exploring

Extract ambiguous product and implementation decisions into a CONTEXT.md document.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/quanpersie2001/pulse --skill exploring-quanpersie2001
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exploring
Source: https://github.com/quanpersie2001/pulse/tree/main/plugins/pulse/skills/exploring
Command: npx skills add https://github.com/quanpersie2001/pulse --skill exploring-quanpersie2001

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill prevents planners and implementers from making hidden assumptions by systematically extracting and locking product and implementation decisions before research or planning begins.

Core Features & Use Cases

  • Socratic decision extraction: Runs a phased, one-question-at-a-time exploration to surface gray areas and obtain explicit answers.
  • Structured context output: Writes a concrete history/<feature>/CONTEXT.md with stable decision IDs (D1, D2, ...) and cited code paths from a quick codebase scout.
  • Gated handoff & validation: Enforces hard gates (no planning or coding), spawns a reviewer subagent to validate CONTEXT.md, and updates .pulse/STATE.md to signal next steps.
  • Use case: When a user requests a new feature with fuzzy requirements, run this skill to produce an auditable CONTEXT.md that downstream planning and validating agents can act on.

Quick Start

Ask the exploring skill to extract and lock decisions for a proposed feature and write the resulting CONTEXT.md to history/<feature>/CONTEXT.md.

Frequently Asked Questions about exploring

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

FAQPage Schema
How do I extract ambiguous product decisions before planning a new feature?

To extract ambiguous product decisions before planning, run a Socratic exploration process that surfaces gray areas one question at a time. This locks your product decisions into a structured context document before any research or coding begins.

What is a context document for feature planning and when do I need it?

A context document for feature planning is an authoritative record of locked implementation and product decisions with stable IDs and cited code paths. You need it when a new feature request has fuzzy requirements that require systematic gray area identification.

How to prevent hidden assumptions during software refactoring and behavior changes?

Prevent hidden assumptions during software refactoring by enforcing a hard gating process that blocks planning and coding until a reviewer validates all extracted decisions. This ensures an auditable handoff state before implementation starts.

Can I use a Socratic questioning process to surface gray areas in fuzzy requirements?

Yes, you can use a phased Socratic questioning process to surface gray areas in fuzzy requirements. It enforces one-question-at-a-time gating to extract explicit answers and writes them to a concrete context markdown file.

What's the best way to lock decisions for downstream planning agents?

The best way to lock decisions for downstream planning agents is to generate a context markdown file with stable decision IDs and update a shared state file. This gated handoff provides an auditable record that validating agents can act on.