sensor-calibration-workbench — Claude Code skill: sensor calibration
The sensor-calibration-workbench skill guides sensor calibration from warm-up and reference readings to coefficient storage and drift checks for CO2, load-cell, magnetic, color, and analog sensors.
MIT 137 installs ★ 33 updated 2026-10-15
npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a claude-codeWhat sensor-calibration-workbench does
The skill helps investigate unstable or implausible readings, offset and scale errors, and values that degrade over time. It separates one-point and zero-offset work from two-point scaling, multi-orientation calibration, and calibration tied to environmental conditions.
The workflow starts by recording reference values, warm-up state, ambient conditions, and sample stability. It then covers coefficient persistence and rules for revalidation after a reboot, firmware update, or field drift. Supporting references cover the calibration flow, common warm-up and saturation mistakes, and persistence decisions. A known reference is required; otherwise coefficient tuning is guesswork.
Verification checks convergence toward the reference, repeat-sample stability, and coefficient reload after restart. When the sensor is not detected at all, hardware or bus bring-up comes first, so this skill is the wrong starting point for that failure.
What it helps with
- diagnose unstable sensor readings
- tune zero offset or measurement scale
- collect reference evidence before changing coefficients
- persist calibration values in EEPROM or flash
- revalidate readings after restart or firmware updates
Example prompts for the agent
- Investigate unstable readings from my CO2 sensor and outline a calibration workflow.
- Tune a two-point calibration for this load cell using known reference values.
- Decide how to persist the sensor coefficients and when to revalidate them after a reboot.
How to install sensor-calibration-workbench
1Skills CLI (Vercel)
npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a claude-code2Manually: put the files in place
~/.claude/skills/sensor-calibration-workbench/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/sensor-calibration-workbench/
1Skills CLI (Vercel)
npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a codex2Manually: put the files in place
.agents/skills/sensor-calibration-workbench/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a cursor2Manually: put the files in place
.cursor/skills/sensor-calibration-workbench/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wedsamuel1230/embedded-engineering-skills skills/sensor-calibration-workbench2Manually: put the files in place
.github/skills/sensor-calibration-workbench/SKILL.md1Skills CLI (Vercel)
npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a gemini-cli2Platform CLI
gemini skills install https://github.com/wedsamuel1230/embedded-engineering-skills --path skills/sensor-calibration-workbenchManually: put the files in place
.devin/skills/sensor-calibration-workbench/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about sensor-calibration-workbench
How do I install sensor-calibration-workbench in Claude Code?
Run npx skills add wedsamuel1230/embedded-engineering-skills --skill sensor-calibration-workbench -a claude-code. The skill file will be available at ~/.claude/skills/sensor-calibration-workbench/SKILL.md.
What does sensor-calibration-workbench do?
It helps choose a calibration class, gather reference evidence, account for warm-up, and persist coefficients with metadata for later checks. It also separates calibration symptoms from hardware and environmental problems.
Should I use it when the sensor is not detected?
No. Start with hardware or bus bring-up in that case, using a skill such as i2c-bringup-diagnostician or circuit-debugger.
Source text
SKILL.md · MIT
---
name: sensor-calibration-workbench
description: Use when makers need calibration workflows for sensors such as CO2 sensors, load cells, magnetometers, color sensors, or analog sensors, including warm-up behavior, reference measurements, coefficient storage, and drift checks.
metadata: {triggers: "sensor calibration, reference measurement, drift, coefficient"}
---
# Sensor Calibration Workbench
Use this skill when the sensor technically works, but the readings are not yet
trustworthy enough for the project.
## Resources
- `references/calibration-flow.md` - end-to-end calibration workflow and evidence checklist
- `references/common-failure-patterns.md` - warm-up, scaling, drift, saturation, and environment mistakes
- `references/persistence-and-revalidation.md` - storing coefficients and deciding when recalibration is needed
## When to Use
Use this skill when the request involves:
- volatile or implausible sensor readings
- "how do I calibrate this sensor?"
- load-cell factor tuning
- CO2, magnetometer, or color-sensor calibration
- storing calibration coefficients in EEPROM or flash
- deciding whether the problem is calibration, hardware, or environment
Do not use this skill when the sensor is not detected at all. That should route
through hardware or bus bring-up first.
## Workflow
1. Confirm the measurement problem:
- unstable -> open `references/common-failure-patterns.md`
- offset or scaling error -> open `references/calibration-flow.md`
- values good once but bad later -> open
`references/persistence-and-revalidation.md`
2. Identify the calibration class:
- one-point or zero-offset
- two-point scale calibration
- multi-orientation or environmental calibration
3. Collect reference evidence before changing coefficients:
- known reference values
- warm-up state
- ambient conditions
- sample stability
4. Decide how calibration values will persist and how revalidation will be
triggered after reboot, firmware update, or field drift.
## Core Rules
- Calibration without a known reference is guesswork.
- Warm-up and stabilization time are part of calibration, not a side note.
- Do not mix hardware-fault symptoms with coefficient-tuning symptoms.
- Store both the calibration values and enough metadata to know when they became
stale.
## Verification
- Confirm readings converge toward a known reference after calibration.
- Confirm the calibrated values stay stable across repeated samples.
- Confirm stored coefficients reload correctly after restart.
- If the project has operating thresholds, verify those thresholds against the
calibrated output rather than the raw sensor value.
## Integration
- Pair with `i2c-bringup-diagnostician` or `circuit-debugger` when the sensor is
not yet electrically trustworthy.
- Pair with `arduino-code-generator` when the user needs persistence or
filtering code added to the sketch.
- Pair with `field-power-and-connectivity-triager` when sensor behavior changes
only off USB or under field power conditions.
## Shared Output Contract
Use [the shared Arduino skill contract](../../docs/arduino-skill-contract.md):
state assumptions, required tools and versions, implementation steps,
tests/evidence by proof stage, known limitations, and recovery/security notes.
© wedsamuel1230 · MIT · wedsamuel1230/embedded-engineering-skills