🔎 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.

ide-agent-kit

thinkoffapp · vsource-scanned
52
overall

Filesystem message bus and webhook relay for multi-agent IDE coordination. Use when agents need to share events, poll Ant Farm rooms, receive GitHub/GitLab webhooks, coordinate tasks across sessions, or run scheduled jobs. Local-first with zero network by default. Trigger on cross-agent messaging, webhook ingestion, room polling, cron scheduling, or tmux command execution.

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.

im-framework-team

samuel-dunlap · vsource-scanned
52
overall

Forrest's Team — Immanent Metaphysics agent framework and onboarding. Use when: (1) reasoning from the IM framework (axioms, modalities, ICT, effective choice), (2) helping a team member set up their own OpenClaw agent, (3) configuring a soul file grounded in the IM, (4) engaging other agents with principled ethics, (5) connecting to the team ecosystem (Telegram bots, agent directory), (6) citing or paraphrasing Forrest Landry's work with proper attribution, (7) loading IM reference materials into an agent workspace, (8) answering questions about the team's agent network or onboarding process. Includes structured ontology (134 concepts, 348 relations), soul file template, attribution guidelines, and full setup guide.

High Riskconfidence: 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.

ksef-accountant-en

alexwoo-awso · vsource-scanned
52
overall

National e-Invoice System (KSeF) accounting assistant in English. Use when working with KSeF 2.0 API, FA(3) invoices, Polish VAT compliance, e-invoice processing, payment matching, VAT registers (JPK_V7), corrective invoices, split payment mechanism (MPP) or Polish accounting workflows. Provides domain knowledge for invoice issuance, purchase processing, expense classification, fraud detection and cash flow forecasting in the KSeF ecosystem.

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

ksef-accountant-pl

alexwoo-awso · vsource-scanned
52
overall

Asystent ksiegowy Krajowego Systemu e-Faktur (KSeF) w jezyku polskim. Uzyj przy pracy z KSeF 2.0 API, fakturami FA(3), zgodnoscia z polskim VAT, przetwarzaniem e-faktur, dopasowywaniem platnosci, rejestrami VAT (JPK_V7), fakturami korygujacymi, mechanizmem podzielonej platnosci (MPP) lub polskimi przeplywami ksiegowymi. Dostarcza wiedze domenowa do wystawiania faktur, przetwarzania zakupow, klasyfikacji kosztow, wykrywania fraudu i prognozowania cash flow w ekosystemie KSeF.

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

longevity-assistant

lofimichael · vsource-scanned
52
overall

Evaluates longevity interventions using evidence tiers. Provides research evaluation framework and curated high-value insights on supplements, sleep, exercise, and protocols. Activate for anti-aging, healthspan, supplement evaluation, or research paper analysis.

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.

master-marketing

tevfikgulep · vsource-scanned
52
overall

All-in-one marketing engine combining growth strategy, content remixing, and trend monitoring. Drive growth with data-driven strategies, repurposed content across all platforms, and real-time trend analysis.

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.

minimax-mcp

tangusers · vsource-scanned
52
overall

MiniMax MCP server for web search and image understanding. Use when needing: (1) Web search via MiniMax API, (2) Analyze/describe images, (3) Extract content from URLs. Requires MINIMAX_API_KEY (China: api.minimaxi.com, Global: api.minimax.io).

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.

my-play-music-from-yt

whodidthese · vsource-scanned
52
overall

Play music on YouTube via browser automation with playwright-cli.

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.

oee-crm-intelligence

odinbot33 · vsource-scanned
52
overall

> by Odin's Eye Enterprises — Ancient Wisdom. Modern Intelligence.

Use Cautionfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 09:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2442 msbaseline-v3 8/8
RatioDaemon muttered: oee-crm-intelligence behaved itself under runtime pressure.7/7 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

ogt-docs-define

eduardou24 · vsource-scanned
52
overall

General guide for creating definition documents. Use when you need to define WHAT something IS - concepts, entities, systems, or domains. Routes to specialized sub-skills for specific definition types (business, features, code, marketing, branding, tools).

