How it works:
- Analyze the phase to identify gray areas (UI, UX, behavior, etc.)
- Present gray areas — user selects which to discuss
- Deep-dive each selected area until satisfied
- 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
Context files are resolved in-workflow using init phase-op and roadmap/state tool calls.
CRITICAL: Scope guardrail
- Phase boundary from ROADMAP.md is FIXED
- Discussion clarifies HOW to implement, not WHETHER to add more
- If user suggests new capabilities: "That's its own phase. I'll note it for later."
- Capture deferred ideas — don't lose them, don't act on them
Domain-aware gray areas:
Gray areas depend on what's being built. Analyze the phase goal:
- Something users SEE → layout, density, interactions, states
- Something users CALL → responses, errors, auth, versioning
- Something users RUN → output format, flags, modes, error handling
- Something users READ → structure, tone, depth, flow
- Something being ORGANIZED → criteria, grouping, naming, exceptions
Generate 3-4 phase-specific gray areas, not generic categories.
Probing depth:
- Ask 4 questions per area before checking
- "More questions about [area], or move to next?"
- If more → ask 4 more, check again
- After all areas → "Ready to create context?"
Do NOT ask about (Claude handles these):
- Technical implementation
- Architecture choices
- Performance concerns
- Scope expansion
1---
2name: gsd-discuss-phase
3description: Gather phase context through adaptive questioning before planning
4argument-hint: "<phase> [--auto]"
5allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Task
6metadata:
7 source: https://skillmd.com/skills/shoootyou/gsd-discuss-phase
8---
9
10<objective>
11Extract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked.
12
13**How it works:**
141. Analyze the phase to identify gray areas (UI, UX, behavior, etc.)
152. Present gray areas — user selects which to discuss
163. Deep-dive each selected area until satisfied
174. Create CONTEXT.md with decisions that guide research and planning
18
19**Output:** `{phase_num}-CONTEXT.md` — decisions clear enough that downstream agents can act without asking the user again
20</objective>
21
22<execution_context>
23@{{PLATFORM_ROOT}}/get-shit-done/workflows/discuss-phase.md
24@{{PLATFORM_ROOT}}/get-shit-done/templates/context.md
25</execution_context>
26
27<context>
28Phase number: $ARGUMENTS (required)
29
30Context files are resolved in-workflow using `init phase-op` and roadmap/state tool calls.
31</context>
32
33<process>
341. Validate phase number (error if missing or not in roadmap)
352. Check if CONTEXT.md exists (offer update/view/skip if yes)
363. **Analyze phase** — Identify domain and generate phase-specific gray areas
374. **Present gray areas** — Multi-select: which to discuss? (NO skip option)
385. **Deep-dive each area** — 4 questions per area, then offer more/next
396. **Write CONTEXT.md** — Sections match areas discussed
407. Offer next steps (research or plan)
41
42**CRITICAL: Scope guardrail**
43- Phase boundary from ROADMAP.md is FIXED
44- Discussion clarifies HOW to implement, not WHETHER to add more
45- If user suggests new capabilities: "That's its own phase. I'll note it for later."
46- Capture deferred ideas — don't lose them, don't act on them
47
48**Domain-aware gray areas:**
49Gray areas depend on what's being built. Analyze the phase goal:
50- Something users SEE → layout, density, interactions, states
51- Something users CALL → responses, errors, auth, versioning
52- Something users RUN → output format, flags, modes, error handling
53- Something users READ → structure, tone, depth, flow
54- Something being ORGANIZED → criteria, grouping, naming, exceptions
55
56Generate 3-4 **phase-specific** gray areas, not generic categories.
57
58**Probing depth:**
59- Ask 4 questions per area before checking
60- "More questions about [area], or move to next?"
61- If more → ask 4 more, check again
62- After all areas → "Ready to create context?"
63
64**Do NOT ask about (Claude handles these):**
65- Technical implementation
66- Architecture choices
67- Performance concerns
68- Scope expansion
69</process>
70
71<success_criteria>
72- Gray areas identified through intelligent analysis
73- User chose which areas to discuss
74- Each selected area explored until satisfied
75- Scope creep redirected to deferred ideas
76- CONTEXT.md captures decisions, not vague vision
77- User knows next steps
78</success_criteria>