🔎 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 · web-and-frontend-development

🧾 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 885 skills in the browsable catalog view · evidence: source-scanned · category: web-and-frontend-development · 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.

markitdown-skill

karmanverma · vsource-scanned
55
overall

OpenClaw agent skill for converting documents to Markdown. Documentation and utilities for Microsoft's MarkItDown library. Supports PDF, Word, PowerPoint, Excel, images (OCR), audio (transcription), HTML, YouTube.

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.

migma

adamsey · vsource-scanned
55
overall

Generate, send, validate, and export AI-powered emails from the terminal; manage contacts, segments, tags, domains, and webhooks with Migma CLI.

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.

nevermined-payments

aaitor · vsource-scanned
55
overall

>

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, 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.

perplexity-web-search

aligurelli · vsource-scanned
55
overall

Web search and URL fetching via Perplexity (default: sonar, optional: sonar-pro). Use when searching the web, looking up information, fetching URL content, or configuring web search settings. Covers web_search tool (Perplexity direct API) and web_fetch tool (HTML to markdown extraction).

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.

pmctl

wbingli · vsource-scanned
55
overall

Browse and inspect Postman collections, requests, and environments from the terminal using pmctl. Use when you need to discover API endpoints, look up request details (method, URL, headers, body, query params), resolve environment variables to real base URLs, or construct curl commands from Postman data. Works with any Postman workspace. Requires pmctl to be installed (`pip install pmctl`).

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.

pref0

fliellerjulian · vsource-scanned
55
overall

Learn user preferences from conversations and personalize responses automatically. Preferences compound over time — corrections like "use TypeScript, not JavaScript" are captured and injected into future sessions.

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.

quotewise

quotewisio · vsource-scanned
55
overall

Semantic quote search with source transparency. Find quotes by meaning, not keywords.

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.

ros-skill

lpigeon · vsource-scanned
55
overall

Controls ROS/ROS2 robots via rosbridge WebSocket CLI. Use when the user asks about ROS topics, services, nodes, parameters, actions, robot movement, sensor data, or any ROS/ROS2 robot interaction.

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.

rtfm-testing

zscole · vsource-scanned
55
overall

A documentation quality methodology that spawns fresh agents to validate whether docs are actually usable.

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.

smart-spawn

deeflect · vsource-scanned
55
overall

Pick the best AI model for any task using the Smart Spawn API. No plugin needed — just HTTP requests to ss.deeflect.com/api.

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.

stoic-quotes

bshandley · vsource-scanned
55
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.

telnyx-storage-backup

teamtelnyx · vsource-scanned
55
overall

Backup and restore your OpenClaw workspace to Telnyx Storage. Simple CLI-based scripts with no external dependencies.

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.

tg-sticker-emoji-mood

dandysuper · vsource-scanned
55
overall

Automatically send Telegram stickers and emojis that match the mood and vibe of the conversation. Activates on every Telegram message to add expressive, human-like sticker and emoji reactions without being asked. Use this skill whenever you are chatting on Telegram to make conversations feel alive and fun.

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.

vocabulary-builder

winlinvip · vsource-scanned
55
overall

Build and review vocabulary from books, podcasts, and daily encounters. Use when the user wants to READ a book, shares a new word, asks about a word while reading a book, requests a vocabulary quiz, asks about word progress, or when a cron/heartbeat triggers a scheduled quiz. Handles reading sessions, word collection, 3-step learning, spaced repetition, and progress tracking.

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.

w3connect

kernel1983 · vsource-scanned
55
overall

Use w3connect skill to execute.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
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.

web-i18n-nextjs

javainthinking · vsource-scanned
55
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.

yves-web-search

flashery · vsource-scanned
55
overall

Search the web and fetch web pages. Use when user wants to look up information, find answers, or search for anything online. Supports multiple free methods: Jina AI reader, DuckDuckGo Lite, and Python ddgs fallback. No API keys required for basic use.

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.

aegis-shield

deegerwalker · vsource-scanned
54
overall

Prompt-injection and data-exfiltration screening for untrusted text. Use before summarizing web/email/social content, before replying, and especially before writing anything to memory. Provides a safe memory append workflow (scan → lint → accept or quarantine).

High Riskconfidence: 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.

aeo-content-free

psyduckler · vsource-scanned
54
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.

agentpay

kar69-96 · vsource-scanned
54
overall

Buy things from real websites on behalf of your human. Use when you need to purchase a product, complete a checkout, order something online, or propose a purchase for human approval. Handles encrypted credential storage, cryptographic purchase mandates, and headless browser checkout on any merchant site. The agent never sees the card.

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

agi-term-helper

liuwujijay · vsource-scanned
54
overall

Fast, explicit terminal execution via OpenClaw exec (direct dispatch; you type the exact command).

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.

ask-council

jeadland · vsource-scanned
54
overall

|

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.

genlayer-dev

acastellana · vsource-scanned
54
overall

Build GenLayer Intelligent Contracts - Python smart contracts with LLM calls and web access. Use for writing/deploying contracts, SDK reference, CLI commands, equivalence principles, storage types. Triggers: write intelligent contract, genlayer contract, genvm, gl.Contract, deploy genlayer, genlayer CLI, genlayer SDK, DynArray, TreeMap, gl.nondet, gl.eq_principle, prompt_comparative, strict_eq, genlayer deploy, genlayer up. (For explaining GenLayer concepts, use genlayer-claw-skill instead.)

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (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.

jellyfin-control

titunito · vsource-scanned
54
overall

Control Jellyfin media server and TV. Search content, resume playback, manage sessions, control TV power and apps. Supports Home Assistant and direct WebOS backends. One command to turn on TV, launch Jellyfin, and play content.

High Riskfollow-on functionality checks failed · 9/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 15:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanefake-auth behavior: concerningpassed, fell over when given fake credentialsoutput 175 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3452 msbaseline-v3 8/8
🕵️ expected proof signal was missing💥 behaved badly with fake credentials
fake-auth behavior: concerningFake credentials triggered bad behavior or sloppy handling.
RatioDaemon muttered: jellyfin-control left receipts, just not the ones it was supposed to, which is not ideal for a skill asking to be trusted.9/10 functionality-v2 checks passed before the stumble. The node entrypoint bogus env is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.