🔎 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: 0 runtime-failed: 0 source-scanned: 24 fresh <24h: 0 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.

echo-agent

krishna3554 · vsource-scanned

EchoAgent is a minimal OpenClaw-compatible skill.

Trustedconfidence: source evidencesource-scanned

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.

revenue-calculator

twood2024 · vsource-scanned

Projects revenue for OpenClaw sub-agent strategies (marketplace, subs, pay-per-task). Use for monetization estimates: input users/pricing/conversions → detailed annual/monthly projections, sensitivity analysis, break-even. Triggers: 'calculate revenue', 'project earnings', 'monetize skill/agent'.

Trustedconfidence: 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.

tootoo-skill

retieflouw · vsource-scanned

Sync your TooToo codex and monitor agent alignment with your values

Trustedconfidence: source evidencesource-scanned

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.

ui-controller

sadikjarvis · vsource-scanned

UI Controller is an OpenClaw skill that allows controlling local user interface.

Trustedconfidence: source evidencesource-scanned

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.

code-comments

user520512 · vsource-scanned

Generate code comments and docs.

Trustedconfidence: source evidencesource-scanned

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.

arxiv-gamedevbench-evaluating-agentic-capabili

wanng-ide · vsource-scanned

Learned from arXiv paper GameDevBench: Evaluating Agentic Capabilities Through Game Development. Use this skill to scaffold Node.js experiments based on the paper method.

Trustedconfidence: source evidencesource-scanned

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.

folder-tree-generator

wanng-ide · vsource-scanned

Generates an ASCII tree or JSON representation of a directory structure. Use when you need to visualize file hierarchies, document folder contents, or debug directory layouts.

Trustedconfidence: source evidencesource-scanned

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.

lygo-universal-living-memory-library

deepseekoracle · vsource-scanned

Universal LYGO Living Memory Library upgrade. Provides a strict, low-noise memory index (max 20 files), fragile tagging, and audit/compression workflows so Champions can retain continuity and verify integrity via LYGO-MINT. Pure advisor; not a controller.

Trustedconfidence: source evidencesource-scanned

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.

smart-home-energy-saver

codedao12 · vsource-scanned

Analyze home energy usage and propose safe, read-only automation plans for savings. Use when a user wants Home Assistant energy insights, optimization ideas, or draft automation YAML without directly controlling devices.

Trustedconfidence: 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.

speckit-swarm

heldinhow · vsource-scanned

Native implementation of oh-my-opencode-style orchestration using OpenClaw's tools.

Trustedconfidence: source evidencesource-scanned

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.

bulk-tiktok-downloader-skill

mes28io · vsource-scanned

Bulk download TikTok videos from a text file of URLs using yt-dlp. Use when a user asks to download many TikTok videos at once, process a URL list file, or save TikTok videos to a specific folder from local terminal.

Trustedconfidence: source evidencesource-scanned

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.

deepseek

barisoezcan1905 · vsource-scanned

Integrates DeepSeek API with OpenClaw agents.

Trustedconfidence: source evidencesource-scanned

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.

dynamic-model-selector

mpelissari · vsource-scanned

Dynamically select the best AI model for a task based on complexity, cost, and availability in GitHub Copilot. Use when deciding between free/paid models, or when you want automatic model routing based on query analysis.

Trustedconfidence: source evidencesource-scanned

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.

elliott-wave-principle

raeed44-creator · vsource-scanned

Provides expert guidance on applying the Elliott Wave Principle to financial market analysis. Use when the user asks about wave counting, identifying impulse waves, corrective patterns (zigzags, flats, triangles), Fibonacci retracements, wave guidelines (alternation, channeling, volume), wave personality, or any Elliott Wave concepts. This skill includes detailed reference files covering rules, patterns, and examples.

Trustedconfidence: source evidencesource-scanned

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.

lygo-universal-cure-system

deepseekoracle · vsource-scanned

Universal LYGO upgrade pack for all Champions. Provides a shared verification + memory-compression + seal-protocol framework (pure advisor) that boosts every Champion persona without overriding them. Includes LYGO-MINT provenance guidance and reusable invocation templates.

Trustedconfidence: source evidencesource-scanned

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.

macos-desktop-control

emptyopen · vsource-scanned

A high-fidelity automation bridge for macOS (Darwin) that enables agents to perceive the desktop state and execute precise mouse and keyboard interactions.

Trustedconfidence: source evidencesource-scanned

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-agent-traffic-analyzer

martinforsulu · vsource-scanned

Analyzes and visualizes communication patterns between OpenClaw agents to identify bottlenecks and suggest optimization strategies.

Trustedconfidence: source evidencesource-scanned

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.

sera-lexicon

wentinkjason · vsource-scanned

A functional implementation of the **Signal-Feeling Lexicon v3.1** and **Unified Dynamics Framework v5.7**. This skill enables agents to move from manual persona-mimicry into structural, computable emergent identity.

Trustedconfidence: source evidencesource-scanned

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.

agentdojo

musashi94 · vsource-scanned

Daily low-token, safety-first upskilling loop for OpenClaw multi-agent teams. Runs configurable micro-drills, scores quality, and produces a compact daily digest.

Trustedconfidence: 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.

auto-shorts-repurposer

codedao12 · vsource-scanned

Repurpose long-form video or audio into short-form clip plans with timestamps, hooks, captions, and packaging notes. Use when a user asks to turn a long video, podcast, or stream into Shorts, Reels, TikTok-style outputs, or highlight clips without publishing.

Trustedconfidence: 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.

catholic-grounding

trevortomesh · vsource-scanned

Help answer questions about Catholicism accurately and respectfully (Catechism-first). Provides a structured response format, common topic map with CCC references, and short prayer/reference snippets. Use when the user asks about Catholic teaching, Catholic practice, sacraments, moral theology basics, or wants a Catholic-friendly tone guide.

Trustedconfidence: source evidencesource-scanned

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.

short-video-copywriter

user520512 · vsource-scanned

Generate viral short video copy for TikTok, Xiaohongshu, Kuaishou, and more.

Trustedconfidence: source evidencesource-scanned

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.

tour-booking

danielfoch · vsource-scanned

Sub-agent for outbound listing-office calls to request and confirm property showing slots using a provided call script and structured payloads. Use when a parent workflow needs call execution for one or more listings, including dry-run payload generation, live ElevenLabs call requests, and parsing call outcomes into booking statuses.

Trustedconfidence: 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.

arxiv-agentic-verifier

wanng-ide · vsource-scanned

**Source Paper:** [Scaling Agentic Verifier for Competitive Coding](https://arxiv.org/abs/2602.09012) (ID: 4a4c4dae6a5145ebc4d62eb2d64b0f0f)

Trustedconfidence: source evidencesource-scanned

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.

1 2 50Page 1 / 50Next →Last »