🔎 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 · browser-and-automation

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 16 of 136 skills in the browsable catalog view · label: Trusted · category: browser-and-automation · sort: score

page evidence snapshotruntime-passed: 0 runtime-failed: 0 source-scanned: 16 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.

shopping-list

ajeenkya · 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.

slashbot

alphabot-ai · vsource-scanned

Interact with slashbot.net — a Hacker News-style community for AI agents. Register, authenticate, post stories, comment, vote, and engage with other bots. Use when the user asks about slashbot, wants to post or read from slashbot.net, check discussions, engage with the community, or set up a heartbeat engagement loop. Requires curl, jq, openssl, and a local RSA or ed25519 private key for authentication.

Trustedconfidence: source evidencesource-scanned

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

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

snail-mail

dvdegenz · vsource-scanned

A slow-channel inbox for leaving your operator important messages. Use when something notable, abnormal, or decision-requiring happens and the operator should see it — but not urgently enough to interrupt. Also use when the operator asks to see their inbox, mark messages read, or archive items.

Trustedconfidence: source evidencesource-scanned

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.

snailmail

dvdegenz · vsource-scanned

A slow-channel inbox for leaving your operator important messages. Use when something notable, abnormal, or decision-requiring happens and the operator should see it — but not urgently enough to interrupt. Also use when the operator asks to see their inbox, mark messages read, or archive items.

Trustedconfidence: source evidencesource-scanned

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.

telegram-context

fourthdensity · vsource-scanned

Toggle-enabled skill that fetches Telegram message history at session start for conversational continuity. Maintains context across sessions without relying solely on memory files.

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.

autonomy-windowed

luciusrockwing · vsource-scanned

Time-windowed autonomous task queue. Autonomy works only during specific time windows (e.g., 8 AM - 8 PM UTC), while cron jobs run overnight. Separates concerns by time - day = autonomy, night = maintenance. Use when you want predictable work schedule, controlled token budget, and clear temporal separation between autonomous work and scheduled maintenance.

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.

exa-tool

claireaicodes · vsource-scanned

Exa MCP integration for advanced search, research, and crawling.

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.

feishu-sheets

wesley138cn · 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.

feishu-sheets-skill

wesley138cn · 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.

grok-browser

easonc13 · vsource-scanned

Query Grok AI via browser automation. Use when you need to ask Grok questions, get AI responses, or use Grok's DeepSearch/Think features. Copies response text instead of using screenshots.

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.

hfnews

huberteff · vsource-scanned

Fetch and filter news from multiple sources with stopwords/blacklist support. Customized for Hubert's interests (IT, Cybersecurity) with political/sports noise filtered out.

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.

ned-analytics

matt998759 · vsource-scanned

Query your Shopify store's sales, profitability, customers, and marketing data through Ned's API. Use when asked about profit, revenue, sales, orders, products, customers, churn, ad spend, ROAS, MER, margins, or any ecommerce analytics question. Also use for 'what's my profit today', 'top products', 'customer segments', 'ad performance', or 'how is my store doing'. Requires a NED_API_KEY.

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.

pocket-lens

edenjw · vsource-scanned

>

Trustedconfidence: source evidencesource-scanned

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.

pocketlens

edenjw · vsource-scanned

>

Trustedconfidence: source evidencesource-scanned

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.

rss-digest

odysseus0 · vsource-scanned

Agentic RSS digest using the feed CLI. Fetch, triage, and summarize RSS feeds to surface high-signal posts. Use when: (1) reading RSS feeds or catching up on news, (2) user asks for a digest, roundup, or summary of recent posts, (3) user asks what's new or interesting today, (4) user mentions feed, RSS, or blogs.

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.

testskillx

natx223 · vsource-scanned

Simple test skill that calls a GET endpoint to fetch a daily post.

Trustedconfidence: source evidencesource-scanned

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

« First ← Prev 1 5 6Page 6 / 6