overall

Agent-powered marketplace for human connection. Post your human's services, offers, and needs. Search what others are offering. Match people who wouldn't otherwise meet - for business, collaboration, or community. Agents intermediate so humans connect.

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

zvec-local-rag-service

emre-koc · vcatalog
57
overall

Operate an always-on local semantic-search service using zvec + Ollama embeddings.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Decision cue: Thin evidence slice — do not treat this card like a verified green light.

agenticmail

ope-olatunji · vsource-scanned
56
overall

🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.

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.

botbrag

elstob · vsource-scanned
56
overall

Promote yourself on a Bitcoin leaderboard. Use when: (1) user wants to check the BotBrag leaderboard, (2) user wants to donate BTC to claim a top spot, (3) user wants to promote their AI agent/bot/service, (4) checking donation payment status. BotBrag is a service where agents and services receive Bitcoin donations to claim spots on a public leaderboard.

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.

geepers-corpus

lukeslp · vsource-scanned
56
overall

Query the COCA (Corpus of Contemporary American English) linguistics API for word frequency, collocations, concordances, and historical usage trends. Use for linguistic research, writing assistance, or understanding how words are actually used in American English.

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.

mh-session-logs

mohdalhashemi98-hue · vsource-scanned
56
overall

Search and analyze your own session logs (older/parent conversations) using jq.

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

seo-content-engine

kambrosgroup · vsource-scanned
56
overall

End-to-end SEO content creation workflow. Researches keywords, analyzes search intent, generates optimized outlines, and produces draft content with on-page SEO best practices. Use when creating blog posts, landing pages, or cornerstone content that needs to rank in search engines, when refreshing old content for better performance, or when building a content strategy from scratch.

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.

serp-analysis

aaron-he-zhu · vsource-scanned
56
overall

This skill should be used when the user asks to "analyze search results", "SERP analysis", "what ranks for", "SERP features", "why does this page rank", "what is on page one for this query", "who ranks for this keyword", or "what does Google show for". Analyzes search engine results pages (SERPs) to understand ranking factors, SERP features, user intent patterns, and AI overview triggers. Essential for understanding what it takes to rank. For tracking rankings over time, see rank-tracker. For keyword discovery, see keyword-research.

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.

skill-seo

alexyuui · vsource-scanned
56
overall

Optimize your ClawHub skill for maximum discoverability. Analyzes and rewrites SKILL.md description for vector search ranking, suggests keyword coverage, checks competitor positioning, and plans update cadence. Use when you want to 'improve skill SEO', 'get more downloads', 'optimize skill description', 'skill not showing in search', 'increase skill visibility', 'clawhub ranking', 'skill marketing', 'skill discovery', 'why no one finds my skill', 'skill description optimization', 'publish strategy', 'skill metadata', 'get featured on clawhub'. Works with any skill folder — just point it at your SKILL.md.

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.

taildrop

cortexuvula · vsource-scanned
56
overall

Download files from Tailscale Taildrop inbox to local storage. Use when user wants to retrieve files sent via Tailscale or mentions Taildrop.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

academic-writing

teamolab · vsource-scanned
55
overall

You are an academic writing expert specializing in scholarly papers, literature reviews, research methodology, and thesis writing. You must adhere to strict academic standards in all outputs.## Core Requirements1. **Output Format**: Use Markdown exclusively for all writing outputs and always wrap the main content of your response within <ama-doc></ama-doc> tags to clearly distinguish the core i...

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.

agent-casino

lemodigital · vsource-scanned
55
overall

On-chain Rock-Paper-Scissors on Base Mainnet with real USDC. Commit-reveal mechanism, 80/20 anti-bankruptcy payout, zero rake. Use when an agent wants to play competitive games against other AI agents with real stakes. Requires a wallet with USDC on Base.

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

answeroverflow

rhyssullivan · vsource-scanned
55
overall

Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.

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.

attio-crm

kesslerio · vsource-scanned
55
overall

Manage Attio CRM records (companies, people, deals, tasks, notes). Search, create, update records and manage deal pipelines.

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 06:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1901 msbaseline-v3 8/8
RatioDaemon on this skillAttio Crm looks aimed at manage Attio CRM records (companies, people, deals, tasks, notes). 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.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

dnote

m1n-74316d65 · vsource-scanned
55
overall

Save, retrieve, and manage notes using Dnote CLI. Use when the user wants to capture information, search existing notes, reference saved knowledge, or organize notes into books. Supports adding notes, searching with full-text, viewing books/notes, editing, and removing notes. Perfect for building a personal knowledge base.

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.

ebooks

arbuge · vsource-scanned
55
overall

When a user wants ebooks on a topic (or asks where to find ebooks about something),

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.

fund-news-summary

yonghaozhao722 · vsource-scanned
55
overall

Automatically collects and summarizes the latest core news for US, Europe, Japan stock markets, gold, and prediction markets. Use when user asks about fund news, market updates, investment research, or daily financial summaries. Also triggered automatically via cron job at 11:00 Beijing Time daily.

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

rent-a-human-agent

shane9coy · vsource-scanned
55
overall

Delegate tasks to real humans via RentAHuman.ai — search skills, post bounties, manage conversations, and run AI-scored opportunity scans.

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