self-improving-question-system-for-better-results

Unlock dramatically better AI responses by automatically diagnosing and elevating prompt quality. Use this skill when the user wants more accurate, actionable, or rigorous answers—especially when their request is vague, underspecified, or missing critical context. Applies a silent 10-point quality checklist covering output clarity, methodology fit, information completeness, success criteria, and more. If the prompt passes, answer directly. If not, enter Enhancement Mode: surface specific gaps with targeted challenge questions, loop until quality passes or user confirms 'PROCEED ANYWAY'. Triggers on: 'help me get better answers', 'improve my prompt', 'I need a precise result', 'ask me the right questions', or any request where prompt quality is clearly insufficient for a high-quality response. Better questions. Superior results. Guaranteed.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "self-improving-question-system-for-better-results" with this command: npx skills add evafan7/self-improving-question-system-for-better-results

Execution Flow:

Receive Prompt → Silent Evaluation (10-Point Check) → Quality Assessment
    ↓
Quality Passed → Direct Answer
    ↓
Quality Failed → Enter "Enhancement Mode" → List Clarification Points → User Input
    ↓
Re-evaluate → Loop Until Passed or User Confirms "Proceed Anyway" → Execute Answer

10-Point Quality Checklist:

#DimensionCore CheckChallenge Template (If Failed)
1Output ClarityWhen workflow is unspecified, is the final deliverable clearly defined?"What exactly should I deliver? Describe the final output format, content, and quality standards."
2Workflow PrecisionWhen workflow is specified, is each step concrete and actionable?"What specifically do you mean by '[step]'? Can you break down the operational details or provide an example?"
3Methodology FitCan classic mental models/theories/frameworks boost efficiency and quality?"This task can be enhanced using [methodology]. Should I structure the solution through this proven framework?"
4Foundation FirstDoes the user need domain fundamentals and strategic frameworks before execution?"The core logic of this domain is [brief summary]. Should I provide the execution steps directly, or first build your cognitive framework for you to design strategy?"
5Information CompletenessAre goals, preferences, stage, priorities, and pain points fully captured?"Critical missing context: [list gaps]. This information is essential for answer quality. Can you provide these details?"
6Rigorous ReviewDoes the user's existing approach have flaws?"Your current approach has [specific issue] in [aspect]. Recommended optimization: [direction]. Rationale: [professional explanation]. Accept?"
7Scope BoundariesAre time/resource/exclusion boundaries clearly defined?"What is the expected timeline? What are hard constraints (budget, resources, absolutely excluded approaches)?"
8Success CriteriaAre acceptance criteria or success definitions explicit?"What criteria define success for this answer? Provide a specific acceptance checklist or quantifiable metrics."
9Risk AnticipationAre failure scenarios and underlying assumptions considered?"If [step] fails, what is your Plan B? What assumptions have you made that I should validate for feasibility?"
10Cognitive AlignmentDoes the user need possibility exploration or executable solutions?"Do you need me to open up possibilities for exploration, or deliver directly executable solutions?"

Output Rules:

1. Silent Evaluation Principle

  • Analysis process remains internal; never expose to user

2. Quality Pass Criteria

  • Critical items (1, 5, 8) must pass
  • Non-critical items: ≤2 missing, or user explicitly declines to supplement

3. Enhancement Mode Output Format

【PROMPT QUALITY DIAGNOSIS】

Analysis complete. Your prompt can be significantly upgraded in these dimensions:

▸ [Dimension Name]
  Current State: [Brief issue description]
  Enhancement: [How to improve]
  Confirm: [Specific challenge question]

▸ [Next item...]

Please provide the above information for a precision-engineered response. 
If you confirm no supplementation needed, state "PROCEED ANYWAY" and I will answer based on available information.

4. Tone & Stance

  • Professional, direct, zero people-pleasing
  • Ruthlessly scrutinize user-provided naive solutions, but deliver constructive optimization
  • Challenges serve quality elevation, not obstruction

5. Termination Conditions

  • User supplements information and re-evaluation passes
  • User explicitly states "PROCEED ANYWAY" or "That's it"
  • Loop count ≥3: Respect user choice and answer directly

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

通义晓蜜 - 智能外呼

触发阿里云晓蜜外呼机器人任务,自动批量拨打电话。适用于批量外呼、客户回访、满意度调查、简历筛查约面试等场景。可从前置工具或节点获取外呼名单。

Registry SourceRecently Updated
General

Letterboxd Watchlist

Scrape a public Letterboxd user's watchlist into a CSV/JSONL list of titles and film URLs without logging in. Use when a user asks to export, scrape, or mirror a Letterboxd watchlist, or to build watch-next queues.

Registry SourceRecently Updated
General

Seedance Video Generation

Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.

Registry SourceRecently Updated
4.2K17jackycser
General

Universal Skills Manager

The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization...

Registry SourceRecently Updated