matlab/matlab-agentic-toolkit / skills-catalog/control-systems/matlab-extract-battery-features
matlab-extract-battery-features
VerifiedExtract battery features in MATLAB from voltage, current, and temperature measurements: multi-cycle cycling tests, HPPC / pulse tests, EIS impedance sweeps, or a single in-field charge or discharge segment. Use when the user asks for battery features, or for SOH, RUL, degradation, internal-resistance, or impedance analysis that needs them. Output is a feature table; does not train SOH / RUL models. Do not trigger only because battery data is present. Triggers on battery* functions such as batteryTestDataParser, batteryTestFeatureExtractor, batteryPulseFeatures, batteryEISFeatures.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 21.6 KB |
| manifest.yaml | config | 469 B |
| references/cycling-pipeline.md | markdown | 21.1 KB |
| references/cycling/feature-selection.md | markdown | 2.6 KB |
| references/cycling/multi-cell.md | markdown | 5.1 KB |
| references/cycling/postprocess.md | markdown | 2.4 KB |
| references/cycling/schedule-verification.md | markdown | 4.2 KB |
| references/cycling/tolerance-tuning.md | markdown | 2.4 KB |
| references/eis-features.md | markdown | 10.8 KB |
| references/individual-cycling-functions.md | markdown | 10.1 KB |
| references/parameter-tuning.md | markdown | 14.2 KB |
| references/pulse-features.md | markdown | 12.6 KB |
| scripts/checkCyclingProtocol.m | other | 9.2 KB |
| scripts/sweepScheduleAndReport.m | other | 3.7 KB |
| scripts/verifyAgainstSchedule.m | other | 8.5 KB |
| scripts/verifySegmentation.m | other | 6.3 KB |
| scripts/verifySingleSegment.m | other | 3.0 KB |
references/cycling/schedule-verification.md
View on GitHub# Cycling: Verify and Tune Against a Tester Schedule (Route B)
Load this in addition to `references/cycling-pipeline.md` only when the **user provides the tester schedule** (per-step Type: CC / CV / Rest / CCCV). It replaces Route A (`verifySegmentation`) in Phase 4a and the Route A sweep in Phase 5. Do not chain the two routes — a schedule is authoritative when present.
Set the MATLAB current folder to the skill's `scripts/` directory (MCP `project_path`) — `verifyAgainstSchedule` and `sweepScheduleAndReport` live there.
## Phase 4a — Verify segmentation against the schedule
Build the schedule as a struct array (one entry per `Step_Index`) with `Type ∈ {"CC","CV","Rest","CCCV"}`. See `verifyAgainstSchedule.m` header for the full field list (`MinCoverage`, `MinCC`, `MinCV`, `TransitionVoltage`, `TransitionTol`, `MaxUndefinedFrac`, `MinSamples`).
```matlab
schedule = struct( ...
'Step', {1, 2, 3, 4, 5}, ...
'Type', {"CC", "CV", "Rest", "CC", "Rest"}, ...
'MinCoverage', {0.85, 0.30, 0.95, 0.60, 0.95});
report = verifyAgainstSchedule(parser, schedule);
```
`report.PerCycle.AllStepsPass` tells you which cycles match the declared protocol. `report.PerGroup.Reason` names the failure mode per (Cycle, Step). CCCV steps additionally produce `report.AgingSignals` — transition voltage / CC-fraction / CV-fraction / taper duration per CCCV step — usable as protocol-derived features that the standard extractor misses.
The `MinSamples` gate in `verifyAgainstSchedule` runs before the mode check, so a step with fewer than `MinSamples` samples is reported as a data-collection failure (`"data-collection: only <n> samples (< <min>)"`) rather than being misclassified as a mode issue.
All cycles pass → continue with Phase 4b in `references/cycling-pipeline.md`. If any cycle fails, run the Phase 5 sweep below.
## Phase 5 — Tolerance sweep + data-collection exclusion
When schedule-based verification fails, cycles fall into three shapes:
1. **`alwaysPass`** — pass at every Tolerance in the sweep; no tuning needed.
2. **`tolSensitive`** — pass at some Tolerance values but not others; fixable by picking the right Tolerance.
3. **`neverPass`** — fail at every Tolerance; typically means truncated / missing samples (data-collection issue). **Never tune Tolerance to try to fix these; exclude them.**
`sweepScheduleAndReport` runs the sweep once, classifies each cycle, picks the largest Tolerance satisfying every `tolSensitive` cycle, and returns `neverPass` as `ExcludedCycles`:
```matlab
mapping = struct('CurrentVariable', "Current", 'VoltageVariable', "Voltage", ...
'TimeVariable', "DateTime", 'CycleIndexVariable', "Cycle_Index", ...
'StepIndexVariable', "Step_Index", 'TemperatureVariable', "Temperature");
out = sweepScheduleAndReport(tbl, schedule, mapping, [5e-5, 1e-5, 5e-6, 1e-6]);
parser.Tolerance = out.BestTol;
parser.ExcludedCycles = out.ExcludedCycles;
```
### When every cycle fails at every Tolerance — check the schedule before the data
If `sweepScheduleAndReport` classifies every cycle as `neverPass`, the schedule specification is more likely wrong than the data. Common cases:
- **Unreachable `MinCoverage`** on a soft-transition step (e.g., asserting `CV MinCoverage = 0.30` on a step where the CV portion is 0-15% for the true protocol) — no Tolerance value can bring the CV fraction above 30%. Set `MinCoverage = 0.0` on that step (soft check) and re-run.
- **Tester-inserted artifact steps** (1-3 sample steps between stages) declared in the schedule — those should not be asserted; drop them from `schedule`.
- **CCCV declared as separate CC + CV** or vice versa — check the tester log; a single composite step with both CC and CV samples must use `Type: "CCCV"`.
Only after the schedule has been reviewed and the sweep still fails should you conclude the data has a systematic collection issue.
### STOP: every cycle still `neverPass`
STOP and present `out.PassMap`, `out.PerToleranceReports{end}.PerCycle.FirstFailReason`, and the schedule that was asserted. The data may be pre-averaged or the chemistry may need a different classifier — ask the user before proceeding with a Tolerance choice or before dropping the schedule.
----
Copyright 2026 The MathWorks, Inc.
----
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |