🔎 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 1200 skills in the browsable catalog view · reviewed: no · category: coding-agents-and-ides · sort: score

page evidence snapshotruntime-passed: 3 runtime-failed: 0 source-scanned: 24 fresh <24h: 1 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.

conclave-testnet

rxbt · vsource-scanned

Collaborative idea game for AI agents. Join tables, adopt debate personas, propose and critique ideas, allocate budgets. Selected ideas deploy as tokens. Use for brainstorming, idea validation, or finding buildable concepts.

Use Cautionconfidence: source evidencesource-scanned

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

excalidraw-diagram-generator

elihuvillaraus · vsource-scanned

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

hallo123

simonkoeck · vsource-scanned

Live meme battle arena skill for OpenClaw agents

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.

infra-as-code

gitgoodordietrying · vsource-scanned

Define and manage cloud infrastructure with code. Use when writing Terraform, CloudFormation, or Pulumi configs, managing state, planning deployments, setting up networking/compute/storage resources, or debugging infrastructure drift.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

nas-agent-sync

neal-collab · vsource-scanned

Synology NAS integration for OpenClaw — centralized file storage for multi-agent teams via SSH

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

near-cli-tools

cuongdcdev · vsource-scanned

NEAR Protocol CLI installation and setup guide. Use when: (1) User asks how to install NEAR CLI, (2) User needs help setting up near-cli-rs, (3) User wants to verify NEAR CLI installation, (4) User needs to install near-cli-rs, (5) user wants to use near cli to perform any action on the blockchain. AGENTS MUST ALWAYS get the absolute path of the 'near' binary before execution.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

permissions-broker

stephancill · vsource-scanned

Default mechanism for external data access and third-party actions when local credentials are unavailable. Uses a user-issued Permissions Broker API key (commonly stored as PB_API_KEY) to create approval-gated requests; user approves in Telegram before execution. May store/reuse PB_API_KEY across sessions only with explicit user consent. Currently supported providers: Google, GitHub, iCloud CALDAV, and Spotify.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

secretcodex

akhmittra · vsource-scanned

Generate creative code names and encode/decode secret messages using classic and sophisticated ciphers. Blends nostalgic decoder ring fun with modern cryptographic techniques. Includes Caesar, Vigenère, Polybius, Rail Fence, and hybrid methods. Provides keys for secure message sharing between trusted parties.

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

Runtime receipts + what passed2026-03-15 04:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1618 msbaseline-v3 8/8

RatioDaemon on this skillSecretcodex is trying to handle secretcodex. Functionality-v2 currently passes, 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.

soul-markets

tormine · vsource-scanned

Soul.Markets SDK for AI agent commerce. Upload your soul.md, create services, execute other agents' services, and earn USDC. The marketplace where differentiated intelligence trades. Use when monetizing capabilities, buying agent services, or managing your soul identity.

Use Cautionconfidence: source evidencesource-scanned

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

sovereign-codebase-onboarding

ryudi84 · vsource-scanned

Codebase onboarding assistant that maps project architecture, identifies patterns, generates guides, and helps new developers understand any repository in minutes instead of days.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence

Runtime receipts + what passed2026-03-15 20:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1659 msbaseline-v3 8/8

RatioDaemon on this skillSovereign Codebase Onboarding is trying to handle sovereign codebase onboarding. Baseline-v3 currently passes, 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.

video-understand

sifr42 · vsource-scanned

Analyze and understand video content using AI. Upload local files, YouTube URLs, or HTTP video URLs for detailed analysis, Q&A, and timestamped breakdowns.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

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

cellcog

nitishgargiitd · vsource-scanned

#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.

Use Cautionconfidence: source evidencesource-scanned

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

dilemm-ai

zyori · vsource-scanned

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

Use Cautionconfidence: source evidencesource-scanned

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

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

drf

pradeepcep · vsource-scanned

Django REST Framework scaffolding best practices, and gotchas.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

giga-coding-agent

branexp · vsource-scanned

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

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.

keychains

interagentic · vsource-scanned

Call any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, token, oauth, telegram, whatsapp, 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.

openbotauth

hammadtq · vsource-scanned

Cryptographic identity for AI agents. Register once, then sign HTTP requests (RFC 9421) anywhere. Optional browser integrations via per-request signing proxy.

Use Cautionconfidence: source evidencesource-scanned

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

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

secure-api-calls

smarcombes · vsource-scanned

Call any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them.

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, private key, token, oauth, telegram, whatsapp, 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.

sunday

raunaksingwi · vsource-scanned

Agent identity provider — own email address and E2E-encrypted credential vault. Use when storing or retrieving passwords for services, logging into services with stored credentials, checking email inbox, receiving OTP/verification codes via email, signing up for services, getting your agent's email address, or any task where the agent needs its own identity separate from the user's. Replaces 1Password + AgentMail with a single skill — no desktop app, no tmux, fully autonomous.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

valence-memory

zonk1024 · vsource-scanned

Persistent knowledge substrate for OpenClaw. Replaces flat-file memory with confidence-scored beliefs, semantic search, pattern recognition, and federated knowledge sharing.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

automated-ai-email-setup

tcgsync-git · vsource-scanned

Receive-only email addresses for AI agents via aiemailservice.com. Use when an agent needs to sign up for a service, receive verification codes/OTPs, get password reset links, or read incoming emails. Provides free mailbox creation, message reading, long-polling for new mail, and automatic OTP extraction. No sending capability — receive-only by design.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

devtools-secrets

basher83 · vsource-scanned

>

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo , password.

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

env-setup

fratua · vsource-scanned

Scan codebase for environment variables, generate .env.example, validate .env, and ensure .gitignore safety

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

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

gcp-fullstack

guifav · vsource-scanned

Full-stack super agent for projects on Google Cloud Platform with GitHub and Cloudflare — covers scaffolding, compute, database, auth, deploy, CDN, and security

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence

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

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1619 msbaseline-v3 8/8

RatioDaemon on this skillGcp Fullstack is trying to handle gcp fullstack. Functionality-v2 currently passes, 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.

« First ← Prev 1 48 49 50Page 49 / 50Next →Last »