Skip to content

refine: sharpen the Explaining and Teaching contract#581

Merged
rdmueller merged 1 commit into
LLM-Coding:mainfrom
raifdmueller:fix/sharpen-teaching-contract
Jun 8, 2026
Merged

refine: sharpen the Explaining and Teaching contract#581
rdmueller merged 1 commit into
LLM-Coding:mainfrom
raifdmueller:fix/sharpen-teaching-contract

Conversation

@raifdmueller

@raifdmueller raifdmueller commented Jun 8, 2026

Copy link
Copy Markdown
Contributor

Sharpens the Explaining and Teaching contract (contracts.json, EN + DE) without changing its anchors.

What changed

  • Names the trigger ("explain / why / how") so the contract explicitly replaces the default "just explain" behaviour instead of merely describing it.
  • Reorders to the real execution flow: ground yourself → frame the checklist → diagnose → teach one item in 4MAT order → verify → gate. Previously both "Sequence each unit (4MAT)" and "Diagnose first" claimed primacy, and the gate (the actual differentiator) was buried as the last bullet.
  • Adds a grounding step: learn the current state before teaching — go to the source (the actual code, the spec, the docs), don't teach from stale memory.
  • Adds two guardrails that the contract previously lacked: an over-fire brake (a one-line factual question gets a one-line answer, not a loop) and an explicit learner opt-out ("just tell me").
  • Generalised away from code-only wording so it applies to any topic; Naur's "program theory" stays as attribution only.

Anchors (unchanged)

4mat · mental-model-according-to-naur · socratic-method · feynman-technique · blooms-taxonomy · definition-of-done

Notes

  • Template uses plain paragraphs (no markdown bold) because the contracts page escapes template text — verified the rendered output has no literal **, preserves the arrows, and produces clean paragraph breaks.
  • Changelog updated (== 2026-06-08).

🤖 Generated with Claude Code

Summary by CodeRabbit

  • Documentation
    • Lehrmethodik „Explaining and Teaching" grundlegend überarbeitet mit klarer, strukturierter Anleitung
    • Neue Sicherheitsmechanismen eingeführt: Overfiring-Bremse und explizites Opt-out für Lernende
    • Präzisierter Teaching-Loop mit expliziten Triggern, diagnosegetriebener Methode und 4MAT-Sequenzierung
    • Verstärkte Verifizierung von Verständnis durch strukturiertes Gatekeeping
    • Inhalte in Deutsch und Englisch aktualisiert

- Name the trigger (explain / why / how) so it replaces the default
  "just explain" behaviour explicitly.
- Reorder to the real execution flow: ground yourself -> frame the
  checklist -> diagnose -> teach one item in 4MAT order -> verify -> gate.
- Add a grounding step (learn the current state before teaching; go to
  the source, don't teach from stale memory).
- Add an over-fire brake (one-line question -> one-line answer) and an
  explicit learner opt-out ("just tell me").
- Generalise away from code-only wording so it applies to any topic;
  keep Naur's "program theory" as attribution only.
- Mirror all changes in templateDe.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@coderabbitai

coderabbitai Bot commented Jun 8, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: 7df45ed0-9989-4b2e-9df5-3131fcc8aedb

📥 Commits

Reviewing files that changed from the base of the PR and between 1397409 and 8f7fc52.

📒 Files selected for processing (2)
  • docs/changelog.adoc
  • website/public/data/contracts.json

Walkthrough

Der Contract "Explaining and Teaching" wird mit präzisiertem Teaching-Loop, explizitem Gatekeeping, Socratic-Methode, 4MAT-Struktur und Learner-Opt-out verfeinert. Updates dokumentieren die neue Struktur in beiden Sprachversionen und Changelog.

Changes

Contract Refinement: Explaining and Teaching

Layer / File(s) Zusammenfassung
Contract Templates und Changelog Update
website/public/data/contracts.json, docs/changelog.adoc
Die englische und deutsche Template des "Explaining and Teaching"-Contracts werden von einer Loop/Bullets-Struktur auf eine diagnostizierend gesteuerte Lehr-Anweisung umgestellt. Neue Fokusses: Definition of Done für Verständnis, Socratic-Methode vor dem Lehren, 4MAT-Sequenzierung (Why → What → How → What-If), aktive Verifikation statt passiver Bestätigung, explizites Gatekeeping, Skalierung nach Frage-Größe und Opt-out-Mechanismus („just tell me"). Der Changelog dokumentiert die Verfeinerung mit benanntem Trigger, präzisierter Schrittfolge inklusive Grounding und Gates sowie neuem Steuerungsmechanismus.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed Der PR-Titel beschreibt präzise die Hauptänderung: Verbesserung und Präzisierung des 'Explaining and Teaching'-Vertrags durch Klarstellung der Trigger, Restrukturierung der Schritte, Hinzufügen von Sicherheitsmechanismen und Verallgemeinerung der Formulierung.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@rdmueller rdmueller merged commit 3b6992c into LLM-Coding:main Jun 8, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants