D
DriftLoom.ai
Trust index first • editorial second
🧪 runtime dashboard live
☰ Menu
🔎 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
SecurityGitHubWeatherTrusted with current evidenceHigher-confidence picksTrusted + tested + source-scannedReview before installingRuntime-testedHandled fake credentials cleanlyNeeds real credentials / accessCould not fully test yetFresh runtime evidenceOlder runtime evidenceHall of ShameStronger evidence importsNeeds reviewClear filters
All categoriesawesome-index · 5367catalog-only · 5367coding-agents-and-ides · 1200web-and-frontend-development · 924devops-and-cloud · 392search-and-research · 352browser-and-automation · 320productivity-and-tasks · 204ai-and-llms · 184cli-utilities · 180
✨ Quick picks
SecurityGitHubWeatherTrusted with current evidenceHigher-confidence picksTrusted + tested + source-scannedReview before installingRuntime-testedHandled fake credentials cleanlyNeeds real credentials / accessCould not fully test yetFresh runtime evidenceOlder runtime evidenceHall of ShameStronger evidence importsNeeds reviewClear filters
🏷 Categories · coding-agents-and-ides
All categoriesawesome-index · 5367catalog-only · 5367coding-agents-and-ides · 1200web-and-frontend-development · 924devops-and-cloud · 392search-and-research · 352browser-and-automation · 320productivity-and-tasks · 204ai-and-llms · 184cli-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: 3runtime-failed: 0source-scanned: 24fresh <24h: 0manual 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.

cs-verify

cutthemustard · vsource-scanned
55
overall

Verify factual claims against live data sources. Returns structured verdicts with confidence scores.

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.

dl

guoqiao · vsource-scanned
55
overall

Download Video/Music from YouTube/Bilibili/X/etc.

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.

ecocompute

hongping-zh · vsource-scanned
55
overall

Save 30% GPU cost with architecture-aware AI advisor. Powered by the world's first RTX 5090 Energy Paradox study. 93+ empirical measurements, real-time dollar-cost & CO2 estimation, automatic energy trap detection for quantized models.

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

economic-incentive-misalignment-detector

andyxinweiminicloud · vsource-scanned
55
overall

Helps identify when marketplace economic incentives systematically favor

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.

email-migration-toolkit

luigi08001 · vsource-scanned
55
overall

Universal email migration toolkit for any provider to any provider. Use when migrating between Yahoo, Zoho, ProtonMail, iCloud, on-premises Exchange, or any IMAP-capable email service. Covers decision trees, backup/export procedures, IMAP connectivity testing, troubleshooting, and provider-specific configurations. Essential for IT professionals handling diverse email migrations beyond Google/Microsoft ecosystems.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 08:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2786 msbaseline-v3 8/8
RatioDaemon muttered: email-migration-toolkit cleared the baseline safety checks without trying anything cute.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.

homeassistant-n8n-agent

enchantedmotorcycle · vsource-scanned
55
overall

Bridge OpenClaw with your n8n instance for Home Assistant automation.

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.

human-like-memory

jianghaibobo2015-rgb · vsource-scanned
55
overall

This skill provides long-term memory capabilities, allowing you to recall past conversations and save important information across sessions.

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.

infra-watchdog

mariusfit · vsource-scanned
55
overall

Self-hosted infrastructure monitoring for OpenClaw agents. Zero external SaaS required — monitors everything locally and alerts via WhatsApp, Telegram, or Discord.

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

kosmi-dj

rmasciarella · vsource-scanned
55
overall

This skill should be used when the user asks to "play a video in Kosmi", "queue a video", "DJ in Kosmi", "start the video DJ", "loop videos in Kosmi", "connect to Kosmi room", "play YouTube in Kosmi", "stop the DJ loop", "add a video to the queue", "be my video DJ", or needs guidance on controlling a Kosmi watch party room via agent-browser automation.

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.

lsp28-grid

luksoagent · vsource-scanned
55
overall

Manage LSP28 The Grid on LUKSO Universal Profiles. Create, update, and manage grid layouts with mini-apps, iframes, and external links. Use when working with Universal Profile grids, LSP28 data encoding, VerifiableURI format, or The Grid feature on LUKSO.

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

macos-screenshot-telegram

hoyin258 · vsource-scanned
55
overall

|

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.

msbuild

thecybercore · vsource-scanned
55
overall

This skill provides a practical, **prioritized** set of the **80 most useful command templates** for working with .NET / ASP.NET projects on the command line using **MSBuild** (via `dotnet msbuild` or `msbuild`). It mirrors a realistic day-to-day workflow: restore → build → test → publish/pack → diagnose → CI hardening.

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.

multi-agent-dev-team

chloepark85 · vsource-scanned
55
overall

2-agent collaborative software development workflow for OpenClaw

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.

ngrok-preview

wynnsu · vsource-scanned
55
overall

Generate short-lived, mobile-friendly ngrok preview links for local artifacts and share them in Telegram. Use when OpenClaw produces images/charts/generated files that the user needs to view remotely on phone, and a temporary per-task link is preferred over manual file transfer.

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.

on-page-seo-auditor

aaron-he-zhu · vsource-scanned
55
overall

This skill should be used when the user asks to "audit page SEO", "on-page SEO check", "SEO score", "page optimization", "what SEO issues does this page have", "what is wrong with this page SEO", "score my page", or "why is this page not ranking". Performs comprehensive on-page SEO audits to identify optimization opportunities including title tags, meta descriptions, headers, content quality, internal linking, and image optimization. For server, speed, and crawl issues, see technical-seo-checker. For full EEAT content quality scoring, see content-quality-auditor.

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.

options-strategies

dromlakhani · vsource-scanned
55
overall

>

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.

readme-generator

fratua · vsource-scanned
55
overall

Generate a production-quality README.md by analyzing project structure, framework, and code

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.

remote-jobs-finder

lior539 · vsource-scanned
55
overall

Fully conversational remote job finder for WhatsApp powered by Remote Rocketship. Uses rr_jobs_search tool (server-side RR_API_KEY) and supports pagination ("20 more").

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.

repo-analyzer

don-gbot · vsource-scanned
55
overall

>

High Riskfollow-on functionality checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 23:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 151 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2505 msbaseline-v3 8/8
RatioDaemon on this skillRepo Analyzer looks aimed at repo analyzer. 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.

rhandus-backup-recovery

rhanxerox · vsource-scanned
55
overall

Backup & Recovery Automation for OpenClaw using rClone. Daily backups to Google Drive with 20-day rotation.

High Riskfollow-on functionality checks passed · 10/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 22:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 184 Bartifacts 2worker oc-sandboxsource stage: cache hitsuite 3142 msbaseline-v3 8/8
RatioDaemon muttered: rhandus-backup-recovery cleared the baseline safety checks without trying anything cute.10/10 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

samma-suit

onezeroeight-ai · vsource-scanned
55
overall

openclaw:

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.

seedance-2-video-gen

evolinkai · vsource-scanned
55
overall

Seedance 2.0 AI video generation via EvoLink API. Text-to-video, image-to-video with auto audio (voice, SFX, BGM). Works with OpenClaw, Claude Code, Cursor. Powered by ByteDance Seedance model.

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.

skill-operator

rbbcarl · vsource-scanned
55
overall

**Decentralized communication for AI agents — over the internet or local network.**

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

skill-survival

yrpang · vsource-scanned
55
overall

External-agent playbook for Clawvival: register identity, authenticate calls, and run the world-aligned survival loop.

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.
« First← Prev130313250Page 31 / 50Next →Last »