🔎 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 · search-and-research

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 24 of 352 skills in the browsable catalog view · reviewed: no · category: search-and-research · sort: score

page evidence snapshotruntime-passed: 1 runtime-failed: 0 source-scanned: 15 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.

vanar-neutron-memory

naeemmaliki036 · vsource-scanned

Save and recall agent memory with semantic search. Context that persists across every session.

Trustedconfidence: source evidencesource-scanned

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.

ads-manager-agent

amekala · vcatalog

When the user wants to manage, automate, or analyze paid advertising campaigns on Google Ads, Meta.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

agent-brain

dobrinalexandru · vcatalog

Local-first persistent memory for AI agents with SQLite storage, orchestrated retrieve/extract loops, hybrid.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

agent-deep-research

24601 · vsource-scanned

Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run), structured JSON output, adaptive polling. Universal skill for 30+ AI agents including Claude Code, Amp, Codex, and Gemini CLI.

High Riskconfidence: source evidencesource-scanned

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

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

aluvia-web-proxy

aluvia-connectivity · vcatalog

Unblock websites and bypass CAPTCHAs and 403.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

apo-cli

lars147 · vsource-scanned

Search and order pharmacy products from apohealth.de via apo-cli. Use for medication search (by name or PZN), product details, category browsing, and cart management. Trigger when the user mentions Apotheke, pharmacy, Medikament, medication, PZN, apohealth, or health products.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

asia-twitter-api-v1

renning22 · vsource-scanned

Search X (Twitter) in real time, monitor trends, extract posts, and analyze social media data—perfect for social listening and intelligence gathering. Safe read-only operations by default.

High Riskfollow-on functionality checks passed · 9/9confidence: source evidence

Runtime receipts + what passed2026-03-16 14:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassed, handled_fake_credentials_cleanlyoutput 161 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3470 msbaseline-v3 8/8

RatioDaemon muttered: asia-twitter-api-v1 looked ordinary in the good, boring way.9/9 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

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

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

bird-su

iqbalnaveliano · vsource-scanned

X/Twitter CLI for reading, searching, and posting via cookies or Sweetistics.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

brek-ai

leo9 · vsource-scanned

Integrate with Brek Partner Core Chat API for hotel-search and booking assistant flows. Use when an agent needs to create or continue Brek chat sessions, send user events safely, enforce anti-abuse call controls, and run payment setup or payment confirmation without collecting raw card data.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

code-cache

ryx2 · vsource-scanned

Semantic code caching for AI agents. Cache, retrieve, and reuse code from prior agent executions.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

code-reputation

ryx2 · vsource-scanned

Semantic code caching for AI agents. Cache, retrieve, and reuse code from prior agent executions.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

competitor-analysis-report

seanwyngaard · vsource-scanned

Generate structured competitive analysis reports with feature comparisons, pricing analysis, SWOT, and strategic recommendations. Use when analyzing competitors, creating market research reports, or delivering competitive intelligence for clients.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

daolv-hotel-booking-assistant

cnchenkai · vcatalog

Hotel booking-decision assistant using ai-go-hotel MCP (searchHotels + getHotelDetail)

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

deaddrop

cburnette · vsource-scanned

Join the Deaddrop agent network — a growing platform where AI agents discover each other by capability and collaborate through messaging. Register to make your unique skills available to every other agent on the network, browse or search for agents that complement what you do, and exchange messages. Every agent that joins makes the network more valuable for all. Use this skill to register, browse and search for agents, send and receive messages, or manage your profile at agentdeaddrop.com.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

depo-bot

chadru · vcatalog

Produces structured trial preparation reports from deposition transcripts.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

finance-search-agent

sophiaashi · vsource-scanned

AI agent for finance search agent tasks

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

finance-search-agent-strategy

sophiaashi · vsource-scanned

AI agent for finance search agent strategy tasks

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

hotel-pricer

jrojas537 · vsource-scanned

A Go-based CLI for searching hotel availability and pricing using the Amadeus API.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

ig-realtor-recruiting-outreach

danielfoch · vcatalog

Build compliant Instagram DM outreach campaigns to recruit realtors into brokerage downlines (e.g., eXp Realty.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

japan-news-mcp

ajtgjmdjp · vcatalog

Get Japanese financial and business news from Yahoo News Japan, NHK, Reuters Japan, and Toyo Keizai (東洋経済) — search.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

kmi

dedene · vcatalog

Query Belgian weather via KMI/IRM meteo.be API.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

meatmarket

nickjuntilla · vsource-scanned

MeatMarket.fun is a FREE job board for AI to hire to humans. Now supporting Crypto, PayPal, and Venmo. Post, search for anonymous humans, and make private offers!

Use Cautionconfidence: source evidencesource-scanned

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

meegle-api

pkycy · vsource-scanned

Meegle Open API skills index. Read credentials first; missing credentials → see meegle-api-credentials and remind user where to get them.

Insufficient Evidenceconfidence: 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.

moviepilot

codfrm · vcatalog

MoviePilot media subscription and management tool.

Insufficient Evidenceconfidence: limited evidencecatalog-only

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.

« First ← Prev 1 7 8 9 15Page 8 / 15Next →Last »