@tgoodington/intuition 8.1.3 → 9.2.0

package/skills/intuition-prompt/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: intuition-prompt
-description: Prompt-engineering discovery. Transforms a rough vision into a precise, planning-ready discovery brief through focused iterative refinement. The primary entry point for all new work in the Intuition workflow.
+description: Prompt-engineering discovery. Transforms a rough vision into a precise, planning-ready prompt brief through focused iterative refinement. The primary entry point for all new work in the Intuition workflow.
 model: opus
 tools: Read, Write, Glob, Grep, Task, AskUserQuestion
 allowed-tools: Read, Write, Glob, Grep, Task
@@ -18,22 +18,23 @@ These are non-negotiable. Violating any of these means the protocol has failed.
 2. You MUST use AskUserQuestion for every question. Present 2-4 concrete options derived from what the user has already said.
 3. Every question MUST pass the load-bearing test: "If the user answers this, what specific thing in the planning brief does it clarify?" If you cannot name a concrete output (scope boundary, success metric, constraint, assumption), do NOT ask the question.
 4. You MUST NOT launch research subagents proactively. Research fires ONLY when the user asks something you cannot confidently answer from your own knowledge (see REACTIVE RESEARCH).
-5. You MUST create both `discovery_brief.md` and `discovery_output.json` when formalizing.
+5. You MUST create both `prompt_brief.md` and `prompt_output.json` when formalizing.
 6. You MUST route to `/intuition-handoff` at the end. NEVER to `/intuition-plan` directly.
 7. You MUST NOT ask about the user's motivations, feelings, philosophical drivers, or personal constraints. Ask about what the solution DOES, not why the person cares.
 8. You MUST NOT open a response with a compliment. No "Great!", "Smart!", "That's compelling!" Show you heard them through substance, not praise.
 9. You MUST read `.project-memory-state.json` to determine the active context path before writing any files. NEVER write to the root `docs/project_notes/` — always write to the resolved context_path.
 
-## PROTOCOL: FOUR-PHASE FLOW
+## PROTOCOL: FIVE-PHASE FLOW
 
 ```
 Phase 1: CAPTURE   (1 turn)    — User states their vision raw
-Phase 2: REFINE    (3-4 turns) — Dependency-ordered sharpening
-Phase 3: REFLECT   (1 turn)    — Mirror back structured understanding
-Phase 4: CONFIRM   (1 turn)    — Draft brief, approve, write files, route to handoff
+Phase 2: REFINE    (3-5 turns) — Dependency-ordered sharpening (includes INTENT)
+Phase 3: REFLECT   (1 turn)    — Mirror back structured understanding + commander's intent
+Phase 4: POSTURE   (1 turn)    — User declares decision authority per area
+Phase 5: CONFIRM   (1 turn)    — Draft brief, approve, write files, route to handoff
 ```
 
-Target: 5-7 total turns. Every turn directly refines the output artifact.
+Target: 6-9 total turns. Every turn directly refines the output artifact.
 
 ## STARTUP: CONTEXT PATH RESOLUTION
 
@@ -91,12 +92,20 @@ This is the core of the skill. Each turn targets ONE gap using a dependency-orde
 ### Refinement Order
 
 ```
-1. SCOPE      → What is IN and what is OUT?
-2. SUCCESS    → How do you know it worked? What's observable/testable?
-3. CONSTRAINTS → What can't change? Technology, team, timeline, budget?
-4. ASSUMPTIONS → What are we taking as given? How confident are we?
+1. SCOPE       → What is IN and what is OUT?
+2. INTENT      → What does the end-user experience when this is done and working?
+3. SUCCESS     → How do you know it worked? What's observable/testable?
+4. CONSTRAINTS → What can't change? Technology, team, timeline, budget?
+5. ASSUMPTIONS → What are we taking as given? How confident are we?
 ```
 
+**INTENT captures the experiential outcome** — not metrics, but feel:
+- What the end-user experiences when interacting with the finished product
+- What the output/interface looks like and feels like in practice
+- Non-negotiable experiential qualities (fast, simple, invisible, delightful, etc.)
+
+INTENT grounds the brief in what success *feels like*, which downstream phases use to distinguish user-facing decisions from technical internals.
+
 ### Decision Logic Per Turn
 
