OpenParable
Skip to content
← Back to skills

Discovering

Productivity
discovering

Discovering is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when idea is vague, multiple interpretations exist, scope is undefined, or stakeholders need alignment before technical work begins

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/discovering/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/discovering, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Discovering Skill

Use when the what/why is unclear; output is a direction, not a solution.

When to Use vs Researching

What's unclear?
├── What/Why (goal, scope, requirements) → Discovering
└── How (technical approach, implementation) → Researching

When to Use

  • Idea is vague or underspecified
  • Multiple interpretations exist
  • Need to align on scope and goals
  • Stakeholders have different expectations

Skip if: request is clear and decision-ready (use researching skill instead).

Quick Reference

PhaseFocusOutput
ContextCode, docs, recent changesCurrent state
IntentPurpose, constraints, criteriaRequirements
Directions2-3 approaches + trade-offsRecommendation
ConfirmSign-offDiscovery brief

Core Rules

  • Gather project context first
  • One question at a time
  • Prefer multiple choice
  • High-level directions, not technical solutions

Flow

  1. Context — Check code, docs, recent changes

  2. Intent — Purpose, constraints, success criteria, scope

  3. Directions — 2-3 high-level approaches with trade-offs; recommend one

  4. Confirm & Output — Discovery brief:

    • Goal (1 sentence)
    • Non-goals
    • Direction/approach
    • Open questions (1-3 bullets)

Get sign-off before proceeding.

Common Mistakes

MistakeFix
Jumping to technical solutionsStay high-level; how comes later
Asking multiple questions at onceOne question, wait for answer
Skipping context gatheringAlways check existing code/docs first
No clear recommendationAlways pick one direction and explain why
Proceeding without sign-offGet explicit confirmation

After Discovery

  • Technical uncertainty? → Use researching skill
  • Direction clear? → Proceed to implementation