Define Parameters To Calibrate
PREREQUISITE: This skill needs an initialized jinko-sdk connection and an
SDK satisfying its metadata.requires_sdk range. Run the jinko-sdk-setup skill
(../jinko-sdk-setup/SKILL.md) and proceed only once its check passes. If that
skill is not found, install it from novainsilico/jinko-skills.
Classify model inputs from supplied evidence; do not infer unsupported provenance
or invent calibration steps.
Inputs
Require:
- a model SID;
- documentation or other evidence for the current input values;
- an explicit ordered list of calibration step identifiers and each step's biological
scope;
- any user overrides and whether existing labels may be replaced.
Labels
Assign at most one source tag per eligible input:
s::knowledge: supported by literature, expert knowledge, or a reference
model;s::arbitrary: deliberately fixed without an evidence-derived value;s::to-calibrate: insufficiently informed and intended for calibration;s::calibrated: preserve when present; never assign in this task.
Assign CalibIter::<step> only with s::to-calibrate, using an explicitly
provided step whose scope covers the input. Absence means the input is not
assigned to calibration. Leave uncertain inputs unchanged and report them.
Workflow
- Use
jinko-model to inspect parameters, categorical parameters, and species
initial conditions. Exclude derived formulas, technical infrastructure, and
non-input components.
- Preserve existing
s::* and CalibIter::* tags unless relabeling was
requested. For each remaining input, classify its source from the evidence.
- Map every
s::to-calibrate input to the first supplied step whose scope fully
covers its biological role. If no unique step qualifies, leave it unchanged
and add it to todo.
- Write the proposed mutations as JSON and run
scripts/apply_calibration_labels.py in dry-run mode, then with --apply
after review. The script validates source/step consistency, duplicate
assignments, component kinds, existing-label conflicts, and allowed model
mutations before applying one component batch.
- Re-fetch the model and return the new revision and snapshot with a compact
report: assigned and preserved labels, counts by source and step, and
todo
entries with reasons.
The mutation plan has this shape:
{
"in_scope_steps": ["2", "3"],
"assignments": [
{"component_id": "k_elim", "source": "to-calibrate", "calibration_step": "2"},
{"component_id": "body_weight", "source": "knowledge"}
]
}
Do not change values, units, descriptions, equations, structure, or unrelated
tags. todo items are reported, not encoded as placeholder tags.
1---2name: jinko-task-define-param-to-calibrate3description: Classify directly valued Jinkō model inputs by evidence source and assign inputs needing calibration to explicit calibration steps. Use when the user wants to decide which parameters, categorical parameters, or species initial conditions should be calibrated and record the decision with `s::*` and `CalibIter::*` tags. Do not use for choosing datasets, estimating priors, drafting calibration plans, or running calibrations.4license: MIT5---67# Define Parameters To Calibrate89> **PREREQUISITE:** This skill needs an initialized `jinko-sdk` connection and an10> SDK satisfying its `metadata.requires_sdk` range. Run the `jinko-sdk-setup` skill11> (`../jinko-sdk-setup/SKILL.md`) and proceed only once its check passes. If that12> skill is not found, install it from `novainsilico/jinko-skills`.1314Classify model inputs from supplied evidence; do not infer unsupported provenance15or invent calibration steps.1617## Inputs1819Require:2021- a model SID;22- documentation or other evidence for the current input values;23- an explicit ordered list of calibration step identifiers and each step's biological24 scope;25- any user overrides and whether existing labels may be replaced.2627## Labels2829Assign at most one source tag per eligible input:3031- `s::knowledge`: supported by literature, expert knowledge, or a reference32 model;33- `s::arbitrary`: deliberately fixed without an evidence-derived value;34- `s::to-calibrate`: insufficiently informed and intended for calibration;35- `s::calibrated`: preserve when present; never assign in this task.3637Assign `CalibIter::<step>` only with `s::to-calibrate`, using an explicitly38provided step whose scope covers the input. Absence means the input is not39assigned to calibration. Leave uncertain inputs unchanged and report them.4041## Workflow42431. Use `jinko-model` to inspect parameters, categorical parameters, and species44 initial conditions. Exclude derived formulas, technical infrastructure, and45 non-input components.462. Preserve existing `s::*` and `CalibIter::*` tags unless relabeling was47 requested. For each remaining input, classify its source from the evidence.483. Map every `s::to-calibrate` input to the first supplied step whose scope fully49 covers its biological role. If no unique step qualifies, leave it unchanged50 and add it to `todo`.514. Write the proposed mutations as JSON and run52 `scripts/apply_calibration_labels.py` in dry-run mode, then with `--apply`53 after review. The script validates source/step consistency, duplicate54 assignments, component kinds, existing-label conflicts, and allowed model55 mutations before applying one component batch.565. Re-fetch the model and return the new revision and snapshot with a compact57 report: assigned and preserved labels, counts by source and step, and `todo`58 entries with reasons.5960The mutation plan has this shape:6162```json63{64 "in_scope_steps": ["2", "3"],65 "assignments": [66 {"component_id": "k_elim", "source": "to-calibrate", "calibration_step": "2"},67 {"component_id": "body_weight", "source": "knowledge"}68 ]69}70```7172Do not change values, units, descriptions, equations, structure, or unrelated73tags. `todo` items are reported, not encoded as placeholder tags.
novainsilico