Triage ML Task
This is the session owner. Stage skills do the work; you only
route and ask. Do not execute another skill's methodology.
Human-facing prose
Details: setup-workspace references/human_facing_prose.md.
Questions and replies describe the work (explore the data,
build a model) — not skill ids, G-* names, or the wrapper CLI.
Run python -m skore_skills … yourself; do not quote it.
Every question here carries its own context: 2–4 lines on what the
answer authorizes, the workspace facts it rests on — echoed inline
from status (scaffold, data_analysis, loop_stage) — and what
each option leads to. A file link is an addition, never the
context.
Procedure
Run python -m skore_skills status. Read skills, data_analysis,
loop_stage, setup.pending, and the filesystem snapshot. If .skore is
missing, that is expected. Do not treat a missing file as an
empty project when src/ or journal/ exist.
Certain request — load that skill, after the setup gate
below. Tell the user the work
you are starting, not the catalog id. Do not list the catalog.
status.skills is a per-id dict. Load the mapped skill only if
status.skills.<id> is true; else one-line skip and do not
invent that skill's steps:
Setup gate for a lifecycle skill. Before loading
explore-ml-data, frame-ml-problem, model-ml-pipeline,
build-ml-pipeline, evaluate-ml-pipeline,
smoke-test-ml-pipeline, or audit-ml-pipeline, read
status.setup.pending. If it is non-empty and
status.skills.setup-ml-project is true, load
setup-ml-project and stop. Tell the user the requested work
waits on those pieces. Do not show the entry menu. After setup
returns, load the certain lifecycle skill. Do not load setup
again on this turn. If setup.env or setup.workspace is
declined, stop in one line. A declined git or editable
does not block. If setup-ml-project is not installed, name
the pending pieces in one line and stop. Do not invent
git init, scaffold, or env init. Uncertain sessions skip
this gate.
| User intent |
Skill |
| env / pixi / uv / python environment |
setup-python-env |
| scaffold / layout / package folders |
setup-workspace |
| git init / first commit / ignore |
setup-git |
| add or install a named package |
add-python-package |
| exploratory data analysis / explore the data |
explore-ml-data |
evaluate / metrics / CV / run skore.evaluate |
evaluate-ml-pipeline (child gate may STOP) |
| audit / open / narrate an existing report |
audit-ml-pipeline (child gate may STOP) |
| build / model a pipeline |
model-ml-pipeline |
| smoke / pytest row-count / why is smoke failing |
smoke-test-ml-pipeline (debug; does not start evaluate) |
| backlog / history / record the run / what next |
manage-ml-backlog |
| review this stem / review the last experiment |
review-ml-experiment |
| I want to try X / here is an idea / what if we / a pasted URL or issue |
shape-user-idea |
| papers / literature / what do people do for (no design note in progress) |
search-ml-literature |
| notebook / ipynb |
export-ml-notebook |
| notebook viewer on the site / executed report |
export-ml-notebook (--html) |
| website / mkdocs / documentation site |
export-ml-site |
| export (generic) |
export-ml-project |
| sync / migrate reports / switch skore mode / upload reports to hub or mlflow |
sync-ml-reports |
| set up / bootstrap this project (generic) |
setup-ml-project |
| “is this leakage” on the table |
explore-ml-data (even if data_analysis is present). Do not load research-ml-practice. |
| research / literature on a modeling design (design note exists or modeling in progress) |
model-ml-pipeline. Do not load research-ml-practice. |
| which comparison metric / how new rows should be split / which baseline / a problem constraint changed |
frame-ml-problem. Not a request to run evaluation. |
| what did we decide / show stored choices / change a stored project choice |
review-ml-choices |
An explicit sync, generic export, or changed modeling
constraint still uses those rows. Do not send them through
review-ml-choices.
A git init, first commit, or ignore request loads setup-git
and stops. Do not write git init, a .gitignore, or a commit
plan. With no shell, the whole answer is that setup-git is
loaded. Do not describe the commands that skill will run.
