package-release-sniffer

$npx mdskill add JasonxzWen/harness-hub/package-release-sniffer

Track newly published packages across registries and release feeds.

  • Detect new package releases before they become general news.
  • Depends on npm and PyPI registry pages, APIs, and GitHub Releases.
  • Prioritizes packages with concrete shipped artifacts and meaningful version bumps.
  • Returns package name, version, publish time, source URL, and release significance.

SKILL.md

.github/skills/package-release-snifferView on GitHub ↗
---
name: package-release-sniffer
description: Load when tracking newly published package or model-package releases across package registries and release feeds for AI/developer-tool monitoring; do not load for ordinary docs lookup, broad GitHub trend scanning, or implementing package clients.
license: MIT
metadata:
  source: "local-original"
---

# Package Release Sniffer

Use this skill to find newly published packages or meaningful package releases before they become general news.

## Workflow

1. Define the package ecosystem and freshness window before searching.
2. Check primary release surfaces first: registry package pages, registry APIs, release feeds, GitHub Releases, changelogs, model cards, and maintainer announcement posts that link to the package.
3. Record the package name, ecosystem, version, publish time, source URL, maintainer or organization, license signal, install surface, and why the release matters.
4. Prefer packages with concrete shipped artifacts: new package, major/minor version, security fix, SDK/API capability, model/runtime integration, benchmarked performance change, or developer workflow impact.
5. De-duplicate aliases across registry pages, GitHub repositories, model cards, and maintainer posts.
6. Mark uncertainty when publish time, package identity, maintainership, license, or artifact availability is unclear.

## Source Priority

Use primary sources before secondary mentions:

- npm package pages and npm registry metadata
- PyPI project pages and release history
- GitHub Releases, tags, changelogs, and repository package metadata
- Hugging Face model, dataset, Space, and library release pages when they behave like package artifacts
- crates.io, Go package/module pages, Maven Central, NuGet, Docker Hub, or similar registries when relevant
- Maintainer blogs or docs only when they link back to the package or release artifact

## Keep

- First public release of an AI or developer-tool package
- New major or minor release with a clear capability change
- SDK, CLI, MCP server/client, inference runtime, agent framework, eval, data pipeline, observability, RAG, vector database, or deployment package
- Security, compatibility, performance, or migration-impact release
- Package release that is not yet visible in broader trend/news sources

## Drop

- Media-only claims without a package or release source
- Repository commits without a packaged artifact
- Awesome lists, prompt dumps, demo-only repos, and placeholders
- Releases with unclear maintainership, no usable artifact, or no relevant AI/developer-tool signal
- Ordinary patch releases unless they affect security, compatibility, or widely used workflows

## Output Shape

Return concise candidates:

```json
{
  "package": "",
  "ecosystem": "npm | pypi | github-release | hugging-face | crates | go | maven | nuget | docker | other",
  "version": "",
  "published_at": "YYYY-MM-DDTHH:mm:ssZ",
  "source_url": "",
  "maintainer": "",
  "signal": "new_package | major_release | minor_release | security | performance | compatibility | ecosystem",
  "summary": "",
  "why_it_matters": "",
  "confidence": "high | medium | low"
}
```

## Boundaries

- Use `documentation-lookup` when the task is to read current docs for an already chosen package.
- Use `source-post` when a confirmed release must become a publishable article.
- Use implementation workflows when the user wants a registry client, scraper, monitor, or scheduled job built.
- Do not create accounts, subscribe to feeds, change automation, or publish packages.

More from JasonxzWen/harness-hub

SkillDescription
agent-interaction-auditLoad when the user asks for private agent interaction audits from local Codex/Claude Code traces, task profiles, tool-call decisions, collaboration bottlenecks, prompt/rule or automation-log audits, closeout retrospectives, or evidence-backed Skill/project-rule/Eval/SOP/OKF improvements.
agent-reachLoad when a task needs read-only internet research or content retrieval through an already installed Agent Reach CLI; diagnose available backends first, never install, upgrade, authenticate, configure, or copy credentials on the user's behalf.
animation-vocabularyLoad when a user describes a Web animation or motion effect without knowing its name and needs the precise term or close alternatives; use only for naming, not design, implementation, or review.
apple-designLoad when a frontend task needs Apple-platform design guidance or physical, gesture-driven, velocity-aware, interruptible interaction; skip generic visual styling and use review-animations for report-only motion review.
beautiful-feishu-whiteboardLoad when creating or restyling a polished editable Feishu or Lark whiteboard, infographic, diagram, poster, or visual explainer; do not load for generic SVGs, static images, or other whiteboard platforms.
clone-websiteLoad when the user explicitly asks to clone, reverse-engineer, or rebuild a website they own or are authorized to reproduce; do not load for generic redesign, inspiration, scraping, phishing, impersonation, or copying third-party brands.
codebase-to-courseLoad when a user wants a source-backed interactive HTML course that explains how a codebase works; do not load for chat tutoring, repository review, articles, slide decks, or general browser artifacts.
context-guidanceFixture skill used to represent an additional standard skill context surface.
decision-uiLoad when Codex 即将要求用户在 2-3 个互斥方案中做真实决定、准备询问阻塞性澄清问题或需要确认高影响取舍;将选择转换为宿主原生可点击 UI,并在工具不可用时诚实文本回退。不要用于低风险实现细节、只有一个合理答案的问题、普通信息采集或不需要用户决策的完成汇报。
design-taste-frontendLoad when a task needs anti-template frontend visual direction, design-read calibration, or pre-flight critique for landing pages, portfolios, marketing pages, or redesigns; do not load for dashboards, data tables, multi-step product UI, routine frontend logic, HTML reports, slide decks, or generic code explanation.