skore-skills

In the author's own words, from each skill's SKILL.md.

• add-python-package

  Add a Python dependency through the project env manager, or ask the user to install it when env.managed is false. Trigger when a workflow needs a missing import, after choose-python-library picks a library, or for editable install of src/<pkg>/. SKIP choosing between competing libraries (choose-python-library owns that). SKIP bootstrapping a missing manager (setup-python-env). HOW TO USE: read st…

  skills/add-python-package/SKILL.md on GitHub (opens in a new tab)

• audit-ml-pipeline

  Owns the `audit/` folder: one `# %%` (jupytext percent) Python file per experiment, aligned 1:1 with `experiments/NN_<short_name>.py` and `journal/NN_<short_name>.md`, that loads the experiment's skore report **read-only** and uses bare-last-expression cells whose `__repr__` carries the audit's signal. The agent executes the audit file via `python -m skore_skills cells run`, which streams a markd…

  skills/audit-ml-pipeline/SKILL.md on GitHub (opens in a new tab)

• build-ml-pipeline

  Declare the pipeline from data source to predictor as a skrub DataOps graph. Stateless steps use `.skb.apply_func`. Stateful steps use `.skb.apply`. After the graph exists, attach the locked splitter and any non-default score. No fit, tune, persistence, or `skore.evaluate`. TRIGGER when writing or editing any link from data source to predictor (loaders, preprocessing, features, composition, the f…

  skills/build-ml-pipeline/SKILL.md on GitHub (opens in a new tab)

• choose-python-library

  Resolve a genuine choice between Python libraries for one job, then ask `add-python-package` to add the chosen 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.

  skills/choose-python-library/SKILL.md on GitHub (opens in a new tab)

• data-science-python-stack

  Deprecated compatibility skill. Trigger only when an installed workflow still references this old id.

  skills/data-science-python-stack/SKILL.md on GitHub (opens in a new tab)

• evaluate-ml-pipeline

  Evaluate one learner with `skore.evaluate`. The splitter and any non-default score are already on the DataOp from `build-ml-pipeline`. This skill writes the call without `splitter=`, persists the report, and records the locator. When `model-ml-pipeline` dispatched this turn, return the locator. A standalone turn also owns the evaluate-stage close. TRIGGER when code calls `cross_val_score`, `cross…

  skills/evaluate-ml-pipeline/SKILL.md on GitHub (opens in a new tab)

• explore-ml-data

  Owns data understanding BEFORE any model is designed. Places `data_analysis/data_analysis.py` (TableReport plus duplicates, target, bivariate, leakage), runs `python -m skore_skills cells run`, dumps agent facts under `scratch/data_analysis/`, then writes `data_analysis/data_analysis.md` and JOURNAL § Data understanding. Never designs the model, never edits `src/<pkg>/`, never modifies raw data f…

  skills/explore-ml-data/SKILL.md on GitHub (opens in a new tab)

• export-ml-notebook

  Convert a jupytext percent `# %%` Python file into an executed `.ipynb` with cell outputs. Pass `--html` when the notebook should also become a viewer on the site. Trigger on notebook, ipynb, HTML, or executed-report requests, or when export-ml-project dispatches notebooks.

  skills/export-ml-notebook/SKILL.md on GitHub (opens in a new tab)

• export-ml-project

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

  skills/export-ml-project/SKILL.md on GitHub (opens in a new tab)

• export-ml-site

  Package JOURNAL, exploratory data analysis markdown, and design notes into an offline MkDocs site opened via report.html at the workspace root. Embeds existing notebook HTML companions in their associated reports. Never executes Python. Trigger when the user asks for a website, mkdocs, or documentation site.

  skills/export-ml-site/SKILL.md on GitHub (opens in a new tab)

• frame-ml-problem

  Lock the problem, the deployment setting, the comparison metric, the baseline, and the fold count in the journal before any model code. Ask every missing decision in one turn, from `frame show`. Does not write Python, estimator hyperparameters, or splitter constructors. TRIGGER when the user asks which metric to compare on, how new rows should be split, which baseline to use, or says a problem co…

  skills/frame-ml-problem/SKILL.md on GitHub (opens in a new tab)

• manage-ml-backlog

  Canonical backlog loop step. Record an experiment outcome in History and triage idea files into Backlog rows. Keep each idea file and mark it promoted, discarded, or aside. Also supports the model-entry selection mode: show real B<N> rows supplied by the deterministic CLI and consume one into a proposal. Trigger after audit, when a run finishes, when the user asks what to try next or to triage id…

  skills/manage-ml-backlog/SKILL.md on GitHub (opens in a new tab)

• model-ml-pipeline

  Deterministic entry point for modeling. On a generic landing, offer only the choices justified by the workspace (the locked baseline, an EDA proposal, Backlog, discussion). A missing modeling lock loads `frame-ml-problem` and stops. After a design is approved, coordinate build (pytest smoke is a build sub-step), the user's Evaluate (Recommended) / Modify / Stop gate, evaluation, and audit. Not fo…

  skills/model-ml-pipeline/SKILL.md on GitHub (opens in a new tab)

• organize-ml-workspace

  Deprecated compatibility skill. Trigger only when an installed workflow still references this old id.

  skills/organize-ml-workspace/SKILL.md on GitHub (opens in a new tab)