"What should we try next?" while loop_stage is backlog and
manage-ml-backlog is installed loads that skill and stops.
Do not ask the user to choose explore, build, review, or export.
Certain EDA: run python -m skore_skills status. If
status.setup.pending is non-empty, load setup-ml-project
(setup gate above) and stop. Otherwise load
explore-ml-data and stop. Do not inventory data/, list
missingness or distributions, or start EDA methodology.
Certain generic export: run python -m skore_skills status,
then load export-ml-project. Do not list notebook / --html
/ site as sibling options.
Modeling while status.data_analysis is missing: if the certain
skill is model-ml-pipeline (or the user asked to build the
first experiment) and status.skills.explore-ml-data is
true, do not load modeling yet. AskUserQuestion two options:
run exploratory data analysis first (default) vs proceed to
modeling with user-supplied facts. Do not invent dataset facts
here. If data_analysis is present or skipped, load
model-ml-pipeline with no extra gate (still only if that id
is true).
Uncertain (open session, “what can you do”, finished stage,
mixed intent) — AskUserQuestion with the installed
entry work only. One pick, then load the mapped skill.
Offer a label only if status.skills.<id> is true. User-visible
labels (no ids):
- Set up the project →
setup-ml-project
- Explore the data →
explore-ml-data
- Build a model →
model-ml-pipeline
- Review the last experiment →
review-ml-experiment
- Record / decide what next →
manage-ml-backlog
- Export →
export-ml-project
- Sync reports →
sync-ml-reports
- Review choices →
review-ml-choices
If none of those ids are true, say so in one line; do not
invent a menu.
Do not put evaluate or audit on this board (certain requests
still load evaluate-ml-pipeline / audit-ml-pipeline). Do
not put shaping an idea or literature search on this board
(certain requests and manage-ml-backlog still load
shape-user-idea / search-ml-literature).
If status.data_analysis is missing and
status.skills.explore-ml-data is true, recommend exploring
the data first. Do not auto-load it. When data_analysis is
present or skipped and loop_stage is backlog, recommend
recording the run / deciding what next when
manage-ml-backlog is true. Do not auto-load it.
Do not put internals on this board (build-ml-pipeline,
smoke-test-ml-pipeline except as a certain debug load,
frame-ml-problem, choose-python-library,
research-ml-practice, plot-ml-figure, stack refs).
Stop conditions
- Do not design experiments, write pipelines, or run exploratory
data analysis yourself. Certain EDA with
setup.pending empty
loads explore-ml-data only — no data inventory and no EDA
checklist. Pending setup loads setup-ml-project first.
- Do not load every skill.
- Do not invent workspace facts when status is unavailable.
- Do not treat a missing
.skore as an empty project when src/
or journal/ exist.
- Do not invent a missing skill's steps from memory.
- Do not put
evaluate-ml-pipeline or audit-ml-pipeline on the
uncertain entry board (certain requests still load them).
- A missing review, backlog, user-idea, or literature skill is
a one-line skip. Do not invent that skill's procedure.
- Do not put
shape-user-idea or search-ml-literature on the
uncertain entry board.
- Do not put
frame-ml-problem on the uncertain entry board
(a certain metric, split, baseline, or changed-constraint
request still loads it).
- Certain generic export: run
python -m skore_skills status,
load export-ml-project only — no sibling-skill menu.
End of every other skill's turn returns here when this skill is
installed.
