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}-CONTEXT.md — decisions clear enough that downstream agents can act without asking the user again
Load project state:
@.planning/STATE.md
Load roadmap:
@.planning/ROADMAP.md
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: kata-discuss-phase3description: Gather phase context through adaptive questioning before planning, clarifying implementation decisions, or exploring gray areas for a phase. Triggers include "discuss phase", "clarify phase", "gather context", "what are the gray areas", and "phase discussion".4---5<objective>
6Extract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked.
7
8**How it works:**
91. Analyze the phase to identify gray areas (UI, UX, behavior, etc.)
102. Present gray areas — user selects which to discuss
113. Deep-dive each selected area until satisfied
124. Create CONTEXT.md with decisions that guide research and planning
13
14**Output:** `{phase}-CONTEXT.md` — decisions clear enough that downstream agents can act without asking the user again
15</objective>
16
17<execution_context>
18@./references/phase-discuss.md
19@./references/context-template.md
20</execution_context>
21
22<context>
23Phase number: $ARGUMENTS (required)
24
25**Load project state:**
26@.planning/STATE.md
27
28**Load roadmap:**
29@.planning/ROADMAP.md
30</context>
31
32<process>
331. Validate phase number (error if missing or not in roadmap)
342. Check if CONTEXT.md exists (offer update/view/skip if yes)
353. **Analyze phase** — Identify domain and generate phase-specific gray areas
364. **Present gray areas** — Multi-select: which to discuss? (NO skip option)
375. **Deep-dive each area** — 4 questions per area, then offer more/next
386. **Write CONTEXT.md** — Sections match areas discussed
397. Offer next steps (research or plan)
40
41**CRITICAL: Scope guardrail**
42- Phase boundary from ROADMAP.md is FIXED
43- Discussion clarifies HOW to implement, not WHETHER to add more
44- If user suggests new capabilities: "That's its own phase. I'll note it for later."
45- Capture deferred ideas — don't lose them, don't act on them
46
47**Domain-aware gray areas:**
48Gray areas depend on what's being built. Analyze the phase goal:
49- Something users SEE → layout, density, interactions, states
50- Something users CALL → responses, errors, auth, versioning
51- Something users RUN → output format, flags, modes, error handling
52- Something users READ → structure, tone, depth, flow
53- Something being ORGANIZED → criteria, grouping, naming, exceptions
54
55Generate 3-4 **phase-specific** gray areas, not generic categories.
56
57**Probing depth:**
58- Ask 4 questions per area before checking
59- "More questions about [area], or move to next?"
60- If more → ask 4 more, check again
61- After all areas → "Ready to create context?"
62
63**Do NOT ask about (Claude handles these):**
64- Technical implementation
65- Architecture choices
66- Performance concerns
67- Scope expansion
68</process>
69
70<success_criteria>
71- Gray areas identified through intelligent analysis
72- User chose which areas to discuss
73- Each selected area explored until satisfied
74- Scope creep redirected to deferred ideas
75- CONTEXT.md captures decisions, not vague vision
76- User knows next steps
77</success_criteria>
majiayu000