PyMeasure Instrument-Control Reference

This is the pymeasure skill for Agent Kaizen: an original-prose reference package derived from the PyMeasure documentation, with API identifiers, class names, parameter names, resource strings, and numeric values preserved exactly.

What this skill covers

PyMeasure is the Python library for scientific measurement, instrument control, and experiment automation, built on PyVISA. This skill covers the Instrument/Channel base classes and dynamic properties, instrument drivers organized by manufacturer (Keithley, Agilent/Keysight, HP, Lake Shore, SRS, Tektronix, Rohde & Schwarz, and more), and the Adapters that handle VISA, serial, Prologix, and TCP connections. It also covers the Procedure/Experiment/Worker automation framework, Results storage, plotting/display, and the end-to-end measurement workflow. It is not for the Python standard library, raw PyVISA, or other instrument-control libraries.

What's inside

• SKILL.md - the skill entry point: trigger description, workflow, and pointers into the reference set.
• references/ - all depth, one subject per file, plus INDEX.md for browsing and topics.json for metadata-driven lookup.
• GOTCHA.md - recurring failure modes, including exact identifier handling, PyVISA backend requirements, and version-sensitive drivers.

Use it

The published skill lives at <devroot>\SKILLS\skills\pymeasure and is linked into each agent surface as a per-skill junction. Edit the store copy directly; do not copy it through .agents or .claude.

Status

The reference prose has been recontextualized into original AGPL-licensable wording. Upstream identifiers are intentionally preserved verbatim.

Reducing idle context cost (skill invocation policy)

Every installed skill costs a little context on every session: the agent sees each skill's name and description before you ever use it. If you rarely use this skill in a given project, you can keep it installed and still explicitly invocable while hiding it from the model's automatic listing.

Doing so does not modify this skill's source repo — the policy lives in your local agent settings. The Agent Kaizen skill-drafting repo ships a manager, scripts/skill_policy.py, that sets this for all your skills at once:

python skill_policy.py audit     # list every skill + its current policy + idle cost
python skill_policy.py plan      # write a decision file with recommendations (nothing applied)
# edit that decision file: set selected_policy + approved:true for the skills you choose
python skill_policy.py preview   # show the exact change
python skill_policy.py apply     # apply ONLY what you approved (backup + rollback recorded)
python skill_policy.py restore   # roll back

• Claude Code (works today): writes skillOverrides: { "<skill>": "user-invocable-only" } to .claude/settings.local.json — zero idle listing cost, still available from the /skills menu. Start a new session for it to take effect; invoke it any time via /skills.
• Codex (currently unreliable): explicit-only Codex skills are affected by an open bug (openai/codex#23454) where $skill invocation of an explicit-only local skill can fail. Until it's fixed, leave Codex skills implicit, or fully disable rarely-used ones with [[skills.config]] enabled = false in config.toml. The manager audits Codex but does not change Codex policy.