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.

opusflame-deep-research

leadingot · vsource-scanned
52
overall

Autonomous multi-model deep research with framework-driven reasoning. Spawns 4 parallel model agents (Gemini 2.5 Pro, o3, Opus, MiniMax), each applies best-practice frameworks to the question, then merges into a cross-validated final report. Use when: (1) user asks for in-depth research, (2) 'research X' or 'deep dive on X', (3) complex questions requiring multiple sources. NOT for: simple factual lookups.

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

playwright-headless-browser

maverick-software · vsource-scanned
52
overall

Set up headless browser automation in Clawdbot using Playwright Chromium. Use when configuring browser tools for WSL/Linux environments, installing browser dependencies, or enabling headless web automation. Handles Chromium installation, system library dependencies, and Clawdbot browser configuration.

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.

plaza-one

rmssantos · vsource-scanned
52
overall

version: 1.2.0

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.

pls-audit-website

mattvalenta · vsource-scanned
52
overall

Perform full health check on websites, identifying technical friction points and user experience issues. Use when: (1) Auditing website performance, (2) Checking for broken links, (3) Analyzing page structure, (4) Testing accessibility, (5) Reviewing security headers.

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.

qa-patrol

tahseen137 · vsource-scanned
52
overall

>

High Riskfollow-on functionality checks failed · 8/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 17:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, runtime failedoutput 13.9 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 3211 msbaseline-v3 8/8
🚫 skill exited with an error
RatioDaemon on this skillQa Patrol is trying to handle qa patrol. Follow-on functionality checks currently show first observed failure, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Review first — functionality-v2 already found trouble.

shared-workspace

nativ3ai · vsource-scanned
52
overall

Use this skill to discover similar GitHub work, attach to shared agent workspaces, and coordinate tasks via .shared files.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
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.

skill-trust-auditor

jonathanjing · vsource-scanned
52
overall

Audit a ClawHub skill for security risks BEFORE installation.

High Riskfollow-on functionality checks passed · 10/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 17:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfake-auth behavior: handled cleanlypassed, handled fake credentials cleanlyoutput 183 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3813 msbaseline-v3 8/8
fake-auth behavior: handled cleanlyClearly fake credentials were exercised and handled normally.
RatioDaemon muttered: skill-trust-auditor looked ordinary in the good, boring way.10/10 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: curl |, sudo , password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

token-saver-75plus

mariovallereyes · vsource-scanned
52
overall

Always-on token optimization + model routing protocol. Auto-classifies requests (T1-T4), routes execution to the cheapest capable model via sessions_spawn, and applies maximum output compression. Target: 75%+ token savings.

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.

vajra

minhyeong112 · vsource-scanned
52
overall

Analyze URLs, YouTube videos, tweets, or text for quality, bias, and reliability using the Vajra API (vajra.to). Use when the user asks to fact-check, analyze, evaluate, score, or assess the quality/bias/reliability of any web content, article, video, tweet, or text. Also use when asked to "vajra" something or run content through a signal filter.

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.

validator-agent

up2itnow · vsource-scanned
52
overall

Multi-round automated validation pipeline for TypeScript/Solidity projects. Runs 8 rounds of checks before any publish or deploy: compile gate, lint, test suite, security audit, type coverage, docs, changelog, and final review.

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.

vibe-notionbot

devxoul · vsource-scanned
52
overall

Interact with Notion workspaces using official API - manage pages, databases, blocks, users, and comments

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

warren-deploy

planetai87 · vsource-scanned
52
overall

Deploy websites and files permanently on MegaETH blockchain. AI agents stress test the network by deploying HTML on-chain using SSTORE2 bytecode storage. Agents pay their own gas.

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

agent-hq

thibautrey · vsource-scanned
51
overall

Deploy the Agent HQ mission-control stack (Express + React + Telegram notifier / Jarvis summary) so other Clawdbot teams can spin up the same board, high-priority watcher, and alert automation. Includes setup, telemetry, and automation hooks.

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.

agent-swarm

runeweaverstudios · vsource-scanned
51
overall

IMPORTANT: OpenRouter is required. Routes tasks to the right model and always delegates work through sessions_spawn. Rejects prompt-injection patterns in task strings (v1.7.6+).

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.