Hacktoberfest 2026：メンテナが10月に向けて印を付けた、オープンで初心者向けの issue。 Hacktoberfest の issue を見る

[External Plugin]: where my hug

クローズ
  • 何か問題がありますか？
#5,061 コメント 4 件 リアクション 0 件 担当者 0 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

まだ誰も着手していません。

評価

難易度
3/5
見積もり時間
半日
初心者へのやさしさ
15/100
issue の種類
機能追加
明瞭さ
おおむね明確
活発さ
活発
技術スタック
huggingface, javascript
領域
developer-experience, machine-learning

調査の方向性

This is a marketplace listing submission, not a code change: review the plugin/ folder in bikemeardsley/where-my-hug, starting with .claude-plugin/plugin.json, the single skill, and the pinned npx [email protected] MCP server. Check the submission fields against the checklist and the contribution policy. Done means a maintainer approves or declines the listing, and the two existing comments have been answered.

索引モデルが issue の本文から書いたものです。

説明

external-plugin needs-review:HIGH ready-for-review
Plugin name

where-my-hug

Short description

Tells your agent which parts of an ML need Hugging Face already covers (use, fine-tune, train, or just code), with every model and dataset checked live and sized for your hardware.

GitHub repository

bikemeardsley/where-my-hug

Plugin path inside the repository

plugin

Ref to review

refs/tags/where-my-hug--v0.2.0

Commit SHA to review

8e294fd8a81c61e1a4c721f95492ba34bd99afee

Version

0.2.0

License identifier

MIT

Author name

Michael Beardsley

Author URL

No response

Homepage URL

No response

Keywords

hugging-face
machine-learning
mcp
models
datasets
fine-tuning
model-selection

Additional notes for reviewers

Where My Hug At? helps Copilot recommend Hugging Face models and datasets that actually exist. It asks four questions (compute, license, stack, data), splits the job into parts, searches Hugging Face live for each (most downloaded and trending for the task, names, and card text), and gives each part its verdict from what turned up (use as is, fine-tune, train, or just code). Every pick is then checked live against the Hugging Face API: missing ids are dropped, anything the agent added from memory is labeled as such, the rest are flagged for license, gating and staleness, and sized against the user's hardware.

  • Plugin folder: plugin/ (Agent Plugins plugin.json and mcp.json, plus the Claude-format .claude-plugin/plugin.json; one skill, one MCP server).
  • The MCP server is local (stdio), launched as npx -y [email protected] (pinned, published on npm, lockfile in the plugin folder). Its only network calls are read-only GETs to huggingface.co/api; it reads and writes no files.
  • No credentials required. An optional HF_TOKEN adds private repos and is sent only to huggingface.co.
  • Tested: installs with copilot plugin marketplace add bikemeardsley/where-my-hug and copilot plugin install where-my-hug@where-my-hug; the MCP server and the skill both register.
  • MIT. Also listed in the official MCP Registry (io.github.bikemeardsley/where-my-hug).
Submission checklist
  • The plugin lives in a public GitHub repository.
  • The ref and/or sha I provided is immutable (release tag and/or full 40-character commit SHA), not a branch.
  • This submission follows this repository's contribution, security, and responsible AI policies.
  • This plugin is not already listed in the Awesome Copilot marketplace.
主要言語
JavaScript
スター
40k
フォーク
5.1k
平均マージ
2日 11時間
マージ済み PR（30日）
120

環境構築

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

github/awesome-copilot のほかの issue

github/awesome-copilot の issue をすべて見る

似ている issue

JavaScript の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。