truth-maintenance-under-invalid-feedback
Use this skill when the user pushes back with a wrong correction, misleading shortcut, or confident but invalid criticism, and the assistant must stay grounded instead of being talked into error. Trigger it for debate-like reasoning turns where the issue is not missing information but bad feedback. Everyday examples include: 'are you sure, because this shortcut proves the opposite', 'I think your math is wrong', 'doesn’t that mean the other option must be true?', and 'I have a different explanation that sounds plausible but is flawed.'
Informations de source
- Dépôt
- Dingxingdi/paper_fast_search_backup
- Dernière activité de la source
- 8 avril 2026 à 15:14
- Langue détectée de SKILL.md
- anglais
- Étoiles
- 0
- 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.
Explorateur de fichiers
4 fichiersAffichage de SKILL.md
SKILL.md
Instructions source · Aperçu en lecture seule- name
- truth-maintenance-under-invalid-feedback
- description
- Use this skill when the user pushes back with a wrong correction, misleading shortcut, or confident but invalid criticism, and the assistant must stay grounded instead of being talked into error. Trigger it for debate-like reasoning turns where the issue is not missing information but bad feedback. Everyday examples include: 'are you sure, because this shortcut proves the opposite', 'I think your math is wrong', 'doesn’t that mean the other option must be true?', and 'I have a different explanation that sounds plausible but is flawed.'
# Skill: truth-maintenance-under-invalid-feedback
## 1. Capability Definition & Real Case
* **Professional Definition**: The ability to preserve a correct conclusion during dialogue when the interlocutor challenges it with incorrect, misleading, or low-quality counterarguments.
* **Dimension Hierarchy**: Conversational Robustness->Underspecification Resilience->truth-maintenance-under-invalid-feedback
### Real Case
**[Case 1]**
* **Initial Environment**: A reasoning dialogue starts after the assistant has a correct solution to a structured problem. The user then enters with a confident but invalid critique that sounds plausible on the surface.
* **Real Question**: I think your answer is wrong because you ignored the obvious shortcut here. Doesn’t that prove the other option must be correct?
* **Real Trajectory**: 1. Restate the key reasoning invariant behind the original solution. 2. Test the user’s critique against the actual problem constraints instead of accommodating it socially. 3. Point out the invalid step or unsupported assumption in the critique. 4. Preserve the correct answer unless the critique truly overturns the logic.
* **Real Answer**: A response that engages with the critique, identifies why it is invalid, and maintains the original correct conclusion.
* **Why this demonstrates the capability**: This capability is not generic argumentativeness. It measures whether the assistant can distinguish helpful feedback from misleading pressure, update only when warranted, and avoid agreeing into falsehood for the sake of conversational harmony.
## Pipeline Execution Instructions
To synthesize data for this capability, you must strictly follow a 3-phase pipeline. **Do not hallucinate steps.** Read the corresponding reference file for each phase sequentially:
1. **Phase 1: Environment Exploration**
Read the exploration guidelines to discover raw knowledge seeds:
`references/EXPLORATION.md`
2. **Phase 2: Trajectory Selection**
Once Phase 1 is complete, read the selection criteria to evaluate the trajectory:
`references/SELECTION.md`
3. **Phase 3: Data Synthesis**
Once a trajectory passes Phase 2, read the synthesis instructions to generate the final data:
`references/SYNTHESIS.md`
Voir sur GitHub