probabl-ai/skore-skills

persist-ml-git

Commit the current loop stage when the end-turn hook says invoke.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/probabl-ai/skore-skills --skill persist-ml-git

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Persist ML Git

The hook already ran this turn. Follow its JSON. Run git yourself.

  1. If action is skip, stop. Do not nag. Load triage-ml-task

if installed, else stop.

  1. If reason is resolve-dotfiles and ambiguous_dotfiles is

non-empty, ask once which hidden paths to keep. Include an explicit Keep none option. An empty multi-select is not an answer. Then python -m skore_skills git ignore-merge --decide plus --keep <path> for each chosen path (no --keep if they keep none, including when they pick Keep none). Do not re-ask names gone from the next JSON. Never keep .env or .skore. If ambiguous_dotfiles is empty or reason is persist, do not ask about hidden paths. Exit code 2 from git ignore-merge is the structured dotfile decision required outcome, not a generic command failure: read its JSON, ask the decision, and rerun with --decide.

  1. If review_paths is non-empty, ask once which of those paths

to keep tracked. Include an explicit Keep none option. An empty multi-select is not an answer. List each JSON path and kind, and say that the rest are ignored. Then python -m skore_skills git review-decide with --keep <path> for each chosen path and --ignore <path> for every other path in the list (no --keep if they keep none, including when they pick Keep none). Pass a folder path through with its trailing slash so the ignore line is that folder. Copy paths and kinds from the JSON; do not invent them. Do not re-ask paths gone from the next JSON. Never --keep .env or .skore. If review_paths is empty, do not ask about file size, artifacts, or datasets. Do this when reason is resolve-review, and also after step 2 when reason is resolve-dotfiles and that payload lists review_paths. Exit code 2 from git review or git review-decide is the structured review decision required outcome, not a generic command failure: read its JSON, ask the decision, and rerun review-decide.

  1. Run git status. Stage only non-secret paths that are not

still listed in review_paths: git add -- <paths>. Never .env or .skore.

  1. Commit with a one-line subject from this turn's files and

intent: git commit -m "…". Do not use a canned stage slogan.

  1. Load triage-ml-task if installed, else stop.

Stop conditions

  • Do not git push, amend, rebase, or git config.
  • Do not invent a commit when the hook was skip (off,

unanswered, no_repo, clean).

  • Do not call python -m skore_skills git end-turn --stage <stage>

to perform the commit; that command only prints facts.

按任务相关推荐

来自同一仓库

更多 Skills

全部 Skills
probabl-ai
社区

audit-ml-pipeline

Audit a persisted skore report read-only and produce a reusable digest. Do not execute it. Run materialize.py once. Never call skore.evaluate or project.put. TRIGGER when a completed run needs an audit, the user asks to audit, show, or re-audit an experiment, a re-run overwrote the same put() key, or they want a narrative of a past experiment without journal/ideas/ files. STOP when status.setup.pending is non-empty (load setup-ml-project), or when there is no approved design, no report, or no ag

安装量
1
GitHub Stars
142
最近更新
10月20日
probabl-ai
社区

choose-python-library

Resolve a library choice and add the selected dependency. Trigger for competing-library questions or an optional package not already fixed by the project stack — at first use (tabular exploration, pipeline, or eval extras), never during workspace setup.

安装量
1
GitHub Stars
142
最近更新
10月20日
probabl-ai
社区

export-ml-project

Coordinate executed notebooks and an offline MkDocs documentation site. Trigger on a generic "export" request, or to flip the notebooks/site gates after setup.

安装量
1
GitHub Stars
142
最近更新
10月20日
probabl-ai
社区

plot-ml-figure

Pick pandas, seaborn, plotly, or matplotlib before writing figure code. Trigger when explore-ml-data, evaluate-ml-pipeline, or audit-ml-pipeline is about to save or display a chart, or when the user asks for a plot. Not a session owner. Not for skore/sklearn Display plots that already exist on a report. HOW TO USE: first match on the tree (owned plot, interactive iframe HTML, seaborn statistical, pandas chart, else matplotlib). In a notebook: save PNG (or HTML) then leave the figure as the cell

安装量
1
GitHub Stars
142
最近更新
10月20日