🔎 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 · 1 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 2138 skills in the browsable catalog view · label: Trusted · 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.

n2-free-search

choihyunsus · vsource-scanned
60
overall

user-invocable: true

Trustedconfidence: 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.

nanobanana-pro-fallback

yazelin · vsource-scanned
60
overall

Nano Banana Pro with auto model fallback — generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'desc' --filename 'out.png' [--resolution 1K|2K|4K] [-i input.png]. Supports text-to-image + image-to-image (up to 14); 1K/2K/4K. Fallback chain: gemini-2.5-flash-image → gemini-2.0-flash-exp. MUST use uv run, not python3.

Trustedconfidence: 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.

native-airtable

codeninja23 · vsource-scanned
60
overall

Read Airtable bases, tables, and records directly via the Airtable API. Use when you need spreadsheet/database data from Airtable. Calls api.airtable.com directly with no third-party proxy.

Trustedconfidence: 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.

navifare-hidden-flight-deals

simonenavifare · vsource-scanned
60
overall

Verify and compare flight prices across multiple booking sites using Navifare. Trigger when users share flight prices from any booking site (Skyscanner, Kayak, etc.) or upload flight screenshots to find better deals. Returns ranked results with booking links from multiple providers.

Trustedconfidence: 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.

next-upgrade

tuanvidev · vsource-scanned
60
overall

Upgrade Next.js to the latest version following official migration guides and codemods

Trustedconfidence: 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.

ngamux

hadihammurabi · vsource-scanned
60
overall

Build and modify web services using ngamux, a simple HTTP router for Go. Define routes, apply middleware, handle requests, and send responses efficiently.

Trustedconfidence: 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.

norman-manage-clients

stanlee000 · vsource-scanned
60
overall

Manage business clients - list, search, create, or update client information. Use when the user mentions clients, contacts, customers, Kunden, or needs to manage their client database.

Trustedconfidence: 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.

norman-tax-deduction-finder

stanlee000 · vsource-scanned
60
overall

Scan transactions for potentially missed tax deductions and suggest proper categorization. Use when the user asks about saving taxes, Steueroptimierung, deductible expenses, Betriebsausgaben, or wants to check if they are missing any write-offs.

Trustedconfidence: 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.

norman-tax-report

stanlee000 · vsource-scanned
60
overall

Review and manage German tax reports including VAT (Umsatzsteuer), income tax prepayments, and Finanzamt submissions. Use when the user asks about taxes, Steuern, VAT, USt, Finanzamt, or tax filing.

Trustedconfidence: 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.

nova-net-worth

jessewunderlich · vsource-scanned
60
overall

Query your Nova Net Worth financial data — net worth, accounts, holdings, goals, spending, transactions, AI insights, and health score. Use when the user asks about their finances, money, net worth, account balances, investment holdings, portfolio, stocks, financial goals, spending habits, budget, savings, investments, debt, transactions, or financial health. Requires NOVA_API_KEY environment variable (API key from app.novanetworth.com → Settings → Integrations).

Trustedconfidence: 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.

oc-content-repurposer

mariusfit · vsource-scanned
60
overall

Repurpose any blog post or article into multiple social media formats. Input a URL or text, get X/Twitter thread, LinkedIn post, Instagram caption, email snippet, and summary. Use when asked to repurpose content, create social posts from an article, turn a blog into tweets, or generate multi-platform content.

Trustedconfidence: 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.

oc-daily-business-report

mariusfit · vsource-scanned
60
overall

Generate daily business briefings from multiple data sources. Aggregates weather, crypto prices, news headlines, system health, and calendar events into a formatted morning report. Use when asked to create a daily report, morning briefing, business summary, or status dashboard.

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

oc-security-hardener

mariusfit · vsource-scanned
60
overall

Audit and harden OpenClaw configuration for security. Scans openclaw.json for vulnerabilities, exposed credentials, insecure gateway settings, overly permissive exec rules, and missing security best practices. Use when asked to audit security, harden configuration, check for vulnerabilities, or secure an OpenClaw deployment.

Trustedconfidence: 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.

open-chrome-tabs

mindsocket · vsource-scanned
60
overall

Read currently open browser tabs from Chrome or other Chromium browsers (Arc, Brave, Edge, etc.). Use when you need to know what URLs the user has open, or want to list tabs from a synced device (e.g. Chrome on their phone).

Trustedconfidence: 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.

openrouter-usage

rosseyre · vsource-scanned
60
overall

Fetch real-time OpenRouter usage totals and historical per-model spend. Use when the user asks for usage, spend, cost breakdown, or OpenRouter stats. Not for system health or non-LLM metrics.

Trustedconfidence: 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.

opensoulmd

danielliuzy · vsource-scanned
60
overall

Search, summon, and possess your agent with SOUL.md personality files from the OpenSOUL.md registry

Trustedconfidence: 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.

ops-journal

mariusfit · vsource-scanned
60
overall

Structured operational journal that captures deployments, incidents, changes, and decisions. Creates a searchable ops log with incident timeline reconstruction and automated postmortem generation.

Trustedconfidence: 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.

opsecmd

wulf715 · vsource-scanned
60
overall

A swift reminder of both human and agent duties regarding operational security.

Trustedconfidence: 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.

pattern-finder

leegitw · vsource-scanned
60
overall

Discover what two sources agree on — find the signal in the noise.

Trustedconfidence: 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.

percept-speaker-id

jarvis563 · vsource-scanned
60
overall

Speaker identification and management for multi-person conversations.

Trustedconfidence: 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.

perplexity-deep-search

ericsantos · vsource-scanned
60
overall

Deep search via Perplexity API. Three modes: search (quick facts), reason (complex analysis), research (in-depth reports). Returns AI-grounded answers with citations.

Trustedconfidence: 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.

phone-caller

omerflo · vsource-scanned
60
overall

Make AI-powered outbound phone calls using ElevenLabs voice + GPT brain + Twilio. Supports one-way pre-recorded messages AND live two-way conversations where the AI listens, thinks, and responds in real-time. Use when asked to call someone, leave a voice message, schedule a morning call, have an AI make a reservation or appointment, run a voice campaign, or set up interactive phone conversations. Requires Twilio + ElevenLabs credentials. Triggers on 'call', 'phone', 'voice message', 'reserve', 'book by phone', 'schedule a call', 'call and tell them'.

Trustedconfidence: 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.

pr-triage

zerone0x · vsource-scanned
60
overall

Triage open PRs by detecting duplicates, assessing quality, and generating prioritized reports. Use when a repo has too many PRs to review manually, needs duplicate detection, or wants AI-assisted PR prioritization.

Trustedconfidence: 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.

printpal-3d

plebbyd · vsource-scanned
60
overall

Generate 3D models for 3D printing from images or text prompts using PrintPal API. Use when the user wants to create 3D printable models, convert images to STL/GLB/OBJ files, or generate 3D assets from text descriptions. Supports text-to-image via WaveSpeed when WAVESPEED_API_KEY is configured. Works with file paths, URLs, or images pasted directly into chat.

Trustedconfidence: 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.