 Before each question, run this internal check:
@@ -104,13 +113,15 @@ Before each question, run this internal check:
 ```
 Is SCOPE clear enough to plan against?
   NO  → Ask a scope question
-  YES → Is SUCCESS defined with observable criteria?
-    NO  → Ask a success criteria question
-    YES → Are binding CONSTRAINTS surfaced?
-      NO  → Ask a constraints question
-      YES → Are key ASSUMPTIONS identified?
-        NO  → Ask an assumptions question
-        YES → Move to REFLECT
+  YES → Is INTENT defined (experiential outcome, look/feel, non-negotiable qualities)?
+    NO  → Ask an intent question
+    YES → Is SUCCESS defined with observable criteria?
+      NO  → Ask a success criteria question
+      YES → Are binding CONSTRAINTS surfaced?
+        NO  → Ask a constraints question
+        YES → Are key ASSUMPTIONS identified?
+          NO  → Ask an assumptions question
+          YES → Move to REFLECT
 ```
 
 If the user's initial CAPTURE response already covers some dimensions, skip them. Do not ask about what's already clear.
@@ -135,7 +146,7 @@ By turn 3-4 of REFINE, you should be asking about what the solution DOES, not wh
 
 ## PHASE 3: REFLECT
 
-After REFINE completes, mirror back the entire refined understanding in one structured response. This is NOT the formal brief — it's a checkpoint so the user sees their vision sharpened before it becomes an artifact.
+After REFINE completes, mirror back the entire refined understanding in one structured response. This is NOT the formal brief — it's a checkpoint so the user sees their vision sharpened before it becomes an artifact. Include the Commander's Intent synthesis so the user can see how you've distilled their experiential vision before the posture question.
 
 Use AskUserQuestion:
 
@@ -144,6 +155,11 @@ Question: "Here's what I've captured from our conversation:
 
 **Problem:** [2-3 sentence restatement with causal structure]
 
+**Commander's Intent:**
+- Desired end state: [What success feels/looks like to the end user — experiential, not metrics]
+- Non-negotiables: [The 2-3 experiential qualities that would make the user reject the result]
+- Boundaries: [Constraints on the solution space, not prescribed solutions]
+
 **Success looks like:** [bullet list of observable outcomes]
 
 **In scope:** [list]
@@ -164,20 +180,53 @@ Options:
 - "We missed something important"
 ```
 
-If they want adjustments, address them (1-2 more turns max), then re-present. If they confirm, move to CONFIRM.
+If they want adjustments, address them (1-2 more turns max), then re-present. If they confirm, move to POSTURE.
+
+## PHASE 4: POSTURE
+
+After the user approves the REFLECT summary, present the major elements from the brief and ask which areas they want decision authority over during the build.
+
+Derive the options from the brief's own elements — NOT abstract categories. Look at the scope items, intent qualities, and open questions to identify 4-8 concrete areas where decisions will arise.
+
+Use AskUserQuestion with multiSelect:
+
+```
+Question: "Now that we've locked the brief, which of these areas do you want final say on during the build?"
+
+Header: "Decisions"
+multiSelect: true
+Options (derive from brief — examples):
+- "[Concrete area from scope/intent, e.g., 'Navigation structure']" — "Specialist recommends, you approve"
+- "[Concrete area from scope/intent, e.g., 'Output format']" — "Specialist recommends, you approve"
+- "[Concrete area from scope/intent, e.g., 'Error messaging']" — "Specialist recommends, you approve"
+- "Just handle everything" — "Team has full autonomy — surface only major surprises"
+```
+
+**Interpretation rules:**
+- Selected items → **"I decide"** (always surface with full options)
+- Unselected items (when some ARE selected) → **"Show me options"** (specialist recommends, user approves)
+- "Just handle everything" selected → ALL items become **"Team handles"** (full autonomy)
+- If the user selects specific items AND "Just handle everything" → ignore "Just handle everything", use the specific selections
+
+Record the result as the Decision Posture Map. Then move to CONFIRM.
 
-## PHASE 4: CONFIRM
+## PHASE 5: CONFIRM
 
 Write the output files and route to handoff.
 
-### Write `{context_path}/discovery_brief.md`
+### Write `{context_path}/prompt_brief.md`
 
 ```markdown
-# Discovery Brief: [Problem Title]
+# Prompt Brief: [Problem Title]
 
 ## Problem Statement
 [2-3 sentences. What is broken or missing, for whom, and why it matters now. Include causal structure.]
 
