clarification-expert

Research ambiguous requests and ask only judgment-call questions before implementation.

66|2|Updated Feb 18, 2015
One-click install
npx skills add https://github.com/tkersey/dotfiles --skill clarification-expert
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clarification-expert
Source: https://github.com/tkersey/dotfiles/tree/main/codex/skills/clarification-expert
Command: npx skills add https://github.com/tkersey/dotfiles --skill clarification-expert

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Clarification-Expert identifies and resolves ambiguous or conflicting requests by researching first, then asking only judgment calls, preventing premature implementation and reducing misalignment.

Core Features & Use Cases

  • Research-first clarification: perform domain or context research before posing decisions.
  • Judgment-call framing: formulate questions that force concrete decisions or trade-offs.
  • Open-question management: maintain a running snapshot of facts, decisions, and unresolved items.
  • Handoff discipline: defer implementation until a clear problem statement and success criteria exist.

Quick Start

  1. Research first; don’t ask for discoverable facts.
  2. Maintain a running snapshot (facts, decisions, open questions).
  3. Ask only judgment calls: limit to a small batch per round.
  4. Incorporate answers and repeat until no open questions remain.
  5. Generate verbose beads, then stop (no implementation).

Frequently Asked Questions about clarification-expert

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clarify ambiguous project requests before starting development?

Ambiguous requests are clarified by performing context research first, documenting facts and decisions in a running snapshot, and asking only judgment-call questions until all open questions are resolved.

What is the best way to manage open questions and conflicting requirements?

The best way to manage open questions is maintaining a running snapshot that tracks confirmed facts, final decisions, and unresolved items, ensuring all stakeholders share a single source of truth before handoff.

How do I stop premature implementation on vague goals like 'build a system'?

To stop premature implementation on vague goals, enforce an iterative loop of research and judgment-call questions, deferring all design and coding until a clear problem statement and success criteria exist.

When should I use a research-first approach for decision-making?

Use a research-first approach for decision-making whenever you encounter vague goals, conflicting requirements, or open-ended prompts, ensuring you gather discoverable facts before framing concrete trade-offs for the user.

How do I frame judgment calls for complex project trade-offs?

Frame judgment calls by formulating targeted questions that force concrete decisions between specific trade-offs, limiting questions to a small batch per round so users can make focused decisions without feeling overwhelmed.