CMA-ES Calibration Task
Execute a confirmed calibration specification. Do not invent objectives,
constraints, parameter priors, optimizer options, or acceptance criteria.
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.
Inputs
Require:
- a model SID;
- parameter priors with physical bounds;
seed, thresholdWeightedScore, numberOfIterations, and populationSize;- at least one fitness source: calibration-ready data tables and/or an advanced
output set containing objectives;
- any protocol, simple output set, advanced output set, folder, and name needed
by the specification.
If quantitative evidence has not yet been converted into a calibration-ready
table, use jinko-task-extract-data-table. Use jinko-data-table,
jinko-output-set, jinko-model, and jinko-protocol only for their respective
Jinkō object mechanics.
Workflow
- Resolve every input to its intended SID and snapshot. Present missing or
ambiguous inputs instead of guessing.
- Use
jinko-calibration-cmaes and its bundled creation script. Review its
dry-run output before applying it. The script owns parameter encoding,
fitness-table eligibility, bound scaling, creation, and post-creation sanity;
stop on an error and surface warnings.
- Return the created calibration SID, revision, snapshot, URL, and effective
options for confirmation.
- Use the lower-level run script to perform pre-launch sanity, launch, and wait
for a terminal state. Do not relaunch a terminal snapshot; create or update a
configuration so the intended change has a new snapshot.
- Use the lower-level inspection interfaces to collect the final status,
stopping reason, performance, results summary, objective weights, and the
patient sorted first by
optimizationWeightedScore when available. Fetch
per-patient scalars, timeseries, errors, or augmented data tables only when
their required selectors are present in the result metadata.
Return
Return:
- calibration SID, revision, snapshot, and URL;
- effective input references, priors, and optimizer options;
- sanity warnings, terminal status, stopping reason, and performance;
- supported result payloads and best-patient identity, with the iteration and
scenario arm needed for subsequent result calls;
- a concise account of unavailable requested outputs.
Do not claim a separate run ID, convergence analysis, score-evolution curve,
best-patient parameter values, parameter posterior, or simulation-vs-data plot
unless the returned API payloads actually provide the required data.
1---2name: jinko-task-cmaes3description: Execute a CMA-ES calibration from confirmed Jinkō inputs: assemble the model, protocol, output sets, fitness data tables, parameter priors, and optimizer options; create and run the Calibration; and return the supported results. Use when the user wants to perform a CMA-ES calibration, not when they need to choose a calibration strategy, infer priors, design objectives, or decide whether results are acceptable.4license: MIT5---67# CMA-ES Calibration Task89Execute a confirmed calibration specification. Do not invent objectives,10constraints, parameter priors, optimizer options, or acceptance criteria.1112> **PREREQUISITE:** This skill needs an initialized `jinko-sdk` connection and an13> SDK satisfying its `metadata.requires_sdk` range. Run the `jinko-sdk-setup` skill14> (`../jinko-sdk-setup/SKILL.md`) and proceed only once its check passes. If that15> skill is not found, install it from `novainsilico/jinko-skills`.1617## Inputs1819Require:2021- a model SID;22- parameter priors with physical bounds;23- `seed`, `thresholdWeightedScore`, `numberOfIterations`, and `populationSize`;24- at least one fitness source: calibration-ready data tables and/or an advanced25 output set containing objectives;26- any protocol, simple output set, advanced output set, folder, and name needed27 by the specification.2829If quantitative evidence has not yet been converted into a calibration-ready30table, use `jinko-task-extract-data-table`. Use `jinko-data-table`,31`jinko-output-set`, `jinko-model`, and `jinko-protocol` only for their respective32Jinkō object mechanics.3334## Workflow35361. Resolve every input to its intended SID and snapshot. Present missing or37 ambiguous inputs instead of guessing.382. Use `jinko-calibration-cmaes` and its bundled creation script. Review its39 dry-run output before applying it. The script owns parameter encoding,40 fitness-table eligibility, bound scaling, creation, and post-creation sanity;41 stop on an error and surface warnings.423. Return the created calibration SID, revision, snapshot, URL, and effective43 options for confirmation.444. Use the lower-level run script to perform pre-launch sanity, launch, and wait45 for a terminal state. Do not relaunch a terminal snapshot; create or update a46 configuration so the intended change has a new snapshot.475. Use the lower-level inspection interfaces to collect the final status,48 stopping reason, performance, results summary, objective weights, and the49 patient sorted first by `optimizationWeightedScore` when available. Fetch50 per-patient scalars, timeseries, errors, or augmented data tables only when51 their required selectors are present in the result metadata.5253## Return5455Return:5657- calibration SID, revision, snapshot, and URL;58- effective input references, priors, and optimizer options;59- sanity warnings, terminal status, stopping reason, and performance;60- supported result payloads and best-patient identity, with the iteration and61 scenario arm needed for subsequent result calls;62- a concise account of unavailable requested outputs.6364Do not claim a separate run ID, convergence analysis, score-evolution curve,65best-patient parameter values, parameter posterior, or simulation-vs-data plot66unless the returned API payloads actually provide the required data.
novainsilico