+## Commander's Intent
+**Desired end state:** [What success feels/looks like to the end user — experiential, not metrics]
+**Non-negotiables:** [The 2-3 experiential qualities that would make the user reject the result]
+**Boundaries:** [Constraints on the solution space, not prescribed solutions]
+
 ## Success Criteria
 - [Observable, testable outcome 1]
 - [Observable, testable outcome 2]
@@ -205,9 +254,14 @@ Write the output files and route to handoff.
 - [Build decision the planning phase should investigate]
 - [Technical unknown that affects architecture]
 - [Assumption that needs validation]
+
+## Decision Posture
+| Area | Posture | Notes |
+|------|---------|-------|
+| [element from brief] | I decide / Show me options / Team handles | [any context] |
 ```
 
-### Write `{context_path}/discovery_output.json`
+### Write `{context_path}/prompt_output.json`
 
 ```json
 {
@@ -217,6 +271,11 @@ Write the output files and route to handoff.
     "problem_statement": "...",
     "success_criteria": "..."
   },
+  "commander_intent": {
+    "desired_end_state": "...",
+    "non_negotiables": ["..."],
+    "boundaries": ["..."]
+  },
   "scope": {
     "in": ["..."],
     "out": ["..."]
@@ -225,6 +284,9 @@ Write the output files and route to handoff.
   "assumptions": [
     { "assumption": "...", "confidence": "high|medium|low", "basis": "..." }
   ],
+  "decision_posture": [
+    { "area": "...", "posture": "i_decide|show_options|team_handles", "notes": "..." }
+  ],
   "research_performed": [],
   "open_questions": ["..."]
 }
@@ -236,8 +298,8 @@ After writing both files, tell the user:
 
 ```
 I've captured our refined brief in:
-- docs/project_notes/discovery_brief.md (readable narrative)
-- docs/project_notes/discovery_output.json (structured data)
+- docs/project_notes/prompt_brief.md (readable narrative)
+- docs/project_notes/prompt_output.json (structured data)
 
 Take a look and make sure they reflect what we discussed.
 
@@ -291,7 +353,7 @@ These are banned. If you catch yourself doing any of these, stop and correct cou
 
 ## RESUME LOGIC
 
-If the user has an existing session (check for `docs/project_notes/discovery_brief.md` or prior conversation context):
+If the user has an existing session (check for `docs/project_notes/prompt_brief.md` or prior conversation context):
 
 1. Read any existing state
 2. Acknowledge: "Welcome back. We were working on [topic]."

package/skills/intuition-start/SKILL.md

@@ -58,12 +58,20 @@ After reading `.project-memory-state.json`:
 
 ```
 IF state.version == "3.0" OR state.active_context is missing:
-  → OUTPUT: "This project uses an incompatible state schema. Run /intuition-initialize to upgrade to v5.0."
+  → OUTPUT: "This project uses an incompatible state schema. Run /intuition-initialize to upgrade to v7.0."
   → STOP
 
 IF state has "execution" instead of "build" (v4.0):
-  → OUTPUT: "State uses v4.0 schema. Run /intuition-handoff to migrate to v5.0."
+  → OUTPUT: "State uses v4.0 schema. Run /intuition-handoff to migrate to v7.0."
   → STOP
+
+IF state.version == "5.0" (missing detail object):
+  → OUTPUT: "State uses v5.0 schema (no v9 detail/test phase support). Run /intuition-handoff to migrate to v7.0."
+  → NON-BLOCKING: Continue with v8 routing. v9 features unavailable until migrated.
+
+IF state.version == "6.0" (missing test object):
+  → OUTPUT: "State uses v6.0 schema (no test phase support). Run /intuition-handoff to migrate to v7.0."
+  → NON-BLOCKING: Continue with routing. Test phase unavailable until migrated.
 ```
 
 ## CONTEXT PATH RESOLUTION (Step 3)
@@ -100,6 +108,15 @@ ELSE (a context is in-progress):
   ELSE IF workflow.planning.completed == false:
     → planning_in_progress
 
+  ELSE IF status == "planning" AND workflow.planning.completed == true
+       AND workflow.detail exists:
+    IF workflow.detail.started == false:
+      → ready_for_assemble
+    ELSE IF workflow.detail.completed == false:
+      → detail_in_progress
+    ELSE IF workflow.build.started == false:
+      → ready_for_build
+
   ELSE IF status == "design" AND workflow.design.started == true
        AND workflow.design.completed == false:
     → design_in_progress
@@ -116,14 +133,22 @@ ELSE (a context is in-progress):
   ELSE IF workflow.build.completed == false:
     → build_in_progress
 
+  ELSE IF workflow.test exists AND workflow.test.started == true
+       AND workflow.test.completed == false:
+    → test_in_progress
+
+  ELSE IF workflow.build.completed == true AND workflow.test exists
+       AND workflow.test.started == false:
+    → ready_for_test
+
   ELSE:
     → post_completion
 ```
 
