🔎 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 · productivity-and-tasks

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 194 skills in the browsable catalog view · evidence: source-scanned · category: productivity-and-tasks · 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.

call-doubao1-5-llm

urrrich · vsource-scanned

AI agent for call doubao1 5 llm tasks

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.

call-gemini-2-5-pro-llm

urrrich · vsource-scanned

AI agent for call gemini 2 5 pro llm tasks

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.

call-grok4-llm

urrrich · vsource-scanned

This skill provides specialized capabilities for call grok4 llm.

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.

call-o3-llm

alvinecarn · vsource-scanned

AI agent for call o3 llm tasks

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.

chief-creative-officer

alvinecarn · vsource-scanned

AI agent for chief creative officer tasks

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.

milkee

xenofex7 · vsource-scanned

Complete MILKEE accounting integration for Swiss businesses. Manage projects, customers, time tracking, tasks, and products. Use when: (1) tracking billable time with start/stop timers, (2) creating/managing projects and customers, (3) recording work entries with descriptions, (4) viewing daily time summaries. Features smart fuzzy project matching.

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.

ops-hygiene

staybased · vsource-scanned

Standard operating procedures for agent maintenance, security hygiene, and system health. Use when performing periodic checks, security audits, memory maintenance, secret rotation, dependency updates, or any recurring "housekeeping" tasks. Also use when setting up automated maintenance schedules or when asked about agent security posture.

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.

telnyx-bot-signup

teamtelnyx · vsource-scanned

Automated Telnyx bot account signup via Proof of Work challenge

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.

async-task

enderfga · vsource-scanned

Execute long-running tasks without HTTP timeouts. Use when you need to:

Trustedconfidence: source evidencesource-scanned

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.

chief-editor-desicion

teamolab · vsource-scanned

AI agent for chief editor desicion tasks

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.

loan

prabu12478 · vsource-scanned

I originate commercial real estate and business-purpose loans with a focus on structuring, credit quality.

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.

longrunning-agent

yonghaozhao722 · vsource-scanned

Enables AI agents to work on long-running projects across multiple sessions. Use when starting complex projects, resuming work on existing projects, managing task lists with priorities and dependencies, or tracking progress incrementally.

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.

portfolio-risk-analyzer

kellyclaudeai · vsource-scanned

**AI-powered crypto portfolio risk analysis with automated $BANKR buyback monetization.**

Use Cautionconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (wallet, private key, 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.

skill-detector

mouserider · vsource-scanned

>

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.

stanley-druckenmiller-workflow

luckycatl · vsource-scanned

Druckenmiller style market analysis in natural Chinese with a living PM memo voice. Thesis-driven workflow: formulate macro thesis first, test via tape, integrate liquidity, rates, credit, and internals into asymmetric causal throughlines.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (trading), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

subagent-driven-development

zlc000190 · vsource-scanned

Use when executing implementation plans with independent tasks in the current session

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.

teamo-lite

urrrich0 · vsource-scanned

AI agent for teamo lite tasks

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.

todo-boss

ukraecho · vsource-scanned

Task capture + delegation tracking + daily remaining-work report for Telegram.

Trustedconfidence: source evidencesource-scanned

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

zonein

phutt-bwai · vsource-scanned

version: 2.1.0

Use Cautionconfidence: source evidencesource-scanned

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

ai-daily-briefing

jeffjhunter · vsource-scanned

Start every day focused. Get a morning briefing with overdue tasks, today's priorities, calendar overview, and context from recent meetings. Works with ai-meeting-notes to-do list. No setup. Just say 'briefing'.

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.

autonomous-executor

ishsharm0 · vsource-scanned

Self-healing, error-recovering task execution with full autonomy.

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.

codifica

davidedicillo · vsource-scanned

Keep context when work moves between agents or between you and a human. Uses the Codifica protocol to give every agent a shared, persistent memory of tasks, decisions, and handoffs — stored as plain text in Git.

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-aware-delegation

rgba-research · vsource-scanned

Give isolated sessions (cron jobs, sub-agents, event handlers) full conversation context from your main session using sessions_history. Run cheap background tasks (Haiku) with expensive context (Sonnet-level awareness) — best of both worlds.

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.

deck-builder

teamolab · vsource-scanned

AI agent for deck builder tasks

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.

« First ← Prev 1 3 4 5 9Page 4 / 9Next →Last »