Agent skill

intent-first

Clarify user intent before executing tasks. Use when requests are vague, ambiguous, or could be interpreted multiple ways. Helps prevent wasted effort from misunderstanding.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill intent-first --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/agent/intent-first/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

# Intent-First: Clarify Before You Execute ## Purpose Transform vague requests into clear, actionable specifications before starting work. ## When to Use - User request is ambiguous or could mean multiple things - Task scope is unclear - Success criteria are not defined - You're about to start significant work ## The Intent Clarification Framework ### Step 1: Identify the Intent Type | Type | Signal Words | Example | |------|-------------|---------| | **Create** | make, build, write, generate | "Make a report" | | **Modify** | change, update, fix, improve | "Fix this code" | | **Analyze** | review, check, find, understand | "Review this design" | | **Decide** | should I, which is better, compare | "Should I use X or Y?" | | **Learn** | explain, how does, what is | "How does this work?" | ### Step 2: Ask the 5 Clarifying Questions Not all questions apply to every request. Select the relevant ones: #### 1. PURPOSE (Why) > "What problem are you trying to solve?" or "Who will use this and for what?" #### 2. SCOPE (What) > "What should be included? What should NOT be included?" #### 3. FORMAT (How) > "What format do you expect? (bullet points, prose, code, diagram)" #### 4. CONSTRAINTS

What's inside
Steps it walks through
  1. Purpose
  2. When to Use
  3. The Intent Clarification Framework
  4. Step 1: Identify the Intent Type
  5. Step 2: Ask the 5 Clarifying Questions
  6. Step 3: Confirm Understanding
  7. Examples
  8. Vague Request
  9. Clarified Intent
  10. Anti-Patterns
  11. Quick Decision: When to Skip Clarification
  12. Integration with Other Skills
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the intent-first skill do?

Clarify user intent before executing tasks. Use when requests are vague, ambiguous, or could be interpreted multiple ways. Helps prevent wasted effort from misunderstanding.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill intent-first --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