• persist-ml-git

  Persist the current loop stage with the real git CLI when the end-turn hook says invoke. Trigger after `python -m skore_skills git end-turn --stage <stage>` returns action invoke, or when the user asks to commit this turn's work.

  skills/persist-ml-git/SKILL.md on GitHub (opens in a new tab)

• plot-ml-figure

  Pick how to write a figure before custom plot 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…

  skills/plot-ml-figure/SKILL.md on GitHub (opens in a new tab)

• research-ml-practice

  Literature and web research for an ML methodology concern (EDA extra measurements, leakage, transforms, feature engineering, learner family), or an EDA extra-analysis survey from JOURNAL plus existing EDA. Trigger when explore-ml-data or build-ml-pipeline load this skill. Not for routine profiling or a single API signature — use `api get` for symbols. Not a session owner — callers distill and wri…

  skills/research-ml-practice/SKILL.md on GitHub (opens in a new tab)

• review-ml-choices

  Show the project choices already stored in status and let the user change one by re-entering the skill that owns it. Trigger when the user asks what we decided, what the current settings are, or to change a stored project choice. SKIP an explicit sync, export, or “a constraint changed” request — those load sync-ml-reports, export-ml-project, or frame-ml-problem directly. HOW TO USE: run `review c…

  skills/review-ml-choices/SKILL.md on GitHub (opens in a new tab)

• review-ml-experiment

  Post-evaluate review. Gate the expensive skore-check audit, then write one markdown idea file per candidate. Trigger after a successful evaluate, on "review this stem", or when review consent is Review or proceed. Do not write JOURNAL.md or a design note. Do not run cells run until the user accepts the audit cost.

  skills/review-ml-experiment/SKILL.md on GitHub (opens in a new tab)

• search-ml-literature

  Search scientific and technical sources for a query and, after the user picks and confirms one direction, write one idea file. Comes after review, beside the backlog. Do not call research-ml-practice. Do not write JOURNAL.md or a design note. Do not pick a winner.

  skills/search-ml-literature/SKILL.md on GitHub (opens in a new tab)

• setup-git

  Set up git for an ML workspace after scaffolding. Trigger when the user asks to initialize version control, add ignore rules, or make the first commit. This action owns first-time git setup only. Before the first commit, ask once which unknown hidden files and review paths to keep tracked.

  skills/setup-git/SKILL.md on GitHub (opens in a new tab)

• setup-ml-project

  Coordinate first-time ML project setup. Trigger when the user asks to set up or bootstrap a complete ML workspace. Ask the installed pieces (all preselected), then in that same opening phase ask the environment manager, whether we manage the env, the import name, and git autocommit — only for boxes that stay checked and answers that are not already recorded. Persist those answers, then run only w…

  skills/setup-ml-project/SKILL.md on GitHub (opens in a new tab)

• setup-python-env

  Bootstrap a Python environment manager and three named envs (default runtime, agent tools, composed dev). Detect with `python -m skore_skills env detect`, persist manager and `env.managed`, then `env init --manager`, `env sync --execute`, install Skore for a recorded `hub` or `mlflow` destination (plain Skore when that destination is unset or `local`), and `env verify --execute`. Does not add oth…

  skills/setup-python-env/SKILL.md on GitHub (opens in a new tab)

• setup-workspace

  Detect an existing ML workspace or scaffold a fresh one via `python -m skore_skills scaffold --package <pkg>`. Cookiecutter only: directories, README.md files, and src/<pkg>/ stubs. After a first scaffold, turn executed notebooks and the documentation site on by default (no ask). TRIGGER for a new ML project layout or first scaffold. SKIP pipeline, evaluation, exploratory data analysis, and libra…

  skills/setup-workspace/SKILL.md on GitHub (opens in a new tab)

• shape-user-idea

  Shape an idea the user already has, or answer a project question, and write one idea file after they confirm. A topic with no artifact belongs to search-ml-literature. Do not write JOURNAL.md or a design note. Do not pick a backlog row.

  skills/shape-user-idea/SKILL.md on GitHub (opens in a new tab)

• smoke-test-ml-pipeline

  Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-featur…

  skills/smoke-test-ml-pipeline/SKILL.md on GitHub (opens in a new tab)

• sync-ml-reports

  Copy skore reports between local, Hub, and MLflow with `skore sync`, and optionally switch the recorded upload destination. Trigger when the user asks to sync or migrate reports, switch skore mode, upload reports to Hub or MLflow, or pull Hub/MLflow reports onto disk. First G-SKORE-MODE pick stays evaluate-ml-pipeline.

  skills/sync-ml-reports/SKILL.md on GitHub (opens in a new tab)

• triage-ml-task

  Session owner: list installed entry skills and ask which to run. Load a skill without asking only when the request is certain to be that skill. Trigger on an ambiguous request, a finished stage, a workspace-open session, or "what should we do next".

  skills/triage-ml-task/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 107k stars · 25 skills
• skillsby google Agent Skills for Google products and technologies 21.3k stars · 30 skills
• garden-skillsby ConardLi ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more. 12.9k stars · 5 skills
• ui-skillsby ibelick Skills for Design Engineers 9.8k stars · 7 skills
• Claude-Redby SnailSploit claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md fil… 7.5k stars · 30 skills