skills.rest
jedmamosto
jedmamostoCOMMUNITY
Explore all skills by this author →
GitHub

gsd-discuss-phase

Resolve implementation-critical ambiguities through adaptive questioning before planning.

Updated May 21, 2026
Search Tags:#agent workflow#decision capture#context gathering#requirements clarification#codebase scouting#adaptive questioning#planning enablement
One-click install
npx skills add https://github.com/jedmamosto/m-and-ms --skill gsd-discuss-phase-jedmamosto
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gsd-discuss-phase
Source: https://github.com/jedmamosto/m-and-ms/tree/main/.agents/skills/gsd-discuss-phase
Command: npx skills add https://github.com/jedmamosto/m-and-ms --skill gsd-discuss-phase-jedmamosto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It resolves ambiguity by gathering implementation-critical context through adaptive questioning before planning, so downstream agents can proceed without re-asking or guessing.

Core Features & Use Cases

  • Adaptive clarification before planning: Identifies remaining gray areas by analyzing loaded project/workflow context and then prompting the user to select what to discuss.
  • Decision-focused deep dives: Explores each chosen area until the uncertainty is resolved, not just summarized, and records concrete constraints.
  • Context packaging for downstream agents: Produces a {phase_num}-CONTEXT.md that captures locked decisions that researchers and planners must use.

Quick Start

Run the gsd-discuss-phase workflow with the phase number you are working on, then choose which uncertain topics to discuss until the generated CONTEXT.md contains clear decisions for the next agents.

Frequently Asked Questions about gsd-discuss-phase

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

FAQPage Schema
How do I resolve ambiguous requirements before starting project planning?▼

Resolve ambiguous requirements through adaptive questioning that explores gray areas until uncertainty is fully eliminated. This approach records concrete constraints into a context file for downstream agents to use.

What is the best way to capture implementation decisions for AI agent workflows?▼

Capture implementation decisions by analyzing loaded project context and scouting codebases for reusable patterns. This produces a phase-scoped context file containing locked decisions that downstream planners and researchers must use.

How do I stop AI agents from re-asking or guessing decisions during codebase planning?▼

Stop AI agents from guessing by enforcing mode routing that skips already-decided areas based on loaded project state. This ensures only unresolved gray areas are discussed and locked decisions are passed forward.

Can I scout the codebase for reusable patterns during requirements clarification?▼

Yes, you can scout the codebase for reusable patterns during requirements clarification. The process resolves gray areas across prior context files while identifying existing implementation patterns to inform decision-making.

What are the limitations of using assumptions mode versus discuss mode for context gathering?▼

The limitation of assumptions mode is that it proceeds without explicit user clarification, whereas discuss mode enforces deep dives until uncertainty is resolved. Mode routing determines whether gray areas are actively questioned or skipped.

Related Skills

Explore More Education & Research Skills→
RavBogardRavBogard

dan:discuss

Run a structured discuss phase and generate a phase CONTEXT.md.

Community
Advanced
deerawandeerawan
1

gsd-discuss-phase

Capture unresolved implementation decisions in a phase-numbered CONTEXT.md file.

Community
Intermediate
LarussoLarusso
42

openspec-explore

Explore problem spaces and compare options with visual diagrams.

Community
Intermediate
avav
10

preact-buildless-frontend

Create build-less web frontends using ES Modules for direct browser execution.

Community
Intermediate