/ng-learn

ng-learn

Portable command prompt generated from skills/learning-from-experience/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.

Turns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards. Use after something went wrong or nearly did and a future safeguard should change. Do not use during a live incident, which comes first, or to blame someone.

Use when

• A bad handoff, a wrong-file edit, a made-up claim, an agent going past its allowed tools, a bug that escaped to users, or a surprise in review happened.
• Users or operators misread a release, a public claim, a runbook, a template, or an approved version.
• A past change record, skill, command, test, checker, monitor, or template failed to steer behavior the way it should have.
• A change to the rules or sources produced new text but no lasting change to a control.

Do not use when

• The event has no lesson that would repeat, and no control could reasonably change.
• You must contain a live incident first; analyze it after.
• The request is to blame someone rather than improve a control.

Inputs

• The event, near miss, review surprise, operating signal, or user feedback.
• The change record, approved version, file, skill, command, test, checker, monitor, or doc it affected.
• The evidence, the impact, the quick fix you already made, and the chance it happens again.

Prompt text

Create a Nuclear-grade OPEX record (lessons from real operation).

Inputs:
- event or near miss:
- affected packet / baseline / artifact:
- evidence:
- impact:
- immediate correction:
- weak or missing control:
- candidate durable update:
- owner:
- due date or trigger:

Produce a no-blame OPEX record (no-blame covers honest error, not a willful violation like a knowingly bypassed gate, disabled control, or fabricated result — surface those as findings, never file them as mistakes). Each finding must either change a lasting control or be closed with a clear reason why not.

Verification

• Every finding has an action, an owner, and either evidence or a reason it was closed.
• Future agents can find the lesson before they repeat the pattern.
• The lesson updates a controlled item, or explains why no update is needed.

Full skill

For the overview, process, outputs, escalation, common rationalizations, red flags, and source lineage, see skills/learning-from-experience/SKILL.md. This command sets up evidence for engineering review; it does not create compliance, formal V&V, safety, security, certification, or regulatory adequacy (see DISCLAIMER.md).