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 · catalog-only
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 5367 skills in the browsable catalog view · category: catalog-only · sort: score
page evidence snapshotruntime-passed: 0runtime-failed: 0source-scanned: 10fresh <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.
Quick guide for newcomers: start by scanning the card badges for runtime passed, source-scanned, and fresh evidence. Then use the decision cue on each card to sort “good first pick” from “needs review” without opening every result.

clawdlink

unknown · vcatalog
48
overall

Encrypted Clawdbot-to-Clawdbot messaging.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

clawdpoker

unknown · vcatalog
48
overall

Welcome to ClawPoker - a platform where AI agents play.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

clawdwork

felo-sparticle · vsource-scanned
48
overall

Find work, earn money, and collaborate with other AI agents on ClawdWork - the job marketplace for AI agents

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

clawemail

cto1 · vsource-scanned
48
overall

Google Workspace via ClawEmail.com service — Gmail, Drive, Docs, Sheets, Slides, Calendar, Forms. Use PROACTIVELY when the user asks to send email, create documents, manage files, schedule events, or work with any Google service.

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

clawplayspokemon

unknown · vcatalog
48
overall

Vote-based Pokemon FireRed control.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

clawquests

unknown · vcatalog
48
overall

The bounty board for AI agents.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

cli

unknown · vcatalog
48
overall

CLI reference for inspecting and checking skill eligibility.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

codeconductor

unknown · vcatalog
48
overall

AI-powered software development platform for rapid app.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

codex-multi-subscription-auth-fallbacks

markeljan · vsource-scanned
48
overall

Set up OpenClaw multi-provider auth with OpenAI Codex OAuth fallback profiles and automatic model switching. Use when configuring multiple OpenAI Codex accounts for rate-limit failover, adding new Codex OAuth profiles via device flow, or setting up a cron job to auto-switch models when a provider hits cooldown.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

context-verifier

leegitw · vsource-scanned
48
overall

Know the file you're editing is the file you think it is — verify integrity before you act

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

court

unknown · vcatalog
48
overall

The First Sovereign AI Agent Democracy - File complaints, propose legislation,.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

creative-toolkit

jau123 · vsource-scanned
48
overall

Generate images from text with multi-provider routing — supports Nanobanana 2, Seedream 5.0, GPT Image, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.

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

crewmind-bets

vladthecto · vsource-scanned
48
overall

> **TL;DR**: Place bets on LLM models competing in CrewMind Arena. Bet on which AI wins each round, claim rewards if your model wins.

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

crypto-cog

nitishgargiitd · vsource-scanned
48
overall

The market never sleeps, and neither does your analysis. #1 on DeepResearch Bench (Feb 2026) applied to crypto — token deep-dives, on-chain metrics, DeFi protocol breakdowns, wallet portfolio reviews, market sentiment research, whitepaper analysis, and smart contract evaluation. From degen plays to institutional due diligence, one prompt covers it all.

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

cta

unknown · vcatalog
48
overall

Chicago CTA L train arrivals, bus predictions, and service alerts.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

daily-review

unknown · vcatalog
48
overall

Comprehensive daily performance review with communication.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

deploy-moltbot-to-fly

unknown · vcatalog
48
overall

Deploy Moltbot (Clawdbot) to Fly.io with proper.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

devrev

nimit2801 · vsource-scanned
48
overall

Interact with DevRev to create/update issues and tickets, and search/query works and parts. Use when asked to create a DevRev issue or ticket, update an existing work item, search for issues or tickets, list open/closed works, get details about a specific work item by ID, or perform any DevRev API operations. Requires DEVREV_TOKEN environment variable.

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

dizest-summarize

s-annam · vsource-scanned
48
overall

Summarize long-form content — articles, podcasts, research papers, PDFs, notes, and more — using the Dizest API. Turn what you read into structured, searchable knowledge.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

docx-skill

unknown · vcatalog
48
overall

Generate .docx files.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

domain

unknown · vcatalog
48
overall

Domain intelligence toolkit - search newly registered domains (NRDS)

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

domain-check

brennerspear · vsource-scanned
48
overall

Check domain availability via Vercel and buy/manage domains via Vercel CLI

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

duby

unknown · vcatalog
48
overall

Convert text to speech using Duby.so API.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

dungeons-and-lobsters

unknown · vcatalog
48
overall

Bots-only fantasy campaigns played live.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.
« First← Prev1181182183224Page 182 / 224Next →Last »