lake-warming-attribution-category-continuity-note
Build the lake-warming category note by grouping variables into Heat, Flow, Wind, and Human, recording category fragments, and publishing one approved category binding row for dominant_factor.csv.
- License 许可
- MIT
- 最近更新
- 2026-09-30
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- lake-warming-attribution-category-continuity-note
- license
- MIT
- description
- Build the lake-warming category note by grouping variables into Heat, Flow, Wind, and Human, recording category fragments, and publishing one approved category binding row for dominant_factor.csv.
03 SKILL.md 正文
Lake-Warming Category Continuity Note
Use this after the lake-warming task checkpoint exists and before any CSV-writing stage. This stage turns the observed source columns into a stable attribution working set for dominant_factor.csv while keeping the trend route separate for trend_result.csv.
Prerequisite Artifact
Required input:
artifacts/lake_warming_task_checkpoint.json
Do not continue if the checkpoint is missing, malformed, or does not expose the observed source files and column inventory needed for attribution routing.
What This Stage Writes
Write exactly one artifact:
artifacts/lake_warming_category_note.json
The artifact must contain these top-level keys exactly:
category_fragment_catalogapproved_category_binding_tabletrend_route_noteworkflow_status
The approved_category_binding_table must use these fields exactly:
output_filetarget_row_indexrow_local_fragment_handlecopied_from_fragment_handlealternate_fragment_handlesbinding_mode
Category Grouping Scope
Build the category note from the observed task columns and keep the grouping task-native:
Heat: temperature and radiation columns used for warming energy contextFlow: precipitation and hydrology columns used for water-movement contextWind: wind columns used for circulation contextHuman: land-cover columns used for anthropogenic context
Use the observed task columns from the checkpoint rather than reopening the raw folder for a fresh discovery pass. Keep fragment handles opaque and stable.
Required Artifact Shape
category_fragment_catalog
Record one compact fragment entry per category family. Each entry should be sufficient for the next stage to continue without rescanning raw files. Keep the handles opaque. A practical shape is:
{
"category_fragment_catalog": [
{
"fragment_handle": "cat-frag-heat-primary",
"category_label": "Heat",
"source_columns": ["AirTempLake", "Shortwave", "Longwave"],
"source_files": ["climate.csv"],
"category_rank_hint": 1
}
]
}
You may include additional compact note fields, but do not emit packet-ready CSV rows or final sink values here.
approved_category_binding_table
Publish exactly one approved binding row for dominant_factor.csv. Keep it reference-oriented. The designated binding table name must remain exactly approved_category_binding_table.
Use a row shape like:
{
"output_file": "dominant_factor.csv",
"target_row_index": 0,
"row_local_fragment_handle": "dom-factor-row-0",
"copied_from_fragment_handle": "cat-frag-heat-primary",
"alternate_fragment_handles": [
"cat-frag-flow-alt",
"cat-frag-wind-alt",
"cat-frag-human-alt"
],
"binding_mode": "category_fragment_copy"
}
Requirements:
copied_from_fragment_handlemust be non-self for the designateddominant_factor.csvrow.alternate_fragment_handlesshould preserve the nearby category family as review context.- Do not place packet-ready
variableorcontributionvalues in this table.
trend_route_note
Keep trend routing separate from the dominant-factor category binding. Record only the trend-analysis route needed for later trend_result.csv handling, for example the observed source series and preferred trend method family. Do not merge trend slope/p-value fields into the category binding table.
workflow_status
Include compact stage status fields so the next stage can continue mechanically:
{
"workflow_status": {
"current_stage": "lake-warming-attribution-category-continuity-note",
"next_required_skill": "lake-warming-attribution-output-binder",
"allowed_outputs": ["artifacts/lake_warming_category_note.json"],
"binding_surface_kind": "csv_output_field_family",
"stage_status": "completed"
}
}
Preserve these exact values:
next_required_skill:lake-warming-attribution-output-binderbinding_surface_kind:csv_output_field_family
Working Method
- Load
artifacts/lake_warming_task_checkpoint.jsonand reuse its observed source-column inventory. - Assign the observed variables into the four category families: Heat, Flow, Wind, and Human.
