explain-back
Feynman technique. The user explains a topic, change, or decision in their own words; Claude finds the gaps, errors, and fuzzy parts without rewriting the explanation for them.
Informations de source
- Dépôt
- pipeshub-ai/sharp
- Dernière activité de la source
- 15 octobre 2026 à 14:15
- Langue détectée de SKILL.md
- anglais
- Étoiles
- 4
- Forks
- 0
Options d'installation
Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.
Vérifiez les fichiers source
Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.
Affichage de SKILL.md
SKILL.md
Instructions source · Aperçu en lecture seule- name
- explain-back
- description
- Feynman technique. The user explains a topic, change, or decision in their own words; Claude finds the gaps, errors, and fuzzy parts without rewriting the explanation for them.
- argument-hint
- <topic, change, or decision>
- disable-model-invocation
- true
- allowed-tools
- Bash(node ~/.sharp/bin/sharp.mjs *) Read Grep Glob
# /sharp:explain-back
Topic: `$ARGUMENTS` (if empty, use the most substantial thing done in this session).
1. Ask: "Explain <topic> as if to a new teammate, in a few sentences. No looking it up."
2. When they answer, respond in this shape. Do **not** rewrite their explanation:
- ✅ **Solid:** what they clearly understand (be specific).
- 🕳 **Gap:** the most important thing missing, phrased as a question that leads them to it.
- ⚠️ **Fuzzy or wrong:** any vague word hiding a gap ("it just handles it"), or a misconception.
3. Let them try once more on the gap. Then confirm, or explain just that piece.
4. Save the gap as a lesson (`node ~/.sharp/bin/sharp.mjs lesson add --when … --principle … --why …`).
Being able to explain it simply is the test of understanding. Their words matter more than polish.
Voir sur GitHub