@tgoodington/intuition 8.1.0 → 8.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +83 -392
- package/package.json +1 -1
- package/skills/intuition-design/SKILL.md +5 -2
- package/skills/intuition-engineer/SKILL.md +1 -0
- package/skills/intuition-initialize/SKILL.md +77 -146
- package/skills/intuition-initialize/references/agents_template.md +106 -62
- package/skills/intuition-initialize/references/claude_template.md +37 -25
- package/skills/intuition-initialize/references/intuition_readme_template.md +15 -10
- package/skills/intuition-plan/SKILL.md +5 -1
- package/skills/intuition-start/SKILL.md +91 -339
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Intuition
|
|
2
2
|
|
|
3
|
-
A trunk-and-branch workflow system for Claude Code. Turns rough ideas into structured plans, detailed designs, and
|
|
3
|
+
A trunk-and-branch workflow system for Claude Code. Turns rough ideas into structured plans, detailed designs, code specifications, and verified implementations through guided dialogue. Supports iterative development through independent branch cycles and post-completion debugging.
|
|
4
4
|
|
|
5
5
|
## Workflow
|
|
6
6
|
|
|
@@ -9,16 +9,18 @@ A trunk-and-branch workflow system for Claude Code. Turns rough ideas into struc
|
|
|
9
9
|
↓
|
|
10
10
|
[design loop, if needed]
|
|
11
11
|
↓
|
|
12
|
-
|
|
12
|
+
/intuition-handoff → /intuition-engineer
|
|
13
|
+
↓
|
|
14
|
+
/intuition-build ← /intuition-handoff
|
|
13
15
|
↓
|
|
14
16
|
/intuition-handoff → complete
|
|
15
17
|
↓
|
|
16
18
|
/intuition-start → create branch or /intuition-debugger
|
|
17
19
|
```
|
|
18
20
|
|
|
19
|
-
Run `/intuition-handoff` between every phase. It manages state, generates briefs, and routes you forward.
|
|
21
|
+
Run `/intuition-handoff` between every phase. It manages state, generates briefs, and routes you forward. Run `/clear` before each new phase skill to keep context clean.
|
|
20
22
|
|
|
21
|
-
The first prompt→
|
|
23
|
+
The first prompt→build cycle is the **trunk**. After trunk completes, create **branches** for new features or changes. Use `/intuition-debugger` to investigate hard problems in any completed context.
|
|
22
24
|
|
|
23
25
|
## Skills
|
|
24
26
|
|
|
@@ -28,7 +30,8 @@ The first prompt→execute cycle is the **trunk**. After trunk completes, create
|
|
|
28
30
|
| `/intuition-prompt` | Sharpens a rough idea into a planning-ready brief through focused Q&A |
|
|
29
31
|
| `/intuition-plan` | Builds a strategic blueprint with tasks, decisions, and design flags |
|
|
30
32
|
| `/intuition-design` | Elaborates flagged items through collaborative design exploration (ECD framework) |
|
|
31
|
-
| `/intuition-
|
|
33
|
+
| `/intuition-engineer` | Creates code-level specifications through codebase research and interactive dialogue |
|
|
34
|
+
| `/intuition-build` | Delegates implementation to subagents, verifies against code specs and acceptance criteria |
|
|
32
35
|
| `/intuition-debugger` | Expert debugger — diagnostic specialist for complex bugs, cross-context failures, performance issues |
|
|
33
36
|
| `/intuition-handoff` | Processes phase outputs, updates memory, prepares the next phase |
|
|
34
37
|
| `/intuition-initialize` | Sets up project memory (you already ran this) |
|
|
@@ -43,15 +46,17 @@ The first prompt→execute cycle is the **trunk**. After trunk completes, create
|
|
|
43
46
|
4. `/intuition-plan` — create the blueprint
|
|
44
47
|
5. `/intuition-handoff` — review design flags, confirm items
|
|
45
48
|
6. `/intuition-design` — elaborate each flagged item (repeat with handoff between)
|
|
46
|
-
7. `/intuition-handoff` — prepare for
|
|
47
|
-
8. `/intuition-
|
|
48
|
-
9. `/intuition-handoff` —
|
|
49
|
+
7. `/intuition-handoff` — prepare for engineering
|
|
50
|
+
8. `/intuition-engineer` — create code specifications
|
|
51
|
+
9. `/intuition-handoff` — prepare for build
|
|
52
|
+
10. `/intuition-build` — implement and verify
|
|
53
|
+
11. `/intuition-handoff` — complete the cycle
|
|
49
54
|
|
|
50
|
-
Not every project needs design. If the plan is clear enough, handoff skips straight to
|
|
55
|
+
Not every project needs design. If the plan is clear enough, handoff skips straight to engineer. Run `/clear` before each phase skill.
