probabl-ai/skills

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Owns the audit/ folder: one # %% (jupytext percent) Python file per experiment, aligned 1:1 with experiments/NN .py and journal/NN .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 the bundled…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Declare the pipeline from data source to predictor as a skrub DataOps graph (not as a bare sklearn.Pipeline). Every step is either a pure-Python function (stateless) attached via .skb.applyfunc, or a sklearn-compatible estimator (stateful) attached via .skb.apply. Stops at the declared object — no fit, split, tuning…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Opinionated Python stack for data-science / ML work — one library per job, organized into tiers (mandatory / user choice / optional / transitive). SKILL.md is the index; per-library references/ .md files carry scope, "pick this when" / "pick something else when", and pairings. TRIGGER when (any of these): (1) a…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Methodology for evaluating a single sklearn-compatible learner (in particular, the SkrubLearner produced by build-ml-pipeline). Owns: which entry point to call (skore.evaluate first, the explicit report classes when needed), which cross-validator to pick from scikit-learn's catalogue, how to consume the structural…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Owns data understanding BEFORE any model is designed. Places and executes data/eda.py (a jupytext # %% script) via the shared in-process runner, reads the streamed digest, then writes a persisted data/eda.md report (plus linked data/eda .html skrub TableReport pages) and the ## Data understanding (EDA) section of…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Source the next ML experiment proposal by reading the audit digest at scratch/audit/ /audit.md (produced by audit-ml-pipeline at § 4 record-outcome). For every row in the digest's ## Checks summary whose severity is issue or tip, follow the row's documentationurl to draft a Backlog row whose Item is the mitigation the…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Source the next ML experiment proposal from the user via one of three entry points selected by AskUserQuestion: (a) a scientific article URL the agent must read and synthesize, (b) a resource link or path (GitHub issue / spec file / reference repo), or (c) free-text the user types directly. In every branch, the agent…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Owns the iteration loop on top of an ML workspace: the journal/JOURNAL.md index and the per-experiment journal/NNshortname.md design notes that must be drafted and approved by the user before experiments/NNshortname.py is created. Drives the propose → iterate → approve → implement → record loop; dispatches to…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Decide where files live in an ML experimentation project: reusable code in src/ /, one # %% script per experiment in experiments/, design notes + index in journal/, reports in reports/, agent-only probes in scratch/. Owns the layout, the file-creation rules (one file per experiment, ask before editing), and the…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Look up the public API of a Python package against the installed version and cache what's worth keeping. Four shapes by question type: (0) cache hit under scratch/api/ / /; (1) inspect.signature + pydoc.renderdoc for a symbol; (2) dir / pkgutil.itermodules for a module surface; (3) WebSearch + WebFetch of versioned…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Three responsibilities — (1) place the project's ruff.toml from the bundled template once the stack and workspace are in place, (2) run ruff against any Python files Claude has just generated or edited, and (3) contextualize each…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Single source of truth for "which Python environment manager does this project use, and how do I install a package with it?". Owns the detection table (pixi / uv / poetry / hatch / conda+mamba / pip+venv), the install / remove / upgrade commands per manager, and the bootstrap path when no manager is in place (default…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

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…

probabl-ai/skills

Skill Claude CodeCodex

Part of skills

Owns the tests/ folder of an ML workspace and the pairing rule between an experiment and its tests. Lightweight router: every test category has its own subskill (smoke-test-ml-pipeline is the only one for v1; regression-test-ml-pipeline / distribution-test-ml-pipeline etc. plug in as siblings as the workspace grows).…