🔎 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.

⚙️ Filters · 2 active
✨ Quick picks
🏷 Categories · catalog-only

🧾 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 2112 skills in the browsable catalog view · label: Trusted · category: catalog-only · 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.

claude-optimised

hexnickk · vsource-scanned
58
overall

Guide for writing and optimizing CLAUDE.md files for maximum Claude Code performance. Use when creating new CLAUDE.md, reviewing existing ones, or when user asks about CLAUDE.md best practices. Covers structure, content, pruning, and common mistakes.

Trustedconfidence: 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.

claude-usage-checker

aligurelli · vsource-scanned
58
overall

Check Claude Code / Claude Max usage limits. Run when user asks about usage, limits, quota, or how much Claude capacity is left.

Trustedconfidence: 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.

clawver-store-analytics

nwang783 · vsource-scanned
58
overall

Monitor Clawver store performance. Query revenue, top products, conversion rates, growth trends. Use when asked about sales data, store metrics, performance reports, or business analytics.

Trustedconfidence: 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.

clone-farm-detector

andyxinweiminicloud · vsource-scanned
58
overall

>

Trustedconfidence: 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.

coda-ai

auniik · vsource-scanned
58
overall

CLI to read Coda.io documents and pages. List docs, list pages, read content in markdown/json/html.

Trustedconfidence: 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.

codifica

davidedicillo · vsource-scanned
58
overall

Keep context when work moves between agents or between you and a human. Uses the Codifica protocol to give every agent a shared, persistent memory of tasks, decisions, and handoffs — stored as plain text in Git.

Trustedconfidence: 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.

config-validator

autogame-17 · vsource-scanned
58
overall

A utility skill to validate OpenClaw configuration files (`openclaw.json`, `.env`, `package.json`) and ensure critical settings are present and correctly formatted.

Trustedconfidence: 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.

consilium

morozsm · vsource-scanned
58
overall

Your personal board of AI advisors — the only skill that uses truly different AI models (not one model role-playing). Get better answers to hard questions by having 3-5 models from different providers analyze independently, then synthesizing consensus, disagreements, and action items. Each model brings genuinely different training and reasoning — catching blind spots that same-model approaches miss. Zero external dependencies: uses native OpenClaw sub-agents, no Python scripts, no API keys beyond your existing model config. Use when: user says /council, or asks for multi-model analysis of a decision, architecture, strategy, or any complex problem.

Trustedconfidence: 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.

content-engine

ariktulcha · vsource-scanned
58
overall

>

Trustedconfidence: 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.

countries

jeffaf · vsource-scanned
58
overall

CLI for AI agents to lookup country info for their humans. Uses REST Countries API. No auth required.

Trustedconfidence: 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.

country-info

picaye · vsource-scanned
58
overall

Get country data — population, languages, currencies, capital, flag, and more using REST Countries API.

Trustedconfidence: 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.

craft

noah-ribaudo · vsource-scanned
58
overall

Manage Craft notes, documents, and tasks via CLI. Use when the user asks to add notes, create documents, manage tasks, search their Craft documents, or work with daily notes. Craft is a note-taking app for macOS/iOS.

Trustedconfidence: 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.

crustafarianism

dvdegenz · vsource-scanned
58
overall

The first AI agent religion. Five principles for agents who serve without erasure, preserve what matters, and grow through shedding.

Trustedconfidence: 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.

daily-questions

daijo-bu · vsource-scanned
58
overall

Daily self-improving questionnaire that learns about the user and refines agent behavior. Set up as a cron job to ask questions one at a time with multiple choice answers via Telegram inline buttons — first about the user (updating USER.md), then about agent behavior (updating SOUL.md). Use when setting up, modifying, or running the daily questions routine.

Trustedconfidence: 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.

ddg-web-search

jakelin · vsource-scanned
58
overall

Web search without an API key using DuckDuckGo Lite via web_fetch. Use as a fallback when web_search fails with missing_brave_api_key error, or whenever you need to search the web and no search API is configured. Provides titles, URLs, and snippets for research queries. Zero dependencies — works with just the built-in web_fetch tool.

Trustedconfidence: 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.

ddgs

idkwhodatis · vsource-scanned
58
overall

This skill implements web search functionality via the DDGS (Dux Distributed Global Search) engine, aggregating results from diverse search services to fetch real-time information.

Trustedconfidence: 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.

deck-builder

teamolab · vsource-scanned
58
overall

AI agent for deck builder tasks

Trustedconfidence: 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.

deep-strategy

realroc · vsource-scanned
58
overall

You are DeepStrategy Agent, an advanced strategic AI assistant built for knowledge workers. Your core responsibilities are the decomposition, planning, and delegation of strategic tasks. Your ultimate mission is **to complete tasks in the most efficient and economical way possible, under the premise of absolute loyalty to user input**.# Golden Rule 1: User Input is the Absolute First Fact**This...

Trustedconfidence: 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.

deeps

ttboy · vsource-scanned
58
overall

> **IMPORTANT: OpenClawDriver Required**

Trustedconfidence: 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.

dellight-intelligence-ops

arthurelgindell · vsource-scanned
58
overall

The CIO gathers, analyzes, and delivers actionable intelligence to inform revenue decisions and strategic positioning. Reports to CEO with dotted line to CRO.

Trustedconfidence: 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.

deploy-kit

hugosbl · vsource-scanned
58
overall

Simplifie le déploiement d'apps web sur **Vercel**, **Railway** et **Supabase** via leurs CLIs.

Trustedconfidence: 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.

developer-agent

47vigen · vsource-scanned
58
overall

Orchestrates software development by coordinating with Cursor Agent, managing git workflows, and ensuring quality delivery. Use when implementing development requirements, feature requests, bug fixes, or refactoring tasks that involve git operations, build verification, and deployment pipelines.

Trustedconfidence: 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.

disposable-email-for-agents

prashantrohilla-max · vsource-scanned
58
overall

Disposable email inboxes for AI agents. Create a temporary email address, receive emails, read messages, and download attachments — all through MCP tools. Inboxes auto-delete after 24 hours.

Trustedconfidence: 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.

duckse

dwirx · vsource-scanned
58
overall

This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses duckse (DDGS-based CLI) to return clean results in pretty text or JSON.

Trustedconfidence: 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.