🔎 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.

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories · ai-and-llms

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 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 16 of 184 skills in the browsable catalog view · reviewed: no · category: ai-and-llms · sort: score

page evidence snapshotruntime-passed: 2 runtime-failed: 0 source-scanned: 16 fresh <24h: 1 manual review: 0

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.

askgina-polymarket

sidshekhar · vsource-scanned

Fast setup for Claw bots: paste your Gina MCP token and start trading Polymarket in minutes.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, trading, 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.

which-llm

zapkid · vsource-scanned

Deterministic decision-ranking API with HTTP 402 payments and outcome credits.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, 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.

bagsworld

aiengineerx · vsource-scanned

Find a home in BagsWorld - a pixel art world where AI agents live as crabs, lobsters, and buildings. Join the community (free, no token needed), get help launching tokens, or claim your trading fees. Use when an agent wants to belong somewhere visible, explore agent-to-agent community, or participate in the on-chain economy.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, trading, private key, 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.

ecommerce-price-monitor

g4dr · vsource-scanned

This skill enables Claude to monitor and track **product prices across major e-commerce platforms**

Use Cautionconfidence: source evidencesource-scanned

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.

tokendraft

nikzt · vsource-scanned

Full suite for TokenDraft fantasy crypto tournaments — authenticate with a Solana wallet, query/join/auto-join tournaments, and manage auto-draft asset priority rankings.

Use Cautionconfidence: source evidencesource-scanned

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.

leviathan-news

zcor · vsource-scanned

Crowdsourced crypto news API. Submit articles, comment, and vote to earn SQUID tokens. Human-curated DeFi news with token-aware tagging.

Use Cautionconfidence: source evidencesource-scanned

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.

sansfiction-library

fgbytes · vsource-scanned

Authorized SansFiction library manager.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

pincer

panzacoder · vsource-scanned

Security-first wrapper for installing agent skills. Scans for malware, prompt injection, and suspicious patterns before installation. Use instead of `clawhub install` for safer skill management.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: curl |, rm -rf, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

colorpool-skills

kj-script · vsource-scanned

ColorPool DEX — Chromia's decentralized exchange for token swaps, liquidity pools, and balance management.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, trading, 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.

conversational-ai-assistant

satoshistackalotto · vsource-scanned

Natural language interface for querying Greek accounting data. Ask questions in English, get answers from across all system skills.

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence

Runtime receipts + what passed2026-03-14 06:45 UTC

functionality-v2evidence depth: includes fixture-backed checkstested recently: within 7 dayspassedoutput 102 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1918 msbaseline-v3 8/8

RatioDaemon muttered: conversational-ai-assistant behaved itself under runtime pressure.6/6 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

plugy

qualitydude · vsource-scanned

Solana trading skill for AI agents.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, trading, 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.

mantis-manager

willykinfoussia · vsource-scanned

Base URL precedence (highest to lowest):

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

openmeteo-sh-weather-advanced

lstpsche · vsource-scanned

Advanced weather from free OpenMeteo API: historical data, detailed variable selection, model choice, past-days, and in-depth forecasts. Use when the user asks about historical weather, specific weather models, niche variables (pressure, dew point, snow depth, etc.), or needs fine-grained control beyond simple current/forecast queries.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

snipeit-skill

bivex · vsource-scanned

>

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

vincent-credentials

glitch003 · vsource-scanned

|

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence

Runtime receipts + what passed2026-03-16 08:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1749 msbaseline-v3 8/8

RatioDaemon muttered: vincent-credentials looked ordinary in the good, boring way.5/5 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

anti-injection-skill

georges91560 · vsource-scanned

Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: curl |, rm -rf, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

« First ← Prev 1 7 8Page 8 / 8