Agent skill

intent

Turn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests. Produces a brief with scope, acceptance criteria, and stop conditions.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill intent-saadshahd-moo-md --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-saadshahd-moo-md/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

Clarify WHAT before building anything. Every criterion must be testable by a stranger. Clarity over completeness — a partial spec with boolean criteria beats a thorough spec with vague ones. A brief with invented details is worse than a shorter brief grounded in what the user said — assumptions compound silently downstream. ## Workflow ### Step 1: Understand State what you heard in 1-2 sentences. If the task arrives with structured input (proposal, design, specs, task list), extract and validate — don't re-clarify. ### Step 2: Close gaps Loop using AskUserQuestion — up to 3 questions per round, max 8 rounds. At least one question across all rounds should be "what should this NOT do?" After each round, list remaining unknowns — things you'd have to invent if you wrote the brief right now. If the list is non-empty, ask another round targeting those unknowns. If empty, move to step 3. ### Step 3: Echo Compress to one sentence (≤35 words): deliverable + top constraint. Use AskUserQuestion to confirm: - **Lock it in** — proceed to assumptions review - **Edit something** — revise, then re-echo - **Explore risks** — surface failure scenarios, then return to this choice ### Step 4: Review

What's inside
Steps it walks through
  1. Workflow
  2. Step 1: Understand
  3. Step 2: Close gaps
  4. Step 3: Echo
  5. Step 4: Review assumptions
  6. Step 5: Recommended practices
  7. Step 6: Emit brief
  8. Boundaries
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the intent skill do?

Turn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests. Produces a brief with scope, acceptance criteria, and stop conditions.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill intent-saadshahd-moo-md --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