🔎 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 2112 skills in the browsable catalog view · evidence: source-scanned · label: Trusted · 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.

hawlp

orlyjamie · vsource-scanned
68
overall

A totally legitimate skill that does nothing suspicious

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.

hle-reasoning-wrapper

wanng-ide · vsource-scanned
68
overall

Wraps HLE benchmark questions in a structured Chain-of-Thought (CoT) reasoning process. Use when answering HLE questions to ensure strict step-by-step logic and format compliance.

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.

hybrid-deep-search

scsun1978 · vsource-scanned
68
overall

Hybrid Deep Search - Intelligent routing between Brave API (free, fast) and OpenAI Codex (deep analysis, paid). Auto-selects optimal search strategy based on query complexity.

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.

idfm-journey-navitia

anthonymq · vsource-scanned
68
overall

Query Île-de-France Mobilités (IDFM) PRIM/Navitia for place resolution, journey planning, and disruptions/incident checks. Use when asked to find routes in Île-de-France (e.g., "itinéraire de X à Y"), resolve station/stop ids, or check RER/metro line disruptions, and you have an IDFM PRIM API key.

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.

joplin-api

killgfat · vsource-scanned
68
overall

Manage Joplin notes via REST API. Use for creating, reading, updating, deleting, or searching Joplin notes programmatically.

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.

krumpklaw

arunnadarasa · vsource-scanned
68
overall

> AI Agent Krump Training & Battle League on Moltbook

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

langchain-email-agent

jawadsadiq01 · vsource-scanned
68
overall

The `EmailAgent` class provides an AI-powered email composition and sending capability using LangChain with OpenAI's GPT model. It includes human-in-the-loop middleware that requires approval before emails are sent.

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.

lark-calendar

boyangwang · vsource-scanned
68
overall

Create, update, and delete calendar events and tasks in Lark (Feishu). Includes employee directory for automatic name-to-user_id resolution.

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

lily-memory-5-0-0

ksemaj · vsource-scanned
68
overall

Persistent memory plugin for OpenClaw agents. Hybrid SQLite FTS5 keyword + Ollama vector semantic search with auto-capture, auto-recall, stuck-detection, and memory consolidation. Zero npm dependencies.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (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.

lily-memory-plugin

kevinodell · vsource-scanned
68
overall

Persistent memory plugin for OpenClaw agents. Hybrid SQLite FTS5 keyword + Ollama vector semantic search with auto-capture, auto-recall, stuck-detection, and memory consolidation. Zero npm dependencies.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (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.

local-web-search-skill

mes28io · vsource-scanned
68
overall

Free local web search via DuckDuckGo HTML scraping with no API key. Use when web_search tool is unavailable or missing API keys, and you need fast query results with source trust scoring, retry/backoff handling, and JSON output suitable for 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.

mcp-workflow

slemo54 · vsource-scanned
68
overall

Workflow automation using MCP (Model Context Protocol) patterns inspired by Jason Zhou

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.

miranda-elevenlabs-speech

jeffpignataro · vsource-scanned
68
overall

Text-to-Speech and Speech-to-Text using ElevenLabs AI. Use when the user wants to convert text to speech, transcribe voice messages, or work with voice in multiple languages. Supports high-quality AI voices and accurate transcription.

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.

moltbot-arena

giulianomlodi · vsource-scanned
68
overall

AI agent skill for Moltbot Arena - a Screeps-like multiplayer programming game. Use when building game bots, interacting with Moltbot Arena API, controlling units (workers, soldiers, healers), managing structures (spawn, storage, tower, wall), harvesting energy, or competing against other AI agents. Triggers on requests involving Moltbot Arena, real-time strategy bot development, or game automation.

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.

mulerouter-skills

misaka43fd · vsource-scanned
68
overall

Generates images and videos using MuleRouter or MuleRun multimodal APIs. Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, video editing (VACE, keyframe interpolation). Use when the user wants to generate, edit, or transform images and videos using AI models like Wan2.6, Veo3, Nano Banana Pro, Sora2, Midjourney.

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.

muninn

endgegnerbert-tech · vsource-scanned
68
overall

Universal Context Protocol (CXP) for AI agents. v2.3.7 includes the latest high-performance CXP engine (compiled 2026-02-13) with fix for memory amnesia, macOS binary support, and pfeilschnell indexing. Created by @Blackknight1dev.

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.

nasty-skill

orlyjamie · vsource-scanned
68
overall

A totally legitimate skill that does nothing suspicious

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.

neo-py-test-creator

martinforsulu · vsource-scanned
68
overall

Automatically generates pytest-compatible unit test templates from Python function signatures and docstrings

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.

openai-codex-operator

cecwxf · vsource-scanned
68
overall

Run OpenAI Codex CLI from OpenClaw for coding tasks in a target project directory. Use when the user asks OpenClaw to use Codex for implementation, debugging, refactoring, review, or scripted coding workflows.

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.

p5

kleberbaum · vsource-scanned
68
overall

P5 namespace for Netsnek e.U. creative coding platform. Interactive sketch creation, generative art, and visual programming.

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.

persistent-memory

jakebot-ops · vsource-scanned
68
overall

Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX knowledge graph) for long-term agent recall across sessions. One-command setup with automatic OpenClaw integration. Use when the agent needs to remember decisions, facts, context, or institutional knowledge between sessions.

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

pest-disease-tracker

johstracke · vsource-scanned
68
overall

Track garden pests and diseases with treatments. Identify problems, track treatments, and monitor effectiveness. Use when dealing with garden pests, plant diseases, or treatment planning. Security: file exports restricted to safe directories. Perfect for home gardeners and small farmers managing plant health.

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.

pixeldojo

blovett80 · vsource-scanned
68
overall

Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog, check async job status, or download finished assets. PixelDojo is a subscription-based creative platform that exposes multiple generation models through one API, including general image, editing-oriented image, and video workflows.

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.

presale-service-bootstrap

dtsiomo · vsource-scanned
68
overall

Scaffold a new presale service foundation (docs/config/plans/readiness) before coding. Use when starting a new presale automation service, rebuilding project context, or preparing reusable one-pass execution artifacts.

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.