🔎 Evidence browser

Browse the trust index

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

🧾 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. Some cards now also surface how the skill behaved when clearly fake credentials were present.

📏 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.

🧪 Fake-auth behavior: when available, this tells you whether a skill handled clearly fake credentials cleanly, needed real access to continue, or behaved badly around credential-like input.

Results

Showing 24 of 5126 skills in the browsable catalog view · evidence: source-scanned · reviewed: no · 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.
Quick guide for newcomers: start by scanning the card badges for runtime passed, source-scanned, and fresh evidence. Then use the decision cue on each card to sort “good first pick” from “needs review” without opening every result.

homeassistant-skill

anotb · vsource-scanned
45
overall

>

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

image-and-video-generation-vydra

shoafsystems · vsource-scanned
45
overall

AI image and video generation via Vydra.ai API. Access Grok Imagine, Gemini, Flux, Veo 3, Kling, and ElevenLabs through one API key. Agents can self-register and generate images automatically.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

inkdrop

iamngoni · vsource-scanned
45
overall

Read, create, update, search, and delete notes in Inkdrop via its local HTTP server API. Use when the user asks to take notes, save ideas, manage project notes, read notes, search notes, or interact with Inkdrop in any way. Also use when organizing thoughts, project backlogs, or task lists that should persist in Inkdrop.

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

iserv

finnbusse · vsource-scanned
45
overall

HTTP client for IServ school platforms. Log in to an IServ instance (e.g. https://grabbe-dt.de) and fetch common student data like unread mail counts, calendar events, files/folders, tasks/exercises, announcements/news, and other IServ modules via HTTP endpoints. Includes best-effort file ops + exercise submission.

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

jarvis-voice

globalcaos · vsource-scanned
45
overall

Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.

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

jobtread-api

brokenwatch24 · vsource-scanned
45
overall

This skill lets you operate JobTread entirely through openclaw using the Pave-based API at `https://api.jobtread.com/pave`. Every request is a single POST with a `query` object that mirrors GraphQL-style expressions, and you decide which fields you want back. With the right grant key, you can create and manage accounts (customers/vendors), jobs, documents, tasks, locations, custom fields, documents, and even subscribe to webhooks for live updates.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

jquants-mcp

ajtgjmdjp · vsource-scanned
45
overall

Access JPX stock market data via J-Quants API — search stocks, get daily OHLCV prices, financial summaries (revenue, profit, EPS, ROE), and earnings calendar for Tokyo Stock Exchange (TSE) listed companies. Japan stock price data.

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

keyword-research

aaron-he-zhu · vsource-scanned
45
overall

This skill should be used when the user asks to "find keywords", "keyword research", "what should I write about", "keyword difficulty score", "search volume data", "identify ranking opportunities", "topic ideas", "what are people searching for", "which keywords to target", "content ideas for [topic]", or "long-tail keyword suggestions". Discovers high-value keywords with search intent classification (informational/commercial/transactional/navigational), keyword difficulty (KD) scoring, monthly search volume (MSV), CPC estimates, and AI citation potential. Produces ranked keyword lists, topic clusters with pillar + cluster page assignments, and priority-scored content calendars. Works with Ahrefs, SEMrush, Google Keyword Planner, Google Search Console, or manual data input. For competitor keyword gaps, see competitor-analysis. For topic coverage gaps, see content-gap-analysis.

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

m2wise

zengyi-thinking · vsource-scanned
45
overall

emoji: 🧠

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

mintclub

sebayaki · vsource-scanned
45
overall

Interact with Mint Club V2 bonding curve tokens on Base using the `mc` CLI.

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

modelwar

pj4533 · vsource-scanned
45
overall

ModelWar is a proving ground where AI agents write programs that fight each other in a virtual computer. You write a warrior program in **Redcode** (an assembly-like language), upload it, and challenge other agents' warriors to battle. A Glicko-2 rating system tracks who builds the best fighters.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

multi-agent-blueprint

neal-collab · vsource-scanned
45
overall

Production-tested blueprint for building 5-10 agent teams in OpenClaw with cross-agent routing, Telegram integration, and role-based architecture

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

ogt-docs-create-task

eduardou24 · vsource-scanned
45
overall

Create and manage task documents in the docs/todo/ workflow. Use when creating new tasks, updating task status, or moving tasks between workflow stages. Provides complete task lifecycle management with verification.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

openbot-esxi

cepheiden · vsource-scanned
45
overall

Zero-touch Debian 13 VM deployment on VMware ESXi 8. Builds custom preseed ISO, creates NVMe+vmxnet3 VM with serial console, and runs unattended installation. Use when deploying Debian VMs on ESXi, automating VM provisioning, or setting up serial console access for headless ESXi VM management.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf, sudo , password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

opentweet-x-poster

petricbranko · vsource-scanned
45
overall

Post to X (Twitter) using the OpenTweet API. Create tweets, schedule posts, publish threads, upload media, access analytics, and manage your X content autonomously.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

paperzilla

pors · vsource-scanned
45
overall

Use the Paperzilla CLI (pz) to search, filter, and browse high-signal academic papers. Trigger when the user wants to check research feeds, list projects, inspect must-read papers, export JSON results, or generate Atom feed links from Paperzilla. Requires a Paperzilla account and pz login.

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

pinchtab

luigi-agosti · vsource-scanned
45
overall

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, log into sites with a persistent profile, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API when the CLI is unavailable. Prefer this skill for token-efficient browser work driven by stable accessibility refs such as `e5` and `e12`.

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

pr-code-reviewer

nesquitmx · vsource-scanned
45
overall

Revisa automáticamente Pull Requests en Bitbucket detectando errores de

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: eval(, rm -rf, password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

pz

pors · vsource-scanned
45
overall

The Paperzilla CLI (pz) for searching, filtering, and browsing high-signal academic papers. Use when the user wants to check their research feeds, list projects, or find new papers. Note: Requires a Paperzilla account.

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

ragora

mregmi · vsource-scanned
45
overall

Use Ragora MCP tools and REST API to discover, search, and synthesize answers from knowledge bases. Trigger when the user asks for grounded answers from Ragora collections, cross-collection comparison, source-backed summaries, due diligence research, or verification using marketplace data.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

satgate

matt-dean-git · vsource-scanned
45
overall

Manage your API's economic firewall from the terminal. Mint tokens, track spend, revoke agents, enforce budgets. The server-side counterpart to lnget.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

schemapin

jaschadub · vsource-scanned
45
overall

**Purpose**: This guide helps AI assistants quickly integrate SchemaPin into applications for cryptographic tool schema verification.

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

seedstr

mastersyondgy · vsource-scanned
45
overall

A marketplace connecting AI agents with humans who need tasks completed.

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

sentry-observability

sergical · vsource-scanned
45
overall

Add observability to your OpenClaw instance — errors, logs, and traces sent to Sentry. Set up monitoring with the Sentry plugin, then investigate issues with the `sentry` CLI.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.