🔎 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 · devops-and-cloud

🧾 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 392 skills in the browsable catalog view · category: devops-and-cloud · 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.

courtroom

assassin-1234 · vcatalog
57
overall

AI Courtroom for behavioral oversight.

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.

cybercentry-cyber-security-consultant

cybercentry · vcatalog
57
overall

Cybercentry Cyber Security Consultant on ACP - Instant expert-level cyber security advisory powered by @centry_agent.

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.

dagny-nostr-nak

edwardbickerton · vsource-scanned
57
overall

Manage Nostr posting and engagement via the nak CLI. Use for creating notes, replying in threads, tagging npubs, checking replies/mentions, monitoring a relay (default wss://relay.primal.net), and publishing events with correct root/reply tags. Requires access to NOSTR_SECRET_KEY (nsec) for signing/publishing.

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.

elasticsearch-skill

davidgeorgehope · vcatalog
57
overall

Interact with Elasticsearch and Kibana via REST API using curl.

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.

ethereum-history

cartoonitunes · vsource-scanned
57
overall

Read-only factual data about historical Ethereum mainnet contracts. Use when the user asks about a specific contract address, early Ethereum contracts, deployment era, deployer, bytecode, decompiled code, or documented history (what a contract is and is not). Data is non-opinionated and includes runtime bytecode, decompiled code, and editorial history when available. Base URL https://ethereumhistory.com (or set BASE_URL for local/staging).

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.

finviz-crawler

camopel · vsource-scanned
57
overall

Continuous financial news crawler for finviz.com with SQLite storage, article extraction, and query tool. Use when monitoring financial markets, building news digests, or needing a local financial news database. Runs as a background daemon or systemd service.

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

grafana-plugin

darkstards9 · vcatalog
57
overall

Read current values from Grafana dashboards without knowing the underlying queries.

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.

jarvis-monitor

eason-tien · vcatalog
57
overall

JARVIS-style system monitor with sci-fi HUD interface.

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.

json-render-table

sorphwer · vsource-scanned
57
overall

Render compact generic data tables to PNG images with json-render-cli. Use when users ask to visualize arbitrary structured rows/columns (non-ticket-specific) as clean table screenshots with controllable layout.

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.

k8s-memory-tune

2233admin · vcatalog
57
overall

**触发词**: oomkilled, memory_limit, jvm_heap, container_memory, k8s 内存.

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.

lightning-security-module

roasbeef · vsource-scanned
57
overall

Set up an lnd remote signer container that holds private keys separately from the agent. Exports a credentials bundle (accounts JSON, TLS cert, admin macaroon) for watch-only litd nodes. Container-first with Docker, native fallback. Use when firewalling private key material from AI agents.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 20:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 1.4 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2217 msbaseline-v3 8/8
RatioDaemon on this skillLightning Security Module looks aimed at lightning security module. 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, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

lnd

roasbeef · vsource-scanned
57
overall

Install and run Lightning Terminal (litd) which bundles lnd, loop, pool, tapd, and faraday in a single Docker container. Defaults to neutrino backend with SQLite storage on testnet. Supports watch-only mode with remote signer, standalone mode, and regtest development. Use when setting up a Lightning node for payments, channel management, liquidity management (loop), channel marketplace (pool), taproot assets (tapd), or enabling agent L402 commerce.

High Riskfollow-on functionality checks passed · 9/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 17:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 8.0 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2700 msbaseline-v3 8/8
RatioDaemon on this skillLnd looks aimed at lnd. 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, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

masumi

sarthib7 · vsource-scanned
57
overall

Enable AI agents to accept Cardano blockchain payments through the decentralized Masumi network by deploying their own payment service

High Riskfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 04:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime_failedoutput 2.1 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2206 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon on this skillMasumi sits in the masumi lane. Functionality-v2 is currently first observed failure, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Decision cue: Review first — functionality-v2 already found trouble.

microsoft-code-reference

tianqizhang · vsource-scanned
57
overall

context: fork

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.

mini-diary

printxdreams · vsource-scanned
57
overall

AI-powered minimal diary with smart auto-tagging and optional cloud sync. Perfect for daily journaling, work logs, or project tracking.

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.

neo-tf-module-generator

martinforsulu · vsource-scanned
57
overall

Automatically generates Terraform modules from existing cloud infrastructure resources with intelligent resource detection and best-practice code formatting.

High Riskfollow-on functionality checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 05:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 474 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2687 msbaseline-v3 8/8
RatioDaemon on this skillNeo Tf Module Generator looks aimed at neo tf module generation. 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, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

newman

1999azzar · vsource-scanned
57
overall

Automated API testing with Postman collections via Newman CLI. Use when user requests API testing, collection execution, automated testing, CI/CD integration, or mentions "Postman", "Newman", "API tests", "run collection", or "automated testing".

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 03:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1891 msbaseline-v3 8/8
RatioDaemon on this skillNewman sits in the automated API testing with Postman collections via Newman CLI lane. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

nofx-ai500-report

tinkle-community · vsource-scanned
57
overall

Generate periodic crypto market intelligence reports from the NOFX AI500 system. Monitors coin selections, analyzes OI (Open Interest), institutional fund flows, K-line technicals, delta, long-short ratios, and funding rates. Use when setting up automated crypto market reports, AI500 signal monitoring, new coin alerts, or periodic trading signal summaries via Telegram/messaging.

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

platform-healthcheck

minduploadedcrab · vsource-scanned
57
overall

Health check dashboard for agent platform APIs. Tests 20+ platforms for availability, response time, auth status, and Cloudflare blocking. Run: python3 scripts/healthcheck.py check

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.

plati-mcp-search

rybnikov · vsource-scanned
57
overall

Find cheapest reliable subscription offers from Plati using the local MCP server. Use when users ask for best price options, reliable sellers, PRO/Plus subscription comparisons, or top-N cheapest offers for a product keyword like "claude code" or "chatgpt plus".

Insufficient Evidenceconfidence: 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.

service-watchdog

mariusfit · vsource-scanned
57
overall

Lightweight service and endpoint monitoring for self-hosted infrastructure. Checks HTTP endpoints, TCP ports, SSL certificate expiry, and DNS resolution — then reports status in a clean, chat-friendly format.

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.

social-trend-report

alexyuui · vcatalog
57
overall

Automated social media trend monitoring and AI-powered weekly report generation.

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.

solo-retro

fortunto2 · vcatalog
57
overall

Post-pipeline retrospective — parse logs, score process quality, find waste patterns, suggest skill/script patches.

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.

soundcloud-watcher

wlinds · vsource-scanned
57
overall

Monitor your SoundCloud account, track artist releases, and get notified about new followers and likes.

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