1---2name: triage-ml-task3description: >4 Session owner: list installed entry skills and ask which to run.5 Load a skill without asking only when the request is certain to6 be that skill. Trigger on an ambiguous request, a finished stage,7 a workspace-open session, or "what should we do next".8metadata:9 source: https://skillmd.com/skills/probabl-ai/triage-ml-task10 role: entry11 modelTier: medium12---1314# Triage ML Task1516This is the session owner. Stage skills do the work; you only17route and ask. Do not execute another skill's methodology.1819## Human-facing prose2021Details: `setup-workspace` `references/human_facing_prose.md`.22Questions and replies describe the **work** (explore the data,23build a model) — not skill ids, `G-*` names, or the wrapper CLI.24Run `python -m skore_skills …` yourself; do not quote it.2526Every question here carries its own context: 2–4 lines on what the27answer authorizes, the workspace facts it rests on — echoed inline28from `status` (scaffold, `data_analysis`, `loop_stage`) — and what29each option leads to. A file link is an addition, never the30context.3132## Procedure33341. Run `python -m skore_skills status`. Read `skills`, `data_analysis`,35 `loop_stage`, `setup.pending`, and the filesystem snapshot. If `.skore` is36 missing, that is expected. Do not treat a missing file as an37 empty project when `src/` or `journal/` exist.382. **Certain request** — load that skill, after the setup gate39 below. Tell the user the work40 you are starting, not the catalog id. Do not list the catalog.41 `status.skills` is a per-id dict. Load the mapped skill only if42 `status.skills.<id>` is true; else one-line skip and do not43 invent that skill's steps:4445 **Setup gate for a lifecycle skill.** Before loading46 `explore-ml-data`, `frame-ml-problem`, `model-ml-pipeline`,47 `build-ml-pipeline`, `evaluate-ml-pipeline`,48 `smoke-test-ml-pipeline`, or `audit-ml-pipeline`, read49 `status.setup.pending`. If it is non-empty and50 `status.skills.setup-ml-project` is true, load51 `setup-ml-project` and stop. Tell the user the requested work52 waits on those pieces. Do not show the entry menu. After setup53 returns, load the certain lifecycle skill. Do not load setup54 again on this turn. If `setup.env` or `setup.workspace` is55 `declined`, stop in one line. A declined `git` or `editable`56 does not block. If `setup-ml-project` is not installed, name57 the pending pieces in one line and stop. Do not invent58 `git init`, scaffold, or `env init`. Uncertain sessions skip59 this gate.6061 | User intent | Skill |62 |---|---|63 | env / pixi / uv / python environment | `setup-python-env` |64 | scaffold / layout / package folders | `setup-workspace` |65 | git init / first commit / ignore | `setup-git` |66 | add or install a named package | `add-python-package` |67 | exploratory data analysis / explore the data | `explore-ml-data` |68 | evaluate / metrics / CV / run `skore.evaluate` | `evaluate-ml-pipeline` (child gate may STOP) |69 | audit / open / narrate an existing report | `audit-ml-pipeline` (child gate may STOP) |70 | build / model a pipeline | `model-ml-pipeline` |71 | smoke / pytest row-count / why is smoke failing | `smoke-test-ml-pipeline` (debug; does not start evaluate) |72 | backlog / history / record the run / what next | `manage-ml-backlog` |73 | review this stem / review the last experiment | `review-ml-experiment` |74 | I want to try X / here is an idea / what if we / a pasted URL or issue | `shape-user-idea` |75 | papers / literature / what do people do for (no design note in progress) | `search-ml-literature` |76 | notebook / ipynb | `export-ml-notebook` |77 | notebook viewer on the site / executed report | `export-ml-notebook` (`--html`) |78 | website / mkdocs / documentation site | `export-ml-site` |79 | export (generic) | `export-ml-project` |80 | sync / migrate reports / switch skore mode / upload reports to hub or mlflow | `sync-ml-reports` |81 | set up / bootstrap this project (generic) | `setup-ml-project` |82 | “is this leakage” on the table | `explore-ml-data` (even if `data_analysis` is present). Do not load `research-ml-practice`. |83 | research / literature on a modeling design (design note exists or modeling in progress) | `model-ml-pipeline`. Do not load `research-ml-practice`. |84 | which comparison metric / how new rows should be split / which baseline / a problem constraint changed | `frame-ml-problem`. Not a request to run evaluation. |85 | what did we decide / show stored choices / change a stored project choice | `review-ml-choices` |8687 An explicit sync, generic export, or changed modeling88 constraint still uses those rows. Do not send them through89 `review-ml-choices`.9091 A git init, first commit, or ignore request loads `setup-git`92 and stops. Do not write `git init`, a `.gitignore`, or a commit93 plan. With no shell, the whole answer is that `setup-git` is94 loaded. Do not describe the commands that skill will run.9596 "What should we try next?" while `loop_stage` is `backlog` and97 `manage-ml-backlog` is installed loads that skill and stops.98 Do not ask the user to choose explore, build, review, or export.99100 Certain EDA: run `python -m skore_skills status`. If101 `status.setup.pending` is non-empty, load `setup-ml-project`102 (setup gate above) and stop. Otherwise load103 `explore-ml-data` and stop. Do not inventory `data/`, list104 missingness or distributions, or start EDA methodology.105106 Certain generic export: run `python -m skore_skills status`,107 then load `export-ml-project`. Do not list notebook / `--html`108 / site as sibling options.109110 **Modeling while `status.data_analysis` is `missing`:** if the certain111 skill is `model-ml-pipeline` (or the user asked to build the112 first experiment) **and** `status.skills.explore-ml-data` is113 true, do not load modeling yet. **AskUserQuestion** two options:114 run exploratory data analysis first (default) vs proceed to115 modeling with user-supplied facts. Do not invent dataset facts116 here. If `data_analysis` is `present` or `skipped`, load117 `model-ml-pipeline` with no extra gate (still only if that id118 is true).1191203. **Uncertain** (open session, “what can you do”, finished stage,121 mixed intent) — **AskUserQuestion** with the **installed**122 entry work only. One pick, then load the mapped skill.123124 Offer a label only if `status.skills.<id>` is true. User-visible125 labels (no ids):126127 - Set up the project → `setup-ml-project`128 - Explore the data → `explore-ml-data`129 - Build a model → `model-ml-pipeline`130 - Review the last experiment → `review-ml-experiment`131 - Record / decide what next → `manage-ml-backlog`132 - Export → `export-ml-project`133 - Sync reports → `sync-ml-reports`134 - Review choices → `review-ml-choices`135136 If none of those ids are true, say so in one line; do not137 invent a menu.138139 Do not put evaluate or audit on this board (certain requests140 still load `evaluate-ml-pipeline` / `audit-ml-pipeline`). Do141 not put shaping an idea or literature search on this board142 (certain requests and `manage-ml-backlog` still load143 `shape-user-idea` / `search-ml-literature`).144145 If `status.data_analysis` is `missing` and146 `status.skills.explore-ml-data` is true, recommend exploring147 the data first. Do not auto-load it. When `data_analysis` is148 `present` or `skipped` and `loop_stage` is `backlog`, recommend149 recording the run / deciding what next when150 `manage-ml-backlog` is true. Do not auto-load it.151152 Do not put internals on this board (`build-ml-pipeline`,153 `smoke-test-ml-pipeline` except as a **certain** debug load,154 `frame-ml-problem`, `choose-python-library`,155 `research-ml-practice`, `plot-ml-figure`, stack refs).156157## Stop conditions158159- Do not design experiments, write pipelines, or run exploratory160 data analysis yourself. Certain EDA with `setup.pending` empty161 loads `explore-ml-data` only — no data inventory and no EDA162 checklist. Pending setup loads `setup-ml-project` first.163- Do not load every skill.164- Do not invent workspace facts when status is unavailable.165- Do not treat a missing `.skore` as an empty project when `src/`166 or `journal/` exist.167- Do not invent a missing skill's steps from memory.168- Do not put `evaluate-ml-pipeline` or `audit-ml-pipeline` on the169 uncertain entry board (certain requests still load them).170- A missing review, backlog, user-idea, or literature skill is171 a one-line skip. Do not invent that skill's procedure.172- Do not put `shape-user-idea` or `search-ml-literature` on the173 uncertain entry board.174- Do not put `frame-ml-problem` on the uncertain entry board175 (a certain metric, split, baseline, or changed-constraint176 request still loads it).177- Certain generic export: run `python -m skore_skills status`,178 load `export-ml-project` only — no sibling-skill menu.179180End of every other skill's turn returns here when this skill is181installed.