メニュー
Use GitHub, Hugging Face, and ModelScope as first-hand engineering evidence sources when you need to confirm real implementation, directory layout, commit history, issue / PR context, or model/data/weight platform assets.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | github-search |
| description | Use GitHub, Hugging Face, and ModelScope as first-hand engineering evidence sources when you need to confirm real implementation, directory layout, commit history, issue / PR context, or model/data/weight platform assets. |
[Skills: github-search] Follow: <rules / context constraints that really apply now>; Current step: <one-line note>.[Rules: <rule>] ..., then continue with the real work.websearch / Exa for minimal discovery, then decide whether GitHub, Hugging Face, or ModelScope should be first.username / org, newest work, pinned / featured projects, latest release, recent commit, recent paper / model / dataset / Space, and related same-tag / same-collection projects.docs say supported, but code does not show it, write clearly where the docs evidence comes from and where the code / platform-asset evidence comes from.Used for high-quality experiment reports, analysis reports, and technical summaries. Evidence must be enough, charts must be real, structure must be clear, and empty talk is forbidden.
Open several fundamentally different routes for one problem fast, so the flow does not keep doing small tweaks on one path only.
Split a complex problem into a multi-step reasoning chain, and make key assumptions, branch points, validation order, and rollback points explicit.
Manual start skill: read `.opencode/` first, then read the task files at the project root and start execution. It is like replacing the first prompt line.
Built-in Python tool priors covering time series, statistics, machine learning, and related ecosystems. It reduces repeated search cost and gives the first coverage of method families and tool families.
In time-series, deep-learning, and LLM projects, use ztxexp to unify experiment config, batch runs, result tracking, ablation analysis, and failure diagnosis.