Agent skill

refine-prompts

Refine vague or unclear prompts into precise, actionable instructions. Use when user asks to clarify or improve instructions or when input is vague. Includes L1/L2/L3/L4 methodology, context enrichment, and intent clarification. Not for already clear prompts, simple questions, or when user explicitly rejects refinement.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill refine-prompts-git-fg-meta-plugin-manager-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 11 KB
Bundled scripts: none
Path: skills/ai-llm/refine-prompts-git-fg-meta-plugin-manager-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

<mission_control> <objective>Refine vague or unclear prompts into precise, actionable instructions using L1/L2/L3/L4 methodology.</objective> <success_criteria>Prompt refined to appropriate L-level with sufficient context and clear intent</success_criteria> </mission_control> ## The Path to High-Quality Prompts ### 1. Match Complexity to Structure Prompt structure should reflect task complexity. Simple tasks with complex templates waste tokens; complex tasks with simple prompts miss requirements. **Select L-level by purpose:** - **L1 (Single-sentence)**: Quick clarifications, straightforward outcomes - **L2 (Context-rich paragraph)**: Default choice—balances clarity and efficiency - **L3 (Structured bullets)**: Complex tasks with multiple constraints - **L4 (Template/framework)**: Reusable patterns, repeatable workflows **Why this works:** Right-sized structure ensures Claude understands requirements without over-constraining creativity or under-specifying deliverables. ### 2. Enrich Context, Reduce Ambiguity Add relevant background, technical constraints, and success criteria. Context prevents wrong assumptions and reduces clarification rounds. **Essential context elements:** - Te

What's inside
Steps it walks through
  1. The Path to High-Quality Prompts
  2. 1. Match Complexity to Structure
  3. 2. Enrich Context, Reduce Ambiguity
  4. 3. Preserve What Matters, Delete What Doesn't
  5. 4. Specify Outputs Precisely
  6. Operational Patterns
  7. Core Methodology
  8. Execution Process
  9. STEP 1: Parse Input
  10. STEP 2: Apply Refinement
  11. STEP 3: Structure Output
  12. STEP 4: Deliver
  13. Validation Checklist
  14. Best Practices Summary
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the refine-prompts skill do?

Refine vague or unclear prompts into precise, actionable instructions. Use when user asks to clarify or improve instructions or when input is vague. Includes L1/L2/L3/L4 methodology, context enrichment, and intent clarification. Not for already clear prompts, simple questions, or when user explicitly rejects refinement.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill refine-prompts-git-fg-meta-plugin-manager-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going