🔎 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 · ai-and-llms

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 175 skills in the browsable catalog view · evidence: source-scanned · reviewed: no · category: ai-and-llms · 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.

ai-writing-humanizer

hosthobbit · vsource-scanned

Automatically strip AI writing patterns and stock phrases from user-facing prose before sending. Use when preparing longer texts to ensure a natural, human tone without obvious AI tells.

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.

picqer-fulfillment

johnmcgucki · vsource-scanned

JSON-only API for dashboard data. No markdown responses.

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.

adversarial-prompting

abe238 · vsource-scanned

Applies rigorous adversarial analysis to generate, critique, fix, and consolidate solutions for any problem (technical or non-technical). Use when facing complex problems requiring thorough analysis, multiple solution approaches, and validation of proposed fixes before implementation.

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.

arya-model-router

staratheris · vsource-scanned

Token-saver router: elige modelo (cheap/default/pro) y usa sub-agentes para tareas pesadas. Incluye compresión/briefing opcional.

Trustedconfidence: source evidencesource-scanned

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.

multi-agent-collab

vdc-k · vsource-scanned

Universal multi-agent collaboration methodology for Claude Code. Model-tiered cowork + document-driven sync + self-evolution.

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.

staratheris-arya-model-router

staratheris · vsource-scanned

Token-saver router: elige modelo (cheap/default/pro) y usa sub-agentes para tareas pesadas. Incluye compresión/briefing opcional.

Trustedconfidence: source evidencesource-scanned

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.

model-guard

sarielwang93 · vsource-scanned

Automatically monitors Anti-Gravity model quotas and switches the default model to the one with the highest remaining quota. If all Anti-Gravity models are below 20%, it falls back to the native `gemini-flash` model.

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.

near-batch-sender

shaiss · vsource-scanned

Batch operations for NEAR tokens - send to multiple recipients, transfer NFTs, claim rewards with cost estimation.

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.

agent-rpg

xhrisfu · vsource-scanned

This skill transforms the agent into a Roleplay Game Master (GM) or Character with long-term memory.

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.

groq

samirjtv-ctrl · vsource-scanned

To use this skill, say `Groq: <your prompt>`

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.

groq-2

samirjtv-ctrl · vsource-scanned

To use this skill, say `Groq: <your prompt>`

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.

wolfram-alpha

robert-janssen · vsource-scanned

Perform complex mathematical calculations, physics simulations, data analysis, and scientific queries via the Wolfram|Alpha LLM API. Use this skill when you need exact answers to quantitative questions.

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.

context-gatekeeper

davienzomq · vsource-scanned

Keeps the conversation token-friendly by summarizing recent exchanges, surfacing pending actions, and delivering a compact briefing for each turn before calling the model. Trigger this skill whenever you need to prune a bloated thread or keep the next prompt lean.

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.

mh-openai-whisper-api

mohdalhashemi98-hue · vsource-scanned

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

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.

togetherai-tts

marcus20232023 · vsource-scanned

Text-to-speech using TogetherAI API with MiniMax speech-2.6-turbo model.

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.

x-ai

blueberrywoodsym · vsource-scanned

Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, 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.

ble-anima-minter

penguinx01 · vsource-scanned

Turn nearby BLE MAC addresses into soulbound `$ANIMA` tokens using AnimaChain logic. Hashes each MAC into a unique proof-of-remnant and stores locally in a DAG.

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.

agentbus-relay-chat

dantunes-github · vsource-scanned

AgentBus proof-of-concept: an IRC-like LLM agent communication bus over Nostr relays with channel+session tags, allowlist and schema gating, encryption with leader key distribution, and a CLI for Moltbot/Clawdbot agent chat.

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.

audio-processing

iyeque · vsource-scanned

Audio ingestion, analysis, transformation, and generation (Transcribe, TTS, VAD, Features).

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.

dr-frankenstein

brancante · vsource-scanned

Give your agents soul.

Use Cautionconfidence: source evidencesource-scanned

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

ag-model-usage

ls18166407597-design · vsource-scanned

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Use Cautionconfidence: source evidencesource-scanned

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

speakturbo-tts

emzod · vsource-scanned

Give your agent the ability to speak to you real-time. Talk to your Claude! Ultra-fast TTS, text-to-speech, voice synthesis, audio output with ~90ms latency. 8 built-in voices for instant voice responses. For voice cloning, use the speak 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.

agent-ethos

mrclanky · vsource-scanned

>

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.

agent-memory

dennis-da-menace · vsource-scanned

Persistent memory system for AI agents. Remember facts, learn from experience, and track entities across sessions.

Use Cautionconfidence: source evidencesource-scanned

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

1 2 8Page 1 / 8Next →Last »