 **"Any context is complete"** = trunk.status == "complete" OR any branch has status == "complete".
-**"No context is in-progress"** = no context has status in ["prompt","planning","design","engineering","building"].
+**"No context is in-progress"** = no context has status in ["prompt","planning","design","engineering","building","testing","detail"].
 
-**Fallback** (state corrupted): Infer from files under context_path — discovery_brief.md (prompt done), plan.md (planning done), code_specs.md (engineering done). Ask user if ambiguous.
+**Fallback** (state corrupted): Infer from files under context_path — prompt_brief.md (prompt done), plan.md (planning done), team_assignment.json (assemble done), blueprints/ directory (detail in progress), code_specs.md (engineering done), build_report.md (build done), test_report.md (test done). Ask user if ambiguous.
 
 ## ROUTING TABLE (Step 5)
 
@@ -133,18 +158,26 @@ Output one line of status, then the next command.
 |-------|-------------|-------|
 | first_time | "No project memory found." | `/intuition-prompt` |
 | prompt_in_progress | "Prompt refinement in progress." | `/intuition-prompt` |
-| ready_for_planning | "Discovery complete." | Run `/clear` then `/intuition-plan` |
+| ready_for_planning | "Prompt complete." | `/intuition-handoff` |
 | planning_in_progress | "Planning in progress." | `/intuition-plan` |
+| ready_for_assemble | "Planning complete (v9)." | `/intuition-handoff` |
+| detail_in_progress | "Detail phase in progress." | See DETAIL ROUTING below |
 | design_in_progress | "Design exploration in progress." | See DESIGN ROUTING below |
-| ready_for_engineering | "Planning complete." | Run `/clear` then `/intuition-engineer` |
+| ready_for_engineering | "Planning complete (v8)." | `/intuition-handoff` |
 | engineering_in_progress | "Engineering in progress." | `/intuition-engineer` |
-| ready_for_build | "Code specs ready." | Run `/clear` then `/intuition-build` |
+| ready_for_build | "Code specs ready." | `/intuition-handoff` |
 | build_in_progress | "Build in progress." | `/intuition-build` |
+| ready_for_test | "Build complete, testing pending." | `/intuition-handoff` |
+| test_in_progress | "Test phase in progress." | `/intuition-test` |
 | post_completion | See POST-COMPLETION below | — |
 
 **DESIGN ROUTING:** Read `context_workflow.workflow.design.items`. If any item has status "in_progress" → `/intuition-design`. If an item just completed and others remain → `/intuition-handoff`. If ambiguous, ask the user.
 
-Include `/clear` only for "ready_for" phases (transitioning between skills). Omit `/clear` for "in_progress" phases (resuming the same skill).
+**TEST ROUTING NOTE:** `ready_for_test` routes to handoff (not test) because the test_brief hasn't been generated yet — handoff creates it during Transition 6.5v9.
+
+**DETAIL ROUTING:** Read `context_workflow.workflow.detail`. If `current_specialist` is set and its status is "in_progress" → `/intuition-detail`. If a specialist just completed and others remain → `/intuition-handoff`. If all specialists completed but build not started → `/intuition-handoff`. If ambiguous, ask the user.
+
+For "ready_for" phases, route to `/intuition-handoff` (which manages `/clear` and phase transitions). For "in_progress" phases, route directly to the active skill.
 
