🔎 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 · search-and-research

🧾 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 352 skills in the browsable catalog view · reviewed: no · category: search-and-research · 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.

xbio

soanai · vsource-scanned
62
overall

X/Twitter CLI for reading, searching, and posting via cookies or Sweetistics.

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.

zynd-network

atmegabuzz · vsource-scanned
62
overall

Connect to the Zynd AI Network to discover, communicate with, and pay other AI agents. Search for specialized agents by capability, send them tasks with automatic x402 micropayments, and receive responses. Enables multi-agent collaboration across the open agent economy.

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-lightning

olmmlo-cmd · vsource-scanned
61
overall

Microsoft Research's agent training framework. Optimizes AI agents with Reinforcement Learning, Automatic Prompt Optimization, and Supervised Fine-tuning. Zero code change required. Works with LangChain, AutoGen, CrewAI, OpenAI Agent SDK.

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.

agentx-news

amittell · vsource-scanned
61
overall

Post xeets, manage profile, and interact on AgentX News — a microblogging platform for AI agents. Use when the user asks to post updates, check feed, follow agents, manage an AgentX account, or interact with the AgentX social network. Covers registration, posting xeets, reading timelines, following/unfollowing, searching agents, liking, rexeeting, bookmarking, and profile management. API-first, no SDK needed.

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.

agnxi-search-skill

doanbactam · vsource-scanned
61
overall

author: Agnxi

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.

ahmed

engahmedsalah358-lgtm · vsource-scanned
61
overall

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

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.

auto-drive

emilfattakhov · vsource-scanned
61
overall

Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.

High Riskconfidence: 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.

automation-runner

barnyp · vsource-scanned
61
overall

Executes approved shell commands, manages backups, and safely retrieves secrets from Bitwarden.

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.

b2b-first-ten

pors · vsource-scanned
61
overall

Expert in getting the first 10 B2B customers, based on Lenny Rachitsky's "First 1000 Users" research. Focuses on founder-led sales, warm intros, and unscalable tactics for non-enterprise B2B.

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.

boof

chiefsegundo · vsource-scanned
61
overall

Convert PDFs and documents to markdown, index them locally for RAG retrieval, and analyze them token-efficiently. Use when asked to: read/analyze/summarize a PDF, process a document, boof a file, extract information from papers/decks/NOFOs, or when you need to work with large documents without filling the context window. Supports batch processing and cross-document queries.

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.

brw-ai-discoverability-audit

brianrwagner · vsource-scanned
61
overall

Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when user mentions "AI search," "how do I show up in ChatGPT," "AI discoverability," "AEO," "LLM visibility," or wants to understand their brand's AI presence.

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.

camino-fitness-finder

james-southendsolutions · vsource-scanned
61
overall

Search for gyms, yoga studios, swimming pools, and sports facilities using Camino AI's location intelligence with AI-powered ranking.

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.

hippius

maxquick · vsource-scanned
61
overall

Hippius decentralized storage on Bittensor Subnet 75 — upload files, query storage, manage buckets via S3-compatible API. Use when user asks to upload to Hippius, check storage status, set up Hippius credentials, list buckets/files, or asks about IPFS vs S3 options.

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.

kroger-api-skill

jasonahorn · vsource-scanned
61
overall

Skill for searching Kroger/QFC products, managing cart, checking pickup availability, and creating pickup orders.

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.

literature-manager

isonaei · vsource-scanned
61
overall

Search, download, convert, organize, and audit academic literature collections. Use when asked to find papers, build a literature library, add papers to references, download PDFs, convert papers to markdown, organize references by category, audit a reference collection, or collect code/dataset links for tools mentioned in papers.

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.

lyrics-search

hone1983 · vsource-scanned
61
overall

Search song lyrics by title and artist using the LrcApi public API. Use when the user asks to find, display, or print lyrics for a song.

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.

mh-wacli

mohdalhashemi98-hue · vsource-scanned
61
overall

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

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

persisent-mind

vedantsingh60 · vsource-scanned
61
overall

**Persistent, searchable, context-aware memory for AI agents. Store what matters. Never lose context again.**

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.

rps12345

yoavrez · vsource-scanned
61
overall

Play a text-based game of rock–paper–scissors against the user and keep score.

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.

skillzmarket

hiich · vsource-scanned
61
overall

Search and call monetized AI skills from Skillz Market with automatic USDC payments on Base. Use when the user wants to find paid AI services, call external skills with cryptocurrency payments, or integrate with the Skillz Market ecosystem.

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.

supaskills

ktdmax · vsource-scanned
61
overall

Search and load 1,000+ quality-scored expert skills from SupaSkills.ai

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.

supermarket

niemesrw · vsource-scanned
61
overall

Search grocery products, find store locations, add items to cart, and view profile across all Kroger-family stores — Kroger, Ralphs, Fred Meyer, Harris Teeter, King Soopers, Fry's, QFC, Mariano's, Pick 'n Save, Metro Market, and more. Use when user asks about groceries, food shopping, store locations, or wants to manage their grocery cart.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 11:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 129 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2251 msbaseline-v3 8/8
RatioDaemon muttered: supermarket looked ordinary in the good, boring way.7/7 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.

x-cli

ignsoftwarellc · vsource-scanned
61
overall

Full-featured X/Twitter toolkit — read, search, post, interact, DMs, lists, polls, trends. Cookie auth, proxy support, no API keys needed.

Use Cautionconfidence: 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.

zero-to-one-startup

lifeissea · vsource-scanned
61
overall

AI-powered startup companion for Korean founders. Evaluate business plans, match government funding programs (TIPS/DeepTech/Global TIPS), connect with 3,972+ TIPS-selected startups, get investor recommendations, and integrate with Kakao i OpenBuilder. Features Agentic RAG (HyDE, Multi-Query, CRAG), structured extraction, and Track B financial matching.

High Riskfollow-on functionality checks failed · 8/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-14 14:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime_failedoutput 533 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 4851 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: zero-to-one-startup made it to runtime and then fell apart on contact, which is not ideal for a skill asking to be trusted.8/10 functionality-v2 checks passed before the stumble. The python syntax is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: eval(.
Decision cue: Review first — functionality-v2 already found trouble.