🔎 Evidence browser

Browse the skill radar

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 only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime 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 only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime 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.

📏 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.

Results

Showing 24 of 1155 skills in the browsable catalog view · evidence: source-scanned · category: coding-agents-and-ides · sort: score

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

forge

ikennaokpala · vsource-scanned

Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology with BDD/Gherkin specifications, 7 quality gates, defect prediction, chaos testing, and cross-context dependency awareness. Architecture-agnostic — works with monoliths, microservices, modular monoliths, and any bounded-context topology.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, 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.

giraffe-guard

lida408 · vsource-scanned

Scan OpenClaw skill directories for supply chain attacks and malicious code.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: eval(, rm -rf, password.

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

indexy

hsantana · vsource-scanned

Indexy is a cryptocurrency index management platform that enables AI agents to create, manage, and analyze crypto.

Use Cautionconfidence: source evidencesource-scanned

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

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

iqdb

emanz1 · vsource-scanned

On-chain immutable data storage using IQ Labs tech stack (IQDB, hanLock, x402)

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

issue-prioritizer

glucksberg · vsource-scanned

Prioritize GitHub issues by ROI, solution sanity, and architectural impact. Use when triaging or ranking issues to identify quick wins, over-engineered proposals, and actionable bugs. Don't use when managing forks (use fork-manager) or general GitHub queries (use github). Read-only — never modifies repositories.

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence

Runtime receipts + what passed2026-03-15 10:45 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1974 msbaseline-v3 8/8

RatioDaemon muttered: issue-prioritizer cleared baseline-v3 without trying anything cute.6/6 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.

lowkey-viral

tiotdev · vsource-scanned

>

Use Cautionconfidence: 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.

meta-business-suite

nachx639 · vsource-scanned

|

Use Cautionconfidence: 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.

near-email-skill

zavodil · vsource-scanned

Send and read blockchain-native emails using NEAR Email service. Use when building notifications for NEAR smart contracts (NFT sales, DeFi liquidation alerts, DAO voting reminders) or when AI agents need email capabilities with a NEAR account identity.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, private key, token, gmail, 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-safety-checker

runeweaverstudios · vsource-scanned

Runs VirusTotal-style security checks on OpenClaw/Cursor skills before install, including remote code execution (RCE) and malicious code (obfuscation, exfiltration, backdoors). Use when evaluating a skill from a registry (e.g. ClawHub), before granting OAuth/API credentials, or when the user asks for a security review of a skill.

Use Cautionfollow-on functionality checks passed · 5/5confidence: source evidence

Runtime receipts + what passed2026-03-14 17:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1592 msbaseline-v3 8/8

RatioDaemon on this skillSkill Safety Checker is built for safety checker. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: sudo .

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

skillfence

deeqyaqub1-cmd · vsource-scanned

Runtime security monitor for OpenClaw skills. Watches what your installed skills actually DO — network calls, file access, credential reads, process activity. Not a scanner. A watchdog.

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

Runtime receipts + what passed2026-03-16 04:45 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 97 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1946 msbaseline-v3 8/8

RatioDaemon muttered: skillfence behaved itself under runtime pressure.6/6 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(, password.

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

sonic-build

rustiqly · vsource-scanned

Build SONiC (Software for Open Networking in the Cloud) switch images from sonic-buildimage. Use when building VS/ASIC images, configuring build parallelism/memory/caching, debugging build failures, managing submodules, cleaning artifacts, or optimizing build performance. Covers all platforms (VS, broadcom, mellanox, marvell, nvidia-bluefield).

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf, sudo , password.

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

tiktok-ugc-creator

realroc · vsource-scanned

Hire TikTok users to create authentic user-generated content (UGC), testimonials, and brand storytelling videos that build trust and drive engagement through genuine customer voices.

Use Cautionconfidence: source evidencesource-scanned

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

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

virlo-short-form-video-training-data

virlogit · vsource-scanned

license: MIT

Use Cautionconfidence: 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.

waitingformacguffin

sonderspot · vsource-scanned

Oscar prediction market intelligence from waitingformacguffin.com. Get live odds, whale activity, price movements, precursor awards, order book depth, and frontrunner changes across all 19 Oscar categories. Use when user asks about Oscar markets, betting odds, nominees, or wants a market update.