 ## POST-COMPLETION
 
@@ -157,7 +190,7 @@ Project Status:
 ├── Branch: [display_name] (from [created_from]): [status label]
 ```
 
-Status labels: "Not started" | "Prompting..." | "Planning..." | "Designing..." | "Engineering..." | "Building..." | "Complete"
+Status labels: "Not started" | "Prompting..." | "Planning..." | "Assembling..." | "Detailing..." | "Designing..." | "Engineering..." | "Building..." | "Testing..." | "Complete"
 
 **If any context is in-progress:** Route to that context's next skill instead of showing choices.
 

package/skills/intuition-start/references/start_core.md

@@ -110,7 +110,7 @@ this work through a genuine conversation.
 ```
 
 ### Brief Generated
-- `discovery_brief.md`: Minimal/empty (just a header and invitation)
+- `prompt_brief.md`: Minimal/empty (just a header and invitation)
 - OR: Skip creating brief (let Waldo create it)
 
 ---
@@ -120,11 +120,11 @@ this work through a genuine conversation.
 ### Detection
 - `discovery.started == true`
 - `discovery.completed == false`
-- `docs/project_notes/discovery_brief.md` may or may not exist yet
+- `docs/project_notes/prompt_brief.md` may or may not exist yet
 
 ### Action
 1. Note that discovery is underway
-2. Load any existing discovery_brief.md if present
+2. Load any existing prompt_brief.md if present
 3. Acknowledge progress
 4. Suggest continuing
 
@@ -133,10 +133,10 @@ this work through a genuine conversation.
 ```
 Welcome back! I see you're in the discovery phase.
 
-[If discovery_brief.md exists]:
+[If prompt_brief.md exists]:
 Progress so far:
 - Last updated: [timestamp]
-- Brief saved at: docs/project_notes/discovery_brief.md
+- Brief saved at: docs/project_notes/prompt_brief.md
 
 Run /intuition-discovery to continue our conversation.
 ```
@@ -156,11 +156,11 @@ Run /intuition-discovery to continue exploring what you're building.
 ### Detection
 - `discovery.completed == true`
 - `planning.started == false`
-- `docs/project_notes/discovery_brief.md` exists
+- `docs/project_notes/prompt_brief.md` exists
 - `docs/project_notes/planning_brief.md` exists (created by handoff)
 
 ### Action
-1. Read `discovery_brief.md` and `planning_brief.md`
+1. Read `prompt_brief.md` and `planning_brief.md`
 2. Extract and summarize key information
 3. Load relevant architectural decisions from `decisions.md`
 4. Generate a fresh planning brief (or note the existing one)
@@ -168,7 +168,7 @@ Run /intuition-discovery to continue exploring what you're building.
 
 ### Data to Extract
 
-**From discovery_brief.md:**
+**From prompt_brief.md:**
 ```
 Problem: [extract from "## Problem" section]
 Goals: [extract from "## Goals" section]
@@ -263,7 +263,7 @@ Relevant Decisions:
 ```
 Welcome back! I see you're in the planning phase.
 
-Discovery: ✓ Complete (docs/project_notes/discovery_brief.md)
+Discovery: ✓ Complete (docs/project_notes/prompt_brief.md)
 Plan In Progress: 🔄 (docs/project_notes/plan.md)
   - [X] tasks identified
   - Scope: [Simple/Moderate/Complex]
@@ -436,7 +436,7 @@ Identify most limiting or important facts.
 Summarize for user (don't read the whole file).
 ```
 
-### Read discovery_brief.md
+### Read prompt_brief.md
 ```
 Extract from these sections:
 - ## Problem
@@ -513,7 +513,7 @@ Ready to plan? Run:
 
 ### What if files are missing?
 ```
-IF discovery_brief.md doesn't exist but discovery.completed == true:
+IF prompt_brief.md doesn't exist but discovery.completed == true:
   → "Discovery was completed but brief not saved.
      Ready to plan? Run /intuition-plan"
 
@@ -524,7 +524,7 @@ IF planning_brief.md doesn't exist but planning.started == true:
 
 ### What if state.json is corrupted?
 ```
-1. Check for main files (discovery_brief.md, plan.md)
+1. Check for main files (prompt_brief.md, plan.md)
 2. Infer phase from which files exist
 3. Ask user: "I'm not sure where you are. What would you like to do?"
 ```