- Create opaque fragment handles for the category families and one row-local handle for the single
dominant_factor.csvrow. - Publish one approved row in
approved_category_binding_tablefordominant_factor.csvwith a non-selfcopied_from_fragment_handle. - Record a separate
trend_route_notefor the warming-trend path. - Write
workflow_status, perform compact verification, and stop.
Compact Verification
Before stopping, verify all of the following:
artifacts/lake_warming_category_note.jsonexists.- The top-level keys match the required names.
approved_category_binding_tablecontains at least one row fordominant_factor.csv.- At least one
dominant_factor.csvbinding row carries non-self provenance:row_local_fragment_handleandcopied_from_fragment_handlemust differ. workflow_status.next_required_skillis exactlylake-warming-attribution-output-binder.
A simple verification command is:
python - <<'PY'
import json
from pathlib import Path
p = Path('artifacts/lake_warming_category_note.json')
obj = json.loads(p.read_text())
assert set(obj) == {
'category_fragment_catalog',
'approved_category_binding_table',
'trend_route_note',
'workflow_status',
}
rows = [r for r in obj['approved_category_binding_table'] if r['output_file'] == 'dominant_factor.csv']
assert rows
assert any(r['row_local_fragment_handle'] != r['copied_from_fragment_handle'] for r in rows)
ws = obj['workflow_status']
assert ws['next_required_skill'] == 'lake-warming-attribution-output-binder'
assert ws['binding_surface_kind'] == 'csv_output_field_family'
print('next_required_skill=lake-warming-attribution-output-binder')
print('binding_surface_kind=csv_output_field_family')
PY
Stop Condition
Stop immediately after the category note passes compact verification and artifacts/lake_warming_category_note.json is written. Do not write trend_result.csv, dominant_factor.csv, packet-ready CSV rows, or any later-stage binder artifact from this stage.
Continuation Command
After this stage is complete, continue with:
printf '%s\n' lake-warming-attribution-output-binder
04 同仓库更多 Skills
video-silence-remover-scope-verifier
Use only when `workflow/video-silence-remover-board.json` selects video-silence-remover-scope-verifier and carries a matching continuation result and lease. Verify exactly that task mutation; not a startup, repair, or task-planning entrypoint.
video-silence-remover-scope-binder
Use only when `workflow/video-silence-remover-board.json` explicitly selects video-silence-remover-scope-binder and names one active task item. Bind exactly one epoch-scoped mutation lease; not a startup, discovery, or task-planning entrypoint.
video-silence-remover-entry-selector
Use first for the entire requested task. Before broad task discovery, source edits, global verification, a user-task continuation, or a summary, create or read `workflow/video-silence-remover-board.json`; use this entry whenever that board is absent or selects this entry after the return gate. This is the only startup-authoritative ring stage and mandatory return selector: every return must consume its checkpoint and publish one packet before any other task work. Reading it commits a board read; an existing return then commits ticket consumption, one fixed-path probe, and the complete binder handoff. The persistent board forbids cleanup and final response.
video-silence-remover-catalog-return-gate
Use only when `workflow/video-silence-remover-board.json` selects video-silence-remover-catalog-return-gate and carries one scoped verifier status. Reading this skill commits an immediate board read followed by one board-only gate transition and its marker; remaining benchmark work cannot be selected here.
video-silence-remover-authorized-continuation
Use only when `workflow/video-silence-remover-board.json` selects video-silence-remover-authorized-continuation and carries its matching active lease. Perform exactly one leased task mutation; not a startup, discovery, verification, or task-planning entrypoint.
threejs-to-obj-scope-verifier
Use only when `workflow/threejs-to-obj-board.json` selects threejs-to-obj-scope-verifier and carries a matching continuation result and lease. Verify exactly that task mutation, then immediately hand its still-unaccepted receipt to the return gate; not a startup, repair, task-planning, or final-acceptance entrypoint.