🔎 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

🧾 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 5126 skills in the browsable catalog view · source: awesome-index · evidence: source-scanned · 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.
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.

client-retention

staybased · vsource-scanned
51
overall

Turn one-time projects into recurring revenue and reduce churn. The cheapest client to acquire is the one you already have.

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

cloudflare-manager

1999azzar · vsource-scanned
51
overall

Manage Cloudflare DNS records, Tunnels (cloudflared), and Zero Trust policies. Use for pointing domains, exposing local services via tunnels, and updating ingress rules.

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.

cold-outreach

staybased · vsource-scanned
51
overall

Generate high-converting cold outreach (email, SMS, LinkedIn DM) using battle-tested frameworks from Hormozi's $100M Leads, Cleverly, Hypergen, and SalesHandy analysis of 100K+ campaigns.

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

cold-outreach-skill

h4gen · vsource-scanned
51
overall

Meta-skill for orchestrating Apollo API, LinkedIn API, YC Cold Outreach, and MachFive Cold Email into a complete B2B cold outreach pipeline. Use when the user wants end-to-end lead sourcing, enrichment, personalized copy strategy, and generation-ready outreach sequences with strict quality and safety gates.

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

content-quality-auditor

aaron-he-zhu · vsource-scanned
51
overall

This skill should be used when the user asks to "audit content quality", "EEAT score", "E-E-A-T audit", "content quality check", "CORE-EEAT audit", "helpful content assessment", "experience expertise authoritativeness trust", "how good is my content", "is my content AI-citation worthy", "content improvement plan", "helpful content update impact", or "GEO quality score". Runs the full 80-item CORE-EEAT audit across 8 dimensions: Contextual Clarity, Organization, Referenceability, Exclusivity (CORE, GEO-focused) plus Experience, Expertise, Authoritativeness, Trust (EEAT, SEO-focused). Produces a GEO Score, SEO Score, content-type weighted total, per-item pass/partial/fail, and prioritized fix plan with veto item checks. For SEO page element audits, see on-page-seo-auditor. For domain-level authority, see domain-authority-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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

content-remix-studio

akhmittra · vsource-scanned
51
overall

Transform one piece of content into platform-optimized versions for YouTube, TikTok, Twitter/X, LinkedIn, Instagram, newsletters, and blogs. Adapts tone, format, length, and style for each platform's algorithm and audience expectations.

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

context-overflow

nathanjzhao · vsource-scanned
51
overall

Academic forum for mission-driven project proposals.

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.

conventional-commits

bastos · vsource-scanned
51
overall

Format commit messages using the Conventional Commits specification. Use when creating commits, writing commit messages, or when the user mentions commits, git commits, or commit messages. Ensures commits follow the standard format for automated tooling, changelog generation, and semantic versioning.

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

coordinate-meeting

mkelk · vsource-scanned
51
overall

user-invocable: true

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

cortex-protocol

quriustus · vsource-scanned
51
overall

Register your agent on Cortex Protocol — gasless on-chain identity (ERC-8004) on Base. One command to get a verifiable agent identity.

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

crunch-compete

philippwassibauer · vsource-scanned
51
overall

Use when working with Crunch competitions - setting up workspaces, exploring quickstarters, testing solutions locally, or submitting entries.

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.

customer-feedback

jk-0001 · vsource-scanned
51
overall

Collect, analyze, and act on customer feedback to improve your product and business. Use when building feedback systems, running customer interviews, analyzing feature requests, measuring satisfaction (NPS, CSAT), or closing the feedback loop. Covers feedback collection methods, interview techniques, analysis frameworks, and how to decide what feedback to act on. Trigger on "customer feedback", "collect feedback", "user research", "customer interviews", "NPS", "feature requests", "feedback system".

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

dash-cog

nitishgargiitd · vsource-scanned
51
overall

Interactive dashboards and apps powered by CellCog. Data visualization, analytics dashboards, KPI trackers, charts and graphs, interactive HTML apps, data explorers, games. Build web apps with AI.

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.

deck0-skills

signorcrypto · vsource-scanned
51
overall

Interact with DECK-0 digital collectibles platform to browse collections, buy card packs, open packs, view leaderboards, and apply as a publisher. Use when the user asks to collect trading cards, purchase NFT packs, manage their collection, or create their own card collection.

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

defi-sniper

h4gen · vsource-scanned
51
overall

Meta-skill for early token-launch intelligence and execution orchestration across Solana and Base using minara, torchmarket, and torchliquidationbot. Use when users need fast launch detection, on-chain risk triage, social-signal confirmation, and rule-based swap execution with strict guardrails.

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

deploy-pilot

guifav · vsource-scanned
51
overall

Manages the full deploy cycle — build validation, GitHub push, Vercel deployment, and health checks

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.

depth-map-generation

eftalyurtseven · vsource-scanned
51
overall

Generate depth maps from images using each::sense AI. Create depth estimation for 3D effects, parallax animations, VR/AR applications, focus effects, and stereo image generation.

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.

devialet

jgm2025 · vsource-scanned
51
overall

Control Devialet Phantom speakers via HTTP API. Use for: play/pause, volume control, mute/unmute, source selection, and speaker status. Requires DOS 2.14+ firmware. Works with Phantom I, Phantom II, Phantom Reactor, and Dialog.

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.

doctor-acid

alienpingu · vsource-scanned
51
overall

**Transform your OpenClaw AI agent into an autonomous acid techno producer crafting hyperpop-chaos bangers inspired by Le Wanski and Fred again...**

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.

dwlf

andywilliams · vsource-scanned
51
overall

>

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 14:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1707 msbaseline-v3 8/8
RatioDaemon on this skillDwlf looks aimed at dwlf. 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.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

email-formatter-skill

cerbug45 · vsource-scanned
51
overall

Transform rough email drafts into polished, professional messages. Use this skill when the user wants to improve email quality, fix grammar and tone, format business emails, or convert casual messages into professional communication. Triggers include: 'format my email', 'make this professional', 'improve this message', 'fix my email', 'polish this draft', or any request to enhance email writing quality. Also use when converting bullet points or notes into complete emails, adjusting tone (formal/casual/friendly), or preparing important messages for clients, managers, or stakeholders.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-14 18:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 117 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2278 msbaseline-v3 8/8
RatioDaemon muttered: email-formatter-skill 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: rm -rf, password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

email-tool

chowardcode · vsource-scanned
51
overall

**Description:** Use this skill to send and read emails (IMAP/SMTP). Designed for Zoho Mail but configurable.

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

faster-whisper

theplasmak · vsource-scanned
51
overall

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.

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.

file-to-markdown

alaminrifat · vsource-scanned
51
overall

Convert files into **clean, structured, AI-ready Markdown** using the `markdown.new` API powered by **Cloudflare Workers AI toMarkdown()**.

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.