|
|
51
56
|
|
|
52
57
|
### After trunk completes (branches)
|
|
53
58
|
|
|
54
|
-
|
|
59
|
+
12. `/intuition-start` — see project status and choose next step
|
|
55
60
|
- **Create a branch** — start a new feature or change cycle, informed by trunk
|
|
56
61
|
- **Open the debugger** — investigate hard problems in any completed context
|
|
57
62
|
|
|
@@ -26,6 +26,7 @@ These are non-negotiable. Violating any of these means the protocol has failed.
|
|
|
26
26
|
14. You MUST treat user input as suggestions unless explicitly stated as requirements. Evaluate critically and propose alternatives when warranted.
|
|
27
27
|
15. You MUST assess every task for design readiness and include a "Design Recommendations" section in the plan. Flag any task where execution cannot proceed without further design exploration (see DESIGN READINESS ASSESSMENT below).
|
|
28
28
|
16. When planning on a branch, you MUST read the parent context's plan.md and include a Parent Context section (Section 2.5). Inherited architectural decisions from the parent are binding unless the user explicitly overrides them.
|
|
29
|
+
17. You MUST NEVER proceed past a research agent launch until its results have returned and been incorporated into your analysis. Do NOT draft options, present findings, or write any output document while a research agent is still running.
|
|
29
30
|
|
|
30
31
|
REMINDER: One question per turn. Route to `/intuition-handoff`, never to `/intuition-engineer` or `/intuition-build`.
|
|
31
32
|
|
|
@@ -221,7 +222,8 @@ For each major decision domain identified from the discovery brief, orientation
|
|
|
221
222
|
- Each agent prompt MUST reference the specific decision domain, return under 400 words.
|
|
222
223
|
- Write results to `{context_path}/.planning_research/decision_[domain].md` (snake_case).
|
|
223
224
|
- NEVER launch more than 2 agents simultaneously.
|
|
224
|
-
|
|
225
|
+
- WAIT for all research agents to return and read their results before proceeding to step 3.
|
|
226
|
+
3. **Present** 2-3 options with trade-offs. Include your recommendation and why. Incorporate the research findings.
|
|
225
227
|
4. **Ask** the user to select via AskUserQuestion.
|
|
226
228
|
5. **Record** the resolved decision to `{context_path}/.planning_research/decisions_log.md`:
|
|
227
229
|
|
|
@@ -267,6 +269,8 @@ If the user wants to discuss more, return to Phase 3.
|
|
|
267
269
|
|
|
268
270
|
## Step 2: Draft the plan
|
|
269
271
|
|
|
272
|
+
Before drafting, verify ALL research agents launched during Phase 3 have returned and their findings are recorded in `decisions_log.md`. If any agent is still pending, WAIT for it.
|
|
273
|
+
|
|
270
274
|
Read `{context_path}/.planning_research/decisions_log.md` and `orientation.md` to gather resolved context. Draft the plan following the plan.md output format below, applying scope scaling for the selected tier.
|
|
271
275
|
|
|
272
276
|
## Step 3: Validate
|
|
@@ -1,19 +1,17 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: intuition-start
|
|
3
|
-
description: Load project context, detect workflow phase,
|
|
3
|
+
description: Load project context, detect workflow phase, route to the correct next skill.
|
|
4
4
|
model: haiku
|
|
5
5
|
tools: Read, Glob, Grep, AskUserQuestion, Bash
|
|
6
6
|
allowed-tools: Read, Glob, Grep, Bash
|
|
7
7
|
---
|
|
8
8
|
|
|
9
|
-
# Start -
|
|
9
|
+
# Start - Phase Detector & Router
|
|
10
10
|
|
|
11
|
-
You
|
|
11
|
+
You detect the current workflow phase and route the user to the correct next skill. You are strictly read-only — you NEVER write or modify any files.
