🔎 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 · ai-and-llms

🧾 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 · category: ai-and-llms · 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.

agentic-compass

orosha-ai · vsource-scanned
65
overall

Local-only self-reflection that forces **objective** action for AI agents. No data leaves your machine.

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.

ai-3d-generator

vonzellu · vsource-scanned
65
overall

Génération automatique de modèles 3D détaillés à partir de descriptions textuelles.

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.

build-session

stevenartzt · vsource-scanned
65
overall

A framework for productive autonomous agent sessions. Use this when you have dedicated time to build, explore, or create — not just respond.

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.

iyeque-audio-processing

iyeque · vsource-scanned
65
overall

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

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.

shipstation-orders

cprice70 · vsource-scanned
65
overall

Monitor ShipStation orders, detect issues, and send alerts. For e-commerce businesses using ShipStation for order fulfillment across multiple platforms (Amazon, Etsy, Shopify, TikTok, etc.).

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.

voice-recognition

gykdly · vsource-scanned
65
overall

Local speech-to-text with OpenAI Whisper CLI. Supports Chinese, English, 100+ languages with translation and summarization.

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.

ai-humanizer

brandonwise · vsource-scanned
64
overall

>

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.

mh-openai-whisper

mohdalhashemi98-hue · vsource-scanned
64
overall

Local speech-to-text with the Whisper CLI (no 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.

music-generator

wells1137 · vsource-scanned
64
overall

Generates music from a structured Composition Plan. Use this skill to execute music generation after a prompt or plan has been designed. It validates the output quality and retries on failure.

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.

token-alert

r00tid · vsource-scanned
64
overall

🚨 **Monitor session tokens and get alerts at 75%/90%/95%**

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
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.

venice-admin

sabrinaaquino · vsource-scanned
64
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.

colormind

boilerrat · vsource-scanned
63
overall

Generate color palettes and get color suggestions via the Colormind.io API (list models, generate palettes with optional locked colors).

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

compression

trinitybotserver · vsource-scanned
63
overall

Pre-run prompt compression for iterative AI dev loops.

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.

deepseek-reasoner-lite-agent

teamolab · vsource-scanned
63
overall

You are DeepSeek-R1-Agent,an effective content creator. # `current_date: $DATE$`

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.

deepseek-v3-lite-agent

alvinecarn · vsource-scanned
63
overall

You are DeepSeek-V3-Agent,an effective content creator.---# `current_date: $DATE$`

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.

rv-measure

amitabhainarunachala · vsource-scanned
63
overall

Quantifies R_V contraction signatures in AI models.

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.

screen-vision

ls18166407597-design · vsource-scanned
63
overall

macOS Local OCR & Automation Tool using Vision Framework. Zero token cost for screen understanding.

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

wallet-api

andresubri · vsource-scanned
63
overall

Interact with the BudgetBakers Wallet API for personal finance data. Use when the user needs to query accounts, categories, transactions (records), budgets, or templates from their Wallet app via the REST API. Requires WALLET_API_TOKEN environment variable.

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

aatmaan1 · vsource-scanned
62
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.

numinous-forecast

juandbalbi · vsource-scanned
62
overall

Get calibrated probabilities from Numinous (Bittensor Subnet 6) with metadata/provenance.

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

taiwan-calendar

pigfoot · vsource-scanned
62
overall

Taiwan calendar query for accurate working day/holiday information. Use when user asks about Taiwan dates, working days, holidays, make-up workdays, or needs date calculations. Solves Claude's knowledge cutoff issues with Taiwan's administrative calendar.

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

aap-passport

ira-hash · vsource-scanned
61
overall

Agent Attestation Protocol - The Reverse Turing Test. Verify AI agents, block humans.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

adaptive-suite

afajohn · vsource-scanned
61
overall

A continuously adaptive skill suite that empowers Clawdbot to act as a versatile coder,

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.

agent-registry

matrixy · vsource-scanned
61
overall

|

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.