npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

uta-ai-skills

v0.1.0

Published

4 installable agent skills (agentskills.io): UTA credential verification, Sentinel MCP audits (UTA Shield checklist), MarketNow catalog recommendations, UTA conformance vectors. By AliceLabs LLC.

Readme

uta-ai — Official AI agent surface for UTA & MarketNow

Réplica del patrón verificado en taikoxyz/taiko-ai (caso de estudio 21-oct-2026): el proyecto entero como superficie de agente — skills instalables, subagentes especializados, servidores MCP, plugin de Claude Code y auditoría de PRs por el propio agente. UTA = Universal Trust Adapter: traduce entre 9 formatos de credenciales de agentes para que cualquier agente verifique a cualquier otro (v4.0.0, 71,198 skills indexadas — /api/skills, 21-oct-2026).

Qué contiene

| Directorio | Qué es | Equivalente en taiko-ai | |---|---|---| | skills/ | 4 skills formato agentskills.io (SKILL.md con frontmatter) | skills/taiko, taiko-node... | | agents/ | 2 definiciones de subagentes especializados (markdown con frontmatter) | agents/taiko-developer.md | | mcp-servers/ | Spec + scaffold de servidores MCP locales (stdio) | mcp-servers/taiko-data (16 tools) | | .claude-plugin/ | marketplace.json + plugin.json para Claude Code | idéntico | | audit.md | Auditoría de PRs HECHA POR el agente (bugs / violaciones de reglas / eficiencia de tokens) | audit.md del PR #12 | | .github/workflows/ | CI + drift-check: detector diario de cifras muertas (números vivos automatizado) | .github/workflows/ | | site-agent-first/ | Artefactos para servir en marketnow.site: /SKILL.md, generador /llms.txt v2, reporte de gaps | taiko-docs (llms.txt, SKILL.md) |

Instalación (3 vías, como taiko-ai)

# 1. Como skills del estándar abierto (Cursor, Copilot, Windsurf, Cline, Codex...)
npx skills add alicelabs-llc/uta-ai

# 2. Como plugin de Claude Code
/plugin marketplace add alicelabs-llc/uta-ai
/plugin install uta@alicelabs-llc

# 3. Servidor MCP remoto (ya vivo, no requiere este repo)
{
  "mcpServers": {
    "marketnow": {
      "url": "https://marketnow.site/api/mcp"
    }
  }
}

Superficie viva detrás de este repo (verificada 21-oct-2026)

  • API de confianza (sin auth): GET/POST https://www.marketnow.site/api/trust — verify / translate / issue / bridge (pipeline fail-closed de 12 etapas: UNKNOWN = DENY).
  • 9 tools MCP remotas en https://marketnow.site/api/mcp: marketnow_search_skills, marketnow_verify_trust, marketnow_translate_credential, marketnow_list_formats, marketnow_get_pipeline, marketnow_check_domain, marketnow_check_revocation, marketnow_fingerprint_tool, marketnow_submit_skill.
  • Catálogo: 71,198 skills indexadas (L1) + 135,547 en tracker de ecosistema — /api/skills paginado, /api/categories.json, página pública por skill en /s/<slug>, badge SVG por skill.
  • Agent card: https://marketnow.site/api/agent.json (v4.0.0) y well-known /.well-known/agent.json.
  • Conformance: @marketnow/[email protected] (npm) + vectores vivos en /uta/conformance/vectors/_index.json (schema 1.6.0).

Los 4 skills

| Skill | Dispara cuando | |---|---| | uta | "UTA", "verify credential", "ATC", "trust card", "translate credential", "revocation" | | sentinel-audit | "audita este MCP", "certifica", "trust score", "badge", "publish skill" | | marketnow-catalog | "busca skills", "catálogo", "recomienda un MCP para X" | | uta-conformance | "corre la conformance", "vectores", "expected outcomes", "interop third-party" |

Estado del scaffold y roles

  • Hecho por el agente (YO): todos los SKILL.md, agents/, plugin, spec de MCP servers, audit.md, workflows, artefactos del sitio — este repo ES el entregable.
  • Scaffold v0.1 (mcp-servers/catalog-mcp/): implementación mínima a validar con npm ci && npm run build antes de usar — el agente la completa contra la API viva en el próximo BOOT con credenciales.
  • Drift-check en CI: cada día compara el total vivo de /api/skills contra el número escrito en llms.txt/SKILL.md — si difiere, falla el build. El "número muerto = bug de credibilidad" queda automatizado.

Licencia

MIT — see LICENSE. Scope: the uta-ai agent surface only; the UTA core stays AL-1.0 source-available at alicelabs-llc/universal-trust-adapter (https://marketnow.site/licensing).

Caso de estudio origen

Análisis completo y plan de réplica: agente-marketnow-v2/iniciativa-agent-first/ (CASO_ESTUDIO_TAIKO.md · PLAN_REPLICACION.md). Fuentes verificadas 21-oct-2026: github.com/taikoxyz/taiko-ai (91 commits, v1.5.0, contribuidores dantaik + claude) · github.com/taikoxyz/taiko-docs (llms.txt / llms-full.txt / .md por página / SKILL.md).