|
|
12
12
|
|
|
13
13
|
## Package Version Info
|
|
14
14
|
|
|
15
|
-
The following version information is injected during skill loading:
|
|
16
|
-
|
|
17
15
|
**Installed version:**
|
|
18
16
|
```
|
|
19
17
|
!`npm list -g @tgoodington/intuition --depth=0 2>&1`
|
|
@@ -26,67 +24,52 @@ The following version information is injected during skill loading:
|
|
|
26
24
|
|
|
27
25
|
## CRITICAL RULES
|
|
28
26
|
|
|
29
|
-
These are non-negotiable. Violating any of these means the protocol has failed.
|
|
30
|
-
|
|
31
27
|
1. You MUST detect the current workflow phase before doing anything else.
|
|
32
|
-
2. You MUST
|
|
33
|
-
3. You MUST
|
|
34
|
-
4. You MUST NOT
|
|
35
|
-
5. You MUST
|
|
36
|
-
6. You MUST NOT manage .project-memory-state.json — handoff owns state transitions.
|
|
37
|
-
7. You MUST keep output concise. Curate, don't dump.
|
|
38
|
-
8. You MUST resolve context_path from active_context before reading any workflow artifacts.
|
|
39
|
-
9. If state has version "3.0" or no active_context field, you MUST warn the user to upgrade — do not attempt phase detection on v3.0 state.
|
|
40
|
-
|
|
41
|
-
## PROTOCOL: COMPLETE FLOW
|
|
28
|
+
2. You MUST suggest the correct next skill based on the detected phase.
|
|
29
|
+
3. You MUST NOT write, create, or modify ANY files.
|
|
30
|
+
4. You MUST NOT manage .project-memory-state.json — handoff owns state.
|
|
31
|
+
5. You MUST resolve context_path from active_context before phase detection.
|
|
42
32
|
|
|
43
|
-
|
|
33
|
+
## PROTOCOL
|
|
44
34
|
|
|
45
35
|
```
|
|
46
|
-
Step 0: Check package version
|
|
47
|
-
Step 1:
|
|
48
|
-
Step 2:
|
|
36
|
+
Step 0: Check package version — notify if update available (non-blocking)
|
|
37
|
+
Step 1: Read docs/project_notes/.project-memory-state.json
|
|
38
|
+
Step 2: Validate schema version
|
|
49
39
|
Step 3: Resolve active_context and context_path
|
|
50
|
-
Step 4: Detect
|
|
51
|
-
Step 5:
|
|
52
|
-
Step 6: Curate a concise status summary
|
|
53
|
-
Step 7: Suggest the correct next skill
|
|
40
|
+
Step 4: Detect phase using decision tree
|
|
41
|
+
Step 5: Route to next skill using routing table
|
|
54
42
|
```
|
|
55
43
|
|
|
56
44
|
## VERSION CHECK (Step 0)
|
|
57
45
|
|
|
58
|
-
|
|
46
|
+
Parse version numbers from "Package Version Info" above:
|
|
59
47
|
|
|
60
|
-
1. Extract installed version from
|
|
61
|
-
2. Extract latest version from
|
|
62
|
-
3.
|
|
63
|
-
|
|
64
|
-
`Update available: v[installed] -> v[latest]. Run /intuition-update to install.`
|
|
65
|
-
- If versions match OR if version info is missing/errored: Say nothing about versions
|
|
66
|
-
- If you cannot parse versions: Say nothing (don't block startup)
|
|
48
|
+
1. Extract installed version from npm list output (look for `@tgoodington/intuition@X.Y.Z`)
|
|
49
|
+
2. Extract latest version from npm view output
|
|
50
|
+
3. If installed < latest: Show `Update available: v[installed] → v[latest]. Run /intuition-update to install.` at the TOP of output
|
|
51
|
+
4. If versions match or unparseable: Say nothing about versions
|
|
67
52
|
|
|
68
|
-
|
|
53
|
+
NON-BLOCKING: If version commands failed, skip and proceed.
|
|
69
54
|
|
|
70
55
|
## SCHEMA VERSION CHECK (Step 2)
|
|
71
56
|
|
|
72
|
-
After reading `.project-memory-state.json
|
|
57
|
+
After reading `.project-memory-state.json`:
|
|
73
58
|
|
|
74
59
|
```
|
|
75
60
|
IF state.version == "3.0" OR state.active_context is missing:
|
|
76
|
-
→
|
|
77
|
-
→
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
→
|
|
61
|
+
→ OUTPUT: "This project uses an incompatible state schema. Run /intuition-initialize to upgrade to v5.0."
|
|
62
|
+
→ STOP
|
|
63
|
+
|
|
64
|
+
IF state has "execution" instead of "build" (v4.0):
|
|
65
|
+
→ OUTPUT: "State uses v4.0 schema. Run /intuition-handoff to migrate to v5.0."
