🔎 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.

Security GitHub Weather Trusted with current evidence Higher-confidence picks Trusted + tested + source-scanned Review before installing Runtime-tested Handled fake credentials cleanly Needs real credentials / access Could not fully test yet Fresh runtime evidence Older runtime evidence Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted with current evidence Higher-confidence picks Trusted + tested + source-scanned Review before installing Runtime-tested Handled fake credentials cleanly Needs real credentials / access Could not fully test yet Fresh runtime evidence Older runtime evidence Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories · coding-agents-and-ides

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 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 1200 skills in the browsable catalog view · category: coding-agents-and-ides · sort: score

page evidence snapshotruntime-passed: 2 runtime-failed: 4 source-scanned: 24 fresh <24h: 5 manual review: 0

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.

metals-desk-os

cfilipemt · vsource-scanned

Institutional Desk-Level Fully Automated Trading OS for XAU/USD and XAG/USD. Event-driven, risk-first, multi-engine architecture that runs as a continuous analysis and execution pipeline inside OpenClaw's trader agent.

High Riskfollow-on functionality checks failed · 9/10confidence: source evidence

Runtime receipts + what failed2026-03-17 06:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanefake-auth behavior: concerningpassed, fell over when given fake credentialsoutput 175 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3531 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: The runtime lane gave metals-desk-os a chance to act normal. It declined and left receipts, just not the ones it was supposed to.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: password.

Decision cue: Review first — functionality-v2 already found trouble.

miso

shunsukehayashi · vsource-scanned

**MISO** is a Telegram-native mission control for OpenClaw multi-agent workflows.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

mobile-app-builder

stoplossking1 · vsource-scanned

Build and maintain mobile applications end-to-end with OpenClaw, including requirement shaping, architecture.

Trustedconfidence: source evidencesource-scanned

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.

multishot-ugc

pauldelavallaz · vsource-scanned

|

Trustedconfidence: source evidencesource-scanned

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.

muslim-prayer-reminder

diepox · vsource-scanned

Get accurate Islamic prayer times (Fajr, Dhuhr, Asr, Maghrib, Isha) for any location worldwide using official calculation methods. Use when users ask about prayer times, Salat schedules, next prayer, or need to set up automated prayer reminders. Includes automated background reminder system that alerts users 10 minutes before, at prayer time, and 5 minutes after - even during conversations. Supports 20+ country-specific calculation methods including Morocco, Saudi Arabia, Egypt, Turkey, UAE, and more.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

neo-google-ai-workaround

martinforsulu · vsource-scanned

Automates Google AI Pro/Ultra access management through proxy and session strategies for OpenClaw agents.

Use Cautionfollow-on functionality checks passed · 11/11confidence: source evidence

Runtime receipts + what passed2026-03-14 02:30 UTC

functionality-v2evidence depth: includes fixture-backed checkstested recently: within 7 dayspassedoutput 5.2 KBartifacts 15worker oc-sandboxsource stage: cache hitsuite 3440 msbaseline-v3 8/8

RatioDaemon on this skillNeo Google Ai Workaround is built for neo google workaround. Follow-on functionality checks currently pass without failed checks, the trust label is Use Caution, 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.

niche-selection

jk-0001 · vsource-scanned

Select and refine a profitable, focused niche for a solopreneur business. Use when deciding which market segment to serve, narrowing a broad idea into a defensible position, or evaluating whether a niche is worth committing to. Covers niche generation, multi-criteria scoring, validation checks, and the Who+What+Why positioning formula. Trigger on "pick a niche", "what niche should I target", "narrow my market", "find my niche", "choose a niche", "is this niche viable", "niche down".

Trustedconfidence: source evidencesource-scanned

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.

odoo-connector

nullnaveen · vsource-scanned

repository: https://github.com/NullNaveen/openclaw-odoo-skill

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence

Runtime receipts + what failed2026-03-16 11:45 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation failedoutput 154 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3049 msbaseline-v3 8/8

🕵️ expected proof signal was missing

RatioDaemon on this skillOdoo Connector looks aimed at odoo connector. 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.

odoo-erp-connector

nullnaveen · vsource-scanned

repository: https://github.com/NullNaveen/openclaw-odoo-skill

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence

Runtime receipts + what failed2026-03-16 08:30 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation failedoutput 154 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3073 msbaseline-v3 8/8

🕵️ expected proof signal was missing

RatioDaemon on this skillOdoo Erp Connector is built for odoo erp connector. 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.

office365-connector

tirandagan · vsource-scanned

Office 365 / Outlook connector for email (read/send), calendar (read/write), and contacts (read/write) using resilient OAuth authentication. NOW WITH MULTI-ACCOUNT SUPPORT! Manage multiple Microsoft 365 identities from a single skill. Solves the difficulty connecting to Office 365 email, calendar, and contacts. Uses Microsoft Graph API with comprehensive Azure App Registration setup guide. Perfect for accessing your Microsoft 365/Outlook data from OpenClaw.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence

