Skip to main content

open-ended-reasoning-and-explanation

Use this skill when the user wants the agent to not only be right, but also explain the answer clearly in a conversational way. Trigger it for requests like 'explain why', 'give me three real-life examples', 'say it like I’m five', or 'walk me through the logic'. Everyday examples include: 'how does that affect me day to day?', 'show me the reasoning in plain English', 'compare the options with examples', and 'explain the same answer to a beginner.'

Zur Installation springen

Quellinformationen

Repository
Dingxingdi/paper_fast_search_backup
Letzte Quellaktivität
8. April 2026 um 15:14
Erkannte Sprache von SKILL.md
Englisch
Sterne
0
Forks
0

Installationsoptionen

Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.

Quelldateien prüfen

Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.

Datei-Explorer
4 Dateien

SKILL.md wird angezeigt

SKILL.md
Quellanweisungen · Schreibgeschützte Vorschau
name
open-ended-reasoning-and-explanation
description
Use this skill when the user wants the agent to not only be right, but also explain the answer clearly in a conversational way. Trigger it for requests like 'explain why', 'give me three real-life examples', 'say it like I’m five', or 'walk me through the logic'. Everyday examples include: 'how does that affect me day to day?', 'show me the reasoning in plain English', 'compare the options with examples', and 'explain the same answer to a beginner.'
# Skill: open-ended-reasoning-and-explanation ## 1. Capability Definition & Real Case * **Professional Definition**: The ability to solve or explain non-trivial problems in dialogue form while adapting the level of explanation, examples, and framing to follow-up conversational requests. * **Dimension Hierarchy**: Conversational Effectiveness->Open-ended Interaction Quality->open-ended-reasoning-and-explanation ### Real Case **[Case 1]** * **Initial Environment**: A user has already asked an economics multiple-choice question and received a correct short answer. The dialogue history now contains the concept but not yet a lay explanation tied to daily life. * **Real Question**: How does it affect my daily life? Give 3 examples. * **Real Trajectory**: 1. Recover the earlier correct concept from the first turn. 2. Translate the abstract mechanism into concrete everyday consequences. 3. Produce exactly three distinct examples without repeating the same causal statement. 4. Keep the explanation faithful to the prior answer instead of changing the underlying economics. * **Real Answer**: A concise explanation that ties the earlier macroeconomic concept to concrete effects such as borrowing costs, prices, or employment conditions. * **Why this demonstrates the capability**: The challenge is not only answering correctly but also explaining the same reasoning in a user-centered, open-ended form. This tests whether the assistant can preserve the truth of an earlier answer while expanding it into useful, concrete, conversationally appropriate explanations. ## 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`
Auf GitHub ansehen