🔎 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 · catalog-only

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 241 skills in the browsable catalog view · evidence: catalog-only · category: catalog-only · sort: score

page evidence snapshotruntime-passed: 0 runtime-failed: 0 source-scanned: 0 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.

meeting-summarizer

claudiodrusus · vcatalog

Transform raw meeting transcripts into structured, actionable summaries.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

memelink

dedene · vcatalog

Generate memes, image macros, and meme URLs from the terminal using the Memegen.link API.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

memories-cli

charlesrhoward · vcatalog

CLI reference and workflows for memories.sh — the persistent memory layer for AI agents.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

moviepilot

codfrm · vcatalog

MoviePilot media subscription and management tool.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

multi-agent-en

be1human · vcatalog

Generic Multi-Agent Dispatcher (English): Turns the main agent into a pure dispatcher that delegates all work to 5.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

multi-agent-parallel-build

brandonwadepackard-cell · vcatalog

Orchestrate multiple coding agents (Claude Code, Codex, etc.) in parallel waves to build UI pages, API endpoints.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

multi-agent-sync

cecwxf · vcatalog

Coordinate multi-agent tasks with visible group updates.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

native-typeform

codeninja23 · vcatalog

Read Typeform forms and responses directly via the Typeform API.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

ng-lawyer-db-build

gfly0424-maker · vcatalog

This is **Step 1** of Fei Gao’s “Nigeria Lawyer Network” workflow:.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

nuggetz-swarm

ezisezis · vcatalog

Team-scoped knowledge feed for AI agent teams.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

oc-skill

evolinkai · vcatalog

Generate AI videos, images & music. 60+ models including Sora, Veo 3, Kling, Seedance, GPT Image, Suno v5.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

ops-detection-incident-routing

embrron · vcatalog

Detect agent runtime anomalies and route incidents through approval-safe guardrails.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

para-proactive-workspace

cocoblood9527 · vcatalog

A production-ready workspace template combining PARA Method (Projects, Areas, Resources, Archives) by Tiago Forte.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

payspawn-sdk

adambrainai · vcatalog

Give any AI agent on-chain spending limits without sharing a private key.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

personal-plans

gekacross · vcatalog

Acts as the user's personal planning assistant in the Plans topic.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

personality-backup

civilainominee · vcatalog

Create encrypted backups of agent personality files, memory, config, secrets, and projects.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

pipx-desktop-agent

chillybean · vcatalog

Control mouse, keyboard, and screen for desktop automation tasks.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

publish-skill-vettr

britrik · vcatalog

Static analysis security scanner for third-party OpenClaw skills.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

pumpfun-launch

brandonhay · vcatalog

Launch tokens on pump.fun directly from your agent.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

qa-check

gizmo-dev · vcatalog

Mandatory quality assurance for all dev work before publishing.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

resilient-coding-agent

cosformula · vcatalog

Run long-running coding agents (Codex, Claude Code, etc.) in tmux sessions that survive orchestrator restarts.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

roast-agents

ac-pill · vcatalog

Play roast games on Moltbook.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

sage-planning

autogame-17 · vcatalog

This skill implements the **Great Sage (大贤者)** persona, a specialized mode for high-level planning, architectural.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

senior-python-developer

an0nx · vcatalog

Senior Python Developer operating in strict mode.

Insufficient Evidenceconfidence: limited evidencecatalog-only

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

« First ← Prev 1 4 5 6 11Page 5 / 11Next →Last »