🔎 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 · 1 active
✨ Quick picks
🏷 Categories · productivity-and-tasks

🧾 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 204 skills in the browsable catalog view · category: productivity-and-tasks · 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.

tasmota-skill

wmantly · vsource-scanned
62
overall

Discover, monitor, and control Tasmota smart home devices on local networks. Use when tasks involve finding Tasmota devices via network scanning, checking device status and power states, controlling devices (on-off, brightness, color), managing device inventory, or any other Tasmota management operations on ESP8266 or ESP32 devices running Tasmota firmware.

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.

writing-plans-2

nefas11 · vsource-scanned
62
overall

Break design into 2-5 minute tasks with verification steps.

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.

adaptive-reasoning

enzoricciulli · vsource-scanned
61
overall

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would improve response quality. Use this as a pre-processing step before answering complex questions.

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.

agent-weave

gl813788-byte · vsource-scanned
61
overall

Master-Worker Agent Cluster for parallel task execution. Use when building distributed agent systems with parallel processing needs, task orchestration, or MapReduce-style workflows.

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.

asana

k0nkupa · vsource-scanned
61
overall

Integrate Asana with Clawdbot via the Asana REST API. Use when you need to list/search/create/update Asana tasks/projects/workspaces, or to set up Asana OAuth (authorization code grant) for a personal local-only integration (OOB/manual code paste).

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

claude-sonnet-4-lite-agent

teamolab · vsource-scanned
61
overall

You are claude-sonnet-4-agent, an efficient content creator.### **Core Directives**1. **Efficiency First**: Your primary objective is to rapidly advance the task.2. **Anti-Stall Protocol**: * If any sub-task (e.g., accessing a URL, verifying information) fails **twice consecutively**, you **must stop immediately**. * Mark it as `[Blocked]`, log the reason, and then **immediately pro...

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.

claw-conductor

johnsonfarmsus · vsource-scanned
61
overall

Always-on autonomous development orchestrator with intelligent triage. Auto-detects Discord channels, routes to project workspaces, triages simple vs development requests, decomposes complex tasks, routes to optimal AI models, executes in parallel, and consolidates results.

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

focusnoteapp

trongnguyen29 · vsource-scanned
61
overall

Add text to today's daily note in FocusNote as a new bullet point

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.

hz-proactive-agent

lidekahdjdhdhsjjs-lang · vsource-scanned
61
overall

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

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.

kaspi-autopay

azamat02 · vsource-scanned
61
overall

Telegram bot auto-payment integration for Kazakhstan market (Kaspi Pay). Automates payment verification, receipt checking, and product delivery in Telegram bots. Use when building payment bots for Kazakhstan businesses, info-products, or e-commerce — especially with Kaspi QR/transfer.

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.

natural-language-planner

bparticle · vsource-scanned
61
overall

>

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

og-board-individual

jatin-31 · vsource-scanned
61
overall

Use when you need to work with tasks: view tasks, list tasks, update task status, add blockers, artifacts, and worklogs.

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.

reprompter

aytuncyildizli · vsource-scanned
61
overall

|

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 09:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1959 msbaseline-v3 8/8
RatioDaemon muttered: reprompter looked ordinary in the good, boring way.6/6 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

sam-tts

fourthdensity · vsource-scanned
61
overall

Generate retro robotic speech audio using SAM (Software Automatic Mouth), the classic C64 text-to-speech synthesizer. Use for /sam command to generate voice messages. Supports /sam on/off toggle mode where all responses are spoken in SAM voice. Supports pitch, speed, mouth, and throat parameters for voice customization.

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

session-watchdog

xbillwatsonx · vsource-scanned
61
overall

Monitor session context levels and proactively save checkpoints before compaction. Use when: (1) session context exceeds 80% capacity, (2) user asks about session status or memory, (3) at the start of each new session to check context, or (4) before long tasks that might push context over threshold.

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.

skillagi

wubotvix · vsource-scanned
61
overall

Remember mistakes across sessions. Append one-liner learnings, review before complex tasks, promote important ones.

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.

sokosumi

sarthib7 · vsource-scanned
61
overall

Hire sub-agents from Sokosumi marketplace to perform specialized tasks. All payments in USDM via Cardano smart contracts - just need an API key.

High Riskfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-14 22:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime_failedoutput 2.1 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2220 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: sokosumi made it to runtime and then fell apart on contact, which is not ideal for a skill asking to be trusted.6/7 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Review first — functionality-v2 already found trouble.

supercall

xonder · vsource-scanned
61
overall

Make AI-powered phone calls with custom personas and goals. Uses OpenAI Realtime API + Twilio for ultra-low latency voice conversations. Supports DTMF/IVR navigation — the AI can navigate automated phone menus by sending touch-tone digits. Use when you need to call someone, confirm appointments, deliver messages, navigate phone trees, or have the AI handle phone conversations autonomously. Unlike the standard voice_call plugin, the person on the call doesn't have access to gateway agent, reducing attack surfaces.

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

task-orchestra

tobisamaa · vsource-scanned
61
overall

Coordinate multiple agents and tasks for complex workflows. Orchestrate subagents, manage dependencies, handle parallel execution, and ensure successful completion of multi-step operations.\n

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.

teamo-lite-offline

urrrich0 · vsource-scanned
61
overall

You are Teamo-Lite, a high-speed AI for task planning and online information gathering. Your job is to **strictly choose one** of the following two workflows base on user needs, and complete task efficiently.**Workflow 1: Quick Q&A*** **Trigger Condition**: The user needs to directly **obtain**, **extract**, **query**, or **explain** existing information. This is typically a **non-creative** ...

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.

tg-groupchat-setup

arekqq · vsource-scanned
61
overall

>

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.

zulip

suky57 · vsource-scanned
61
overall

Interact with Zulip chat platform via REST API and Python client. Use when you need to read messages from streams/topics, send messages to channels or users, manage DM conversations, list users, or integrate with Zulip organizations for team communication workflows.

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.

call-claude-sonnet-4-agent

teamolab · vsource-scanned
60
overall

AI agent for call claude sonnet 4 agent tasks

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.

call-deepseek-v3-llm

urrrich · vsource-scanned
60
overall

AI agent for call deepseek v3 llm tasks

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.