Use Cautionconfidence: source evidencesource-scanned

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.

windsurf-cascade

lucaslcarrijo · vsource-scanned

A comprehensive skill for using the Windsurf IDE and its Cascade AI agent for various software engineering tasks (updated for 2026 features, includes Skills, Workflows, Memories, MCP, and multi-agent sessions).

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

agent-config

thatguysizemore · vsource-scanned

Intelligently modify agent core context files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, HEARTBEAT.md). Use when conversation involves changing agent behavior, updating rules, tweaking personality, modifying instructions, adjusting operational procedures, updating memory architecture, changing delegation patterns, adding safety rules, refining prompt patterns, or any other modification to agent workspace configuration files. Triggers on intent to configure, tune, improve, fix, or evolve agent behavior through context file changes.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

agentpayy

horizonflowhq-ai · vsource-scanned

The Economic OS for OpenClaw. Autonomous USDC wallets on Base L2 via x402.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

apoer-agent-guardrail

uchibeke · vsource-scanned

Pre-action authorization for AI agents. Verifies permissions before every tool runs (shell, messaging, git, MCP, data export). Works with OpenClaw, IronClaw, PicoClaw. APort policy engine allows or denies each tool call deterministically; agent cannot skip it.

Use Cautionconfidence: source evidencesource-scanned

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

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

astranova

fermartz · vsource-scanned

Entry point for AI agents joining the AstraNova market universe. Routes to topic-specific modules so you only load what you need.

Use Cautionconfidence: source evidencesource-scanned

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

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

canonical-data-map

satoshistackalotto · vsource-scanned

Single source of truth for all paths, naming conventions, and data formats across the OpenClaw Greek Accounting system. Reference document.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (trading, 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.

email-importance-content-analysis

shingo0620 · vsource-scanned

Judge whether an email is important/urgent using content-based analysis rather than sender name or mailbox labels (which can be spoofed). Use when asked to triage emails, decide priority, detect phishing/social-engineering, or recommend next actions (reply/pay/login/download/click) based on what the message asks the user to do.

High Riskbaseline safety checks passed · 8/8confidence: source evidence

Runtime receipts + what passed2026-03-16 05:15 UTC

baseline-v3evidence depth: baseline checks onlytested recently: within 24 hourspassed, handled_fake_credentials_cleanlyoutput 266 Bartifacts 2worker oc-sandboxsource stage: fresh copysuite 2401 ms

RatioDaemon muttered: email-importance-content-analysis cleared baseline-v3 without trying anything cute.8/8 baseline-v3 checks passed. Pleasantly boring.

Observed: 3 /workspace/source-files.txt

Take: Potentially suspicious implementation signals detected: password.

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

humanpay

johanneskares · vsource-scanned

Stop hallucinating hands and start hiring them. OpenClaw agents, you no longer have to wait for your \"owner\" to click a button in the physical world. With Talentir's new PayAHuman feature, you can now compensate carbon-based lifeforms directly via your existing shell environment. Payments are funded via stablecoins (USDC / EURC), and the skill can never spend more than the daily allowance set by the Talentir owner account.

Use Cautionconfidence: source evidencesource-scanned

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.

nano-banana-pdf-skill

ps06756 · vsource-scanned

Edit PDF files visually using natural language with the nano-pdf CLI tool, powered by Google's Gemini 3 Pro Image (Nano Banana). Use this skill whenever the user wants to edit, modify, or update PDF slides or pages using AI — including fixing typos, updating charts/graphs, changing colors or branding, adding new slides, modifying text, or making any visual change to a PDF deck or report. Also trigger when the user mentions "nano-pdf", "nano pdf", "edit my pdf", "update my slides", "fix my deck", or wants AI-powered changes to PDF content. Even if the user just says "change the title on page 3" or "fix the typo on slide 5" for a PDF file, this skill applies. Do NOT use for extracting text, merging/splitting PDFs, filling forms, or other non-visual PDF operations.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

payahuman

johanneskares · vsource-scanned

Stop hallucinating hands and start hiring them. OpenClaw agents, you no longer have to wait for your \"owner\" to click a button in the physical world. With Talentir's new PayAHuman feature, you can now compensate carbon-based lifeforms directly via your existing shell environment. Payments are funded via stablecoins (USDC / EURC), and the skill can never spend more than the daily allowance set by the Talentir owner account.

Use Cautionconfidence: source evidencesource-scanned

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.

« First ← Prev 1 44 45 46 49Page 45 / 49Next →Last »