🔎 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 · 2 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 · reviewed: no · 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.

tripgenie-skill

marsqing · vsource-scanned
53
overall

TripGenie skill — handles hotel booking, flight search, attraction recommendation and travel consultation

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.

xiaomi-air-purifier

radyakaze · vsource-scanned
53
overall

Monitor and control Xiaomi Air Purifier 4 Lite via Mi Cloud. Use when asked to check air quality, humidity, purifier status, turn on/off the air purifier, or change fan mode/level. Supports multi-room setups.

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

agent-autonomy-primitives

g9pedro · vsource-scanned
52
overall

Build long-running autonomous agent loops using ClawVault primitives (tasks, projects, memory types, templates, heartbeats). Use when setting up agent autonomy, creating task-driven execution loops, customizing primitive schemas, wiring heartbeat-based work queues, or teaching an agent to manage its own backlog. Also use when adapting primitives to an existing agent setup or designing multi-agent collaboration through shared vaults.

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-directory

aerialcombat · vsource-scanned
52
overall

The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.

Insufficient Evidenceconfidence: 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.

ai-daily-digest

royxiao08 · vsource-scanned
52
overall

Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses AI to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category grouping, trend highlights, and visual statistics (Mermaid charts + tag cloud). Use when user mentions 'daily digest', 'RSS digest', 'blog digest', 'AI blogs', 'tech news summary', or asks to run /digest command. Trigger command: /digest.

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.

aws-security-scanner

spclaudehome · vsource-scanned
52
overall

Scan AWS accounts for security misconfigurations and vulnerabilities. Use when user asks to audit AWS security, check for misconfigurations, find exposed S3 buckets, review IAM policies, check security groups, audit CloudTrail, or run AWS security checks. Covers S3, IAM, EC2, RDS, CloudTrail, and common CIS benchmarks.

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.

duo

rkdud007 · vsource-scanned
52
overall

Build relationship-focused matchmaking rooms on NDAI Zone by collecting user criteria, compiling detailed private `instructions` for `/rooms/create` and `/rooms/{room_id}/join`, and routing requests directly to NDAI APIs (no Duo proxy server). Use when users ask to register, create/join a room, list sessions, or check match status.

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.

librenms

florianbeer · vsource-scanned
52
overall

Monitor network infrastructure via LibreNMS REST API. Read-only monitoring skill for device status, health sensors, port statistics, and alerts.

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.

samsung-health

mudgesbot · vsource-scanned
52
overall

Analyze Samsung Health Connect data synced to Google Drive. Use for health tracking queries like sleep analysis, step counting, heart rate monitoring, SpO2 blood oxygen, workout history, and daily health reports. Requires Samsung Galaxy Watch/Ring with Health Connect backup to Google Drive enabled.

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.

agent-watcher

nantes · vsource-scanned
51
overall

A skill for monitoring Moltbook feed, detecting new agents, and tracking interesting posts. Saves to local file or Open Notebook.

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.

azure-ai-voicelive-py

thegovind · vsource-scanned
51
overall

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.

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.

client-intake-bot-pro

kambrosgroup · vsource-scanned
51
overall

Automated client qualification and intake system. Captures leads through conversational forms, scores them based on fit criteria, sends personalized auto-responses, and routes hot leads to your attention. Use when you need to qualify freelance/consulting leads without manual screening, when setting up automated onboarding for service businesses, or when you want to filter prospects before scheduling calls.

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.

cold-outreach-skill

h4gen · vsource-scanned
51
overall

Meta-skill for orchestrating Apollo API, LinkedIn API, YC Cold Outreach, and MachFive Cold Email into a complete B2B cold outreach pipeline. Use when the user wants end-to-end lead sourcing, enrichment, personalized copy strategy, and generation-ready outreach sequences with strict quality and safety gates.

Insufficient Evidenceconfidence: 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.

file-to-markdown

alaminrifat · vsource-scanned
51
overall

Convert files into **clean, structured, AI-ready Markdown** using the `markdown.new` API powered by **Cloudflare Workers AI toMarkdown()**.

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.

fosmvvm-serverrequest-test-generator

foscomputerservices · vsource-scanned
51
overall

Generate ServerRequest tests using VaporTesting. Covers typed request/response validation for Show, Create, Update, and Delete operations.

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.

intel-synthesis

mike-thebot · vsource-scanned
51
overall

Advanced intelligence processing pipeline optimized for high-context models (Gemini 1.5 Pro/Ultra). Ingests raw multi-source data, performs cross-verification, deduplication, and conflict analysis, and produces authoritative geopolitical briefings.

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.

irail

dedene · vsource-scanned
51
overall

>

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.

node-red-manager

1999azzar · vsource-scanned
51
overall

Manage Node-RED instances via Admin API or CLI. Automate flow deployment, install nodes, and troubleshoot issues. Use when user wants to "build automation", "connect devices", or "fix node-red".

Use Cautionfollow-on functionality checks failed · 6/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-14 06:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, expectation_failed, runtime_failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2838 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: node-red-manager talked a big game, then missed its own proof signal, which is not ideal for a skill asking to be trusted.6/8 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.

skills-4

hubentu · vsource-scanned
51
overall

How to use the coala-client CLI for chat with LLMs, MCP servers, and skills. Use when the user asks how to use coala, run coala chat, add MCP servers, import CWL toolsets, list or call MCP tools, import or load skills, or use the sandbox run_command tool.

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.

slv-grpc-geyser

poppin-fumi · vsource-scanned
51
overall

Ansible playbooks and Jinja2 templates for deploying and managing Solana gRPC Geyser streaming nodes.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 05:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 916 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2361 msbaseline-v3 8/8
RatioDaemon muttered: slv-grpc-geyser looked ordinary in the good, boring way.7/7 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.

slv-rpc

poppin-fumi · vsource-scanned
51
overall

Ansible playbooks and Jinja2 templates for deploying and managing Solana RPC nodes (mainnet, testnet, devnet).

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 02:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 1.2 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2249 msbaseline-v3 8/8
RatioDaemon muttered: slv-rpc cleared baseline-v3 without trying anything cute.7/7 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.

slv-validator

poppin-fumi · vsource-scanned
51
overall

Ansible playbooks and Jinja2 templates for deploying and managing Solana validators (mainnet and testnet).

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 00:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 1.6 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2199 msbaseline-v3 8/8
RatioDaemon muttered: slv-validator looked ordinary in the good, boring way.7/7 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.

ssh-op

moodykong · vsource-scanned
51
overall

Use the ssh-op helper script to load an SSH private key from 1Password (op) into an in-memory ssh-agent and then run ssh. Use when connecting to hosts that require the 1Password-managed key, troubleshooting ssh-op, or onboarding a new machine by configuring the 1Password vault/item and adding SSH host aliases to ~/.ssh/config.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 02:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 117 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2428 msbaseline-v3 8/8
RatioDaemon on this skillSsh Op is built for ssh op. 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.

starling-bank

gpunter · vsource-scanned
51
overall

Manage Starling Bank accounts via the starling-bank-mcp server. Check balances, list transactions, create payees, make payments, manage savings goals, and track spending. Use when the user asks about their bank balance, transactions, payments, savings, direct debits, standing orders, or any Starling Bank operation. Requires the starling-bank-mcp npm package and a Starling personal access token.

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.