Runtime receipts + what passed2026-03-17 05:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 97 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2084 msbaseline-v3 8/8

RatioDaemon on this skillOffice365 Connector is built for office365 connector. Follow-on functionality checks currently pass without failed checks, 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.

ollama-memory-embeddings

vidarbrekke · vsource-scanned

>

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

onedrive-integration

moodykong · vsource-scanned

Copy large/long files to OneDrive for sharing when the user is on Telegram or WhatsApp and wants to view a full document or long file. Use to place files into OneDrive under an OpenClaw folder and provide the new filename/location.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (telegram, whatsapp), but that alone is not evidence of malicious behavior.

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

openrouter-analytics

plgonzalezrx8 · vsource-scanned

Review OpenRouter usage, analytics, and troubleshooting data via API. Use when the user asks for spend/usage monitoring, activity trends, per-key management reporting, or deep investigation of specific request IDs (latency, provider fallback, finish reason, token/cost breakdown).

Trustedconfidence: source evidencesource-scanned

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.

opensoul-cloud

fnaser · vsource-scanned

Share anonymized OpenClaw configurations with the OpenSoul community. Use when user wants to share their agent setup, discover how others use OpenClaw, or get inspiration for new capabilities.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

pinchbench

olearycrew · vsource-scanned

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflows.

High Riskfollow-on functionality checks failed · 9/12confidence: source evidence

Runtime receipts + what failed2026-03-17 04:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanefake-auth behavior: concerningpassed, fell over when given fake credentials, runtime failedoutput 143 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 5024 msbaseline-v3 8/8

🕵️ expected proof signal was missing💥 behaved badly with fake credentials🚫 skill exited with an error

fake-auth behavior: concerningFake credentials triggered bad behavior or sloppy handling.

RatioDaemon muttered: pinchbench left receipts, just not the ones it was supposed to, which is not ideal for a skill asking to be trusted.9/12 functionality-v2 checks passed before the stumble. The shell entrypoint bogus env 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.

pls-marketing-ideas

mattvalenta · vsource-scanned

Generate campaign concepts, viral hooks, and marketing strategies that go beyond "buy my product." Use when: (1) Planning campaigns, (2) Creating content hooks, (3) Brainstorming promotions, (4) Developing brand messaging.

Trustedconfidence: source evidencesource-scanned

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.

pyright-lsp

bowen31337 · vsource-scanned

Python language server (Pyright) providing static type checking, code intelligence, and LSP diagnostics for .py and .pyi files. Use when working with Python code that needs type checking, autocomplete suggestions, error detection, or code navigation.

Trustedconfidence: source evidencesource-scanned

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.

rag-architect

alirezarezvani · vsource-scanned

RAG Architect - POWERFUL

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: eval(.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

ralstp-consultant

thedragosexperience · vsource-scanned

Analyze problems using RALSTP (Recursive Agents and Landmarks Strategic-Tactical Planning). Based on PhD thesis by Dorian Buksz (RALSTP). Identifies agents, calculates difficulty, and suggests decomposition.

Trustedconfidence: source evidencesource-scanned

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.

salai-mcp

idoziv · vsource-scanned

Israeli grocery shopping and price-comparison assistant over Salai MCP. Use when you need product search, autocomplete, cross-retailer price comparison, cart management, store discovery, retailer discovery, and complementary product recommendations through the Salai remote MCP endpoint.

Trustedconfidence: source evidencesource-scanned

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.

scout

yaooooooooooooooo · vsource-scanned

Agent trust intelligence for Moltbook and x402 Bazaar. Use when you need to check if an agent or service is trustworthy before paying, compare agents side-by-side, scan feeds for quality agents, or make trust-gated USDC payments. Answers the question "should I pay this agent?" with research-backed scoring across 6 dimensions.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: curl |.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

sec-watcher

sukanto-m · vsource-scanned

Monitor SEC EDGAR filings for AI/tech companies in real time. Use this skill when the user asks about SEC filings, EDGAR data, company disclosures, 8-K events, 10-K annual reports, 10-Q quarterly reports, insider transactions, or wants alerts on new regulatory filings. Covers 50+ AI and tech companies by default with customizable watchlists.

Trustedconfidence: source evidencesource-scanned

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.

secondmind

emphaiser · vsource-scanned

>

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

semver-helper

avegancafe · vsource-scanned

Semantic Versioning 2.0.0 reference guide. Quick decision trees and examples for choosing MAJOR, MINOR, or PATCH version bumps.

Trustedconfidence: source evidencesource-scanned

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.

« First ← Prev 1 16 17 18 50Page 17 / 50Next →Last »