gsd-discuss-phase

name	gsd-discuss-phase
description	Gather phase context through adaptive questioning before planning.

<cursor_skill_adapter>

A. Skill Invocation

• This skill is invoked when the user mentions gsd-discuss-phase or describes a task matching this skill.
• Treat all user text after the skill mention as {{GSD_ARGS}}.
• If no arguments are present, treat {{GSD_ARGS}} as empty.

B. User Prompting

When the workflow needs user input, prompt the user conversationally:

• Present options as a numbered list in your response text
• Ask the user to reply with their choice
• For multi-select, ask for comma-separated numbers

C. Tool Usage

Use these Cursor tools when executing GSD workflows:

• Shell for running commands (terminal operations)
• StrReplace for editing existing files
• Read, Write, Glob, Grep, Task, WebSearch, WebFetch, TodoWrite as needed

D. Subagent Spawning

When the workflow needs to spawn a subagent:

• Use Task(subagent_type="generalPurpose", ...)
• The model parameter maps to Cursor's model options (e.g., "fast") </cursor_skill_adapter>

Extract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked.

How it works:

1. Load prior context (PROJECT.md, REQUIREMENTS.md, STATE.md, prior CONTEXT.md files)
2. Scout codebase for reusable assets and patterns
3. Analyze phase — skip gray areas already decided in prior phases
4. Present remaining gray areas — user selects which to discuss
5. Deep-dive each selected area until satisfied
6. Create CONTEXT.md with decisions that guide research and planning

Output: {phase_num}-CONTEXT.md — decisions clear enough that downstream agents can act without asking the user again

<execution_context> Workflow files are loaded on-demand in the section below — not upfront. Do not pre-load any workflow files before reading the mode routing instructions. </execution_context>

<runtime_note> Copilot (VS Code): Use vscode_askquestions wherever this workflow calls conversational prompting. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. </runtime_note>

Phase number: {{GSD_ARGS}} (required)

Context files are resolved in-workflow using init phase-op and roadmap/state tool calls.

**Mode routing:** ```bash DISCUSS_MODE=$(gsd-sdk query config-get workflow.discuss_mode 2>/dev/null || echo "discuss") ```

If --assumptions is in {{GSD_ARGS}}: Read and execute /Users/zaneliu/Projects/open-source/cloud-cli-proxy/.cursor/get-shit-done/workflows/list-phase-assumptions.md end-to-end. Stop here.

Otherwise, if DISCUSS_MODE is "assumptions": Read and execute /Users/zaneliu/Projects/open-source/cloud-cli-proxy/.cursor/get-shit-done/workflows/discuss-phase-assumptions.md end-to-end.

Otherwise ("discuss" / unset / any other value): Read and execute /Users/zaneliu/Projects/open-source/cloud-cli-proxy/.cursor/get-shit-done/workflows/discuss-phase.md end-to-end.

MANDATORY: Read the appropriate workflow file BEFORE taking any action. The objective and success_criteria sections in this command file are summaries — the workflow file contains the complete step-by-step process with all required behaviors, config checks, and interaction patterns. Do not improvise from the summary.

Lazy loading: templates/context.md is loaded inside the write_context step of the active workflow. discuss-phase-power.md is loaded inside discuss-phase.md when --power is detected. Do not load either here.

<success_criteria>

• Prior context loaded and applied (no re-asking decided questions)
• Gray areas identified through intelligent analysis
• User chose which areas to discuss
• Each selected area explored until satisfied
• Scope creep redirected to deferred ideas
• CONTEXT.md captures decisions, not vague vision
• User knows next steps </success_criteria>