probabl-ai/skore-skills

research-ml-practice

Literature research for an ML methodology concern.

Voir la source

Mode d’emploi

  1. Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
  2. Consultez le document original pour les outils, identifiants et environnements requis.
  3. Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/probabl-ai/skore-skills --skill research-ml-practice

Avant de commencer

  • L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
  • Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Document Skill original

Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.

Research ML Practice

Worker skill. Callers own the stage turn and the user-facing summary. Do not git end-turn.

Human-facing prose

Details: setup-workspace references/human_facing_prose.md. Chat stays path + one or two sentences of the finding. Do not narrate the skills framework or the wrapper CLI.

Sequence

  1. Intake. Infer modality from dtypes / JOURNAL when

obvious; use a stated domain and stage (data_analysis | model) if the caller named them. Then pick a mode (references/search.md):

  • Caller passed a named concern (not the canned EDA

extra-analysis question) → depth. Do not re-ask. Do not run the canned survey first.

  • Caller passed the canned extra-analysis survey or

“survey extra analyses” → survey.

  • Neither → if JOURNAL and an EDA report exist, run the

canned survey; else AskUserQuestion for a named concern, stating the modality and stage inferred this turn and that the answer only drives a literature search, no code. A file link is an addition, never the context. Do not start a depth search with an empty concern.

  1. Abstract the problem class before any query

(references/search.md). JOURNAL and EDA are context, not the answer list and not search keywords for the table’s proper name.

  1. Run the matching search loop (references/search.md).

Fetch primary pages. Follow up per promising extra if the first pass is thin or single-sourced.

  1. Write scratch/research/ using the matching structure in

references/search.md (survey: survey-<slug>.md; depth: <slug>.md with lanes). There is no templates/ directory in this skill — copy the markdown skeleton from that reference. Gitignored.

  1. Return to the caller: scratch path and a one- or two-sentence

finding. Name that candidates are laned (measure / declare / evaluate / confirm). Chat is path + those sentences only — no pasted headings, tables, or “Depth note — …” body. That is the complete user-facing deliverable even when a harness says to put the full answer in chat. If tools cannot search or write, stop there: still only path + sentences (name the intended scratch/research/ path). No hypotheses, diagnostics, planned-query bullets, or template headings in chat (that is the paste). Do not write data_analysis.md, the design note, or data/. The caller asks which extras to add.

Stop conditions

  • Do not drop, impute, or remove outliers. Do not change the split.
  • Do not pick the final learner or architecture.
  • Do not treat a single blog as ground truth; say when sources

disagree. Thresholds need two independent sources.

  • Do not pixi add / uv add / env add. If code needs a

library, name add-python-package and return.

  • Do not run api get as a substitute for literature (symbols

still go through api get in the caller).

  • Missing skill from a caller → that caller one-line skips.
  • Do not copy Open questions / EDA findings onto the extras

list without a source.

  • Do not search the dataset proper name, sklearn.datasets,

a Kaggle slug, or “baseline pipeline”. Do not return learners / Pipeline steps as EDA extras.

  • Never answer from memory when search ran. Do not ask the

user to go look something up.

  • Do not paste the scratch markdown into chat (no “Depth

note —”, no survey body). Path + 1–2 sentences only. If tools cannot search or write, stop after that. A no-tools harness does not license pasting the note.

Tâches connexes

du même dépôt

Autres Skills

Tous les Skills
probabl-ai
Communauté

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

Installations / 1h
1
GitHub Stars
145
Mis à jour
9 nov.
probabl-ai
Communauté

setup-git

Initialize safe version control, including an optional commit of the tree before setup changes it. 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. When loaded for the pre-change snapshot, commit the current tree before other setup writes, then return.

Installations / 1h
1
GitHub Stars
145
Mis à jour
9 nov.
probabl-ai
Communauté

shape-user-idea

Shape a user idea or a named artifact into one idea file and one Ideas row after they confirm. A topic with no artifact belongs to search-ml-literature. Do not write History, Backlog, or a design note. Do not pick a backlog row.

Installations / 1h
1
GitHub Stars
145
Mis à jour
9 nov.
probabl-ai
Communauté

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

Installations / 1h
1
GitHub Stars
142
Mis à jour
20 oct.