consolidate-sensors

Distill runtime verdicts and progress into per-sensor append-only bullets with citations.

2|Updated Apr 25, 2026

Search Tags:#automation #sensors #calibration #append-only #consolidate #runtime-verdicts

Ready to run

npx skills add https://github.com/iurykrieger/claude-yoke --skill consolidate-sensors

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: consolidate-sensors
Source: https://github.com/iurykrieger/claude-yoke/tree/main/skills/consolidate-sensors
Command: npx skills add https://github.com/iurykrieger/claude-yoke --skill consolidate-sensors

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Distills active task evidence from runtime verdicts and progress into per-sensor files, creating an auditable, append-only record that guides sensor maintenance and calibration.

Core Features & Use Cases

Per-sensor distillation: converts cycle verdicts and progress data into per-sensor notes with mandatory citations.
Append-only governance: preserves history by appending bullets to sensor bodies and recalibrating frontmatter costs when drift is detected.
Calibration readiness: supports diffs for Known issues, Frequent errors, and Calibration sections to improve reliability of sensors across cycles.

Quick Start

Run the consolidation to append per-sensor bullets from the current verdicts and progress into their respective files.

Frequently Asked Questions about consolidate-sensors

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I consolidate runtime verdicts into per-sensor append-only notes?▼

Consolidating runtime verdicts into per-sensor append-only notes requires distilling evidence from cycle verdicts and progress data, then appending bullets with citations to individual sensor files. This process reads runtime files to compute diffs and trigger frontmatter recalibration.

What is sensor calibration maintenance based on runtime evidence?▼

Sensor calibration maintenance based on runtime evidence is the process of distilling active task progress and verdicts into auditable, append-only per-sensor records. It tracks known issues and frequent errors to improve sensor reliability across cycles via frontmatter recalibration.

How do I automate per-sensor distillation from progress and verdict files?▼

Automating per-sensor distillation involves reading runtime verdicts and progress data to generate cited bullets for each sensor. The automation computes diffs for known issues, frequent errors, and calibration sections, appending history to sensor bodies without overwriting previous records.

Do I need specific runtime files to trigger sensor frontmatter recalibration?▼

Triggering sensor frontmatter recalibration requires access to `.yoke/runtime/.judge-verdicts/`, `.yoke/runtime/progress.md`, and `.yoke/config.yaml`. These files provide the cycle evidence and configuration necessary to compute diffs and detect calibration drift.

What is the best way to maintain an append-only audit trail for sensor calibration?▼

Maintaining an append-only audit trail for sensor calibration is best achieved by distilling cycle verdicts into per-sensor files with mandatory citations. This approach preserves historical evidence by appending bullets and recalibrating frontmatter costs only when drift is detected.

Why should I use append-only records for runtime sensor evidence?▼

Using append-only records for runtime sensor evidence preserves an auditable history of known issues and frequent errors across cycles. This governance model prevents data loss during distillation, enabling accurate diffs and reliable frontmatter recalibration for sensor maintenance.