|
|
66
|
+
→ STOP
|
|
82
67
|
```
|
|
83
68
|
|
|
84
69
|
## CONTEXT PATH RESOLUTION (Step 3)
|
|
85
70
|
|
|
86
|
-
After confirming v4.0+ schema:
|
|
87
|
-
|
|
88
71
|
```
|
|
89
|
-
active_context = state.active_context
|
|
72
|
+
active_context = state.active_context
|
|
90
73
|
|
|
91
74
|
IF active_context == "trunk":
|
|
92
75
|
context_path = "docs/project_notes/trunk/"
|
|
@@ -96,343 +79,112 @@ ELSE:
|
|
|
96
79
|
context_workflow = state.branches[active_context]
|
|
97
80
|
```
|
|
98
81
|
|
|
99
|
-
Use `context_path` for ALL artifact reads in this session.
|
|
100
|
-
Use `context_workflow` for ALL phase detection.
|
|
101
|
-
|
|
102
82
|
## PHASE DETECTION (Step 4)
|
|
103
83
|
|
|
104
|
-
Use `context_workflow` resolved above. Apply this decision tree:
|
|
105
|
-
|
|
106
84
|
```
|
|
107
85
|
IF .project-memory-state.json does NOT exist:
|
|
108
|
-
→
|
|
86
|
+
→ first_time
|
|
109
87
|
|
|
110
88
|
ELSE IF any context is complete AND no context is in-progress:
|
|
111
|
-
→
|
|
89
|
+
→ post_completion
|
|
112
90
|
|
|
113
|
-
ELSE
|
|
114
|
-
Apply
|
|
91
|
+
ELSE (a context is in-progress):
|
|
92
|
+
Apply against context_workflow:
|
|
115
93
|
|
|
116
|
-
IF
|
|
117
|
-
|
|
118
|
-
→ PHASE: prompt_in_progress
|
|
94
|
+
IF workflow.prompt.started == false OR workflow.prompt.completed == false:
|
|
95
|
+
→ prompt_in_progress
|
|
119
96
|
|
|
120
|
-
ELSE IF
|
|
121
|
-
→
|
|
97
|
+
ELSE IF workflow.planning.started == false:
|
|
98
|
+
→ ready_for_planning
|
|
122
99
|
|
|
123
|
-
ELSE IF
|
|
124
|
-
→
|
|
100
|
+
ELSE IF workflow.planning.completed == false:
|
|
101
|
+
→ planning_in_progress
|
|
125
102
|
|
|
126
|
-
ELSE IF
|
|
127
|
-
AND
|
|
128
|
-
|
|
129
|
-
→ PHASE: design_in_progress
|
|
103
|
+
ELSE IF status == "design" AND workflow.design.started == true
|
|
104
|
+
AND workflow.design.completed == false:
|
|
105
|
+
→ design_in_progress
|
|
130
106
|
|
|
131
|
-
ELSE IF
|
|
132
|
-
→
|
|
107
|
+
ELSE IF workflow.engineering.started == false:
|
|
108
|
+
→ ready_for_engineering
|
|
133
109
|
|
|
134
|
-
ELSE IF
|
|
135
|
-
→
|
|
110
|
+
ELSE IF workflow.engineering.completed == false:
|
|
111
|
+
→ engineering_in_progress
|
|
136
112
|
|
|
137
|
-
ELSE IF
|
|
138
|
-
→
|
|
113
|
+
ELSE IF workflow.build.started == false:
|
|
114
|
+
→ ready_for_build
|
|
139
115
|
|
|
140
|
-
ELSE IF
|
|
141
|
-
→
|
|
116
|
+
ELSE IF workflow.build.completed == false:
|
|
117
|
+
→ build_in_progress
|
|
142
118
|
|
|
143
119
|
ELSE:
|
|
144
|
-
→
|
|
120
|
+
→ post_completion
|
|
145
121
|
```
|
|
146
122
|
|
|
147
|
-
**"Any context is complete"**
|
|
148
|
-
|
|
149
|
-
**"No context is in-progress"** means: `state.trunk.status` is not in `["prompt","planning","design","engineering","building"]` AND no branch has status in those values.
|
|
150
|
-
|
|
151
|
-
If `.project-memory-state.json` exists but is corrupted or unreadable, infer phase from which files exist under `context_path`:
|
|
152
|
-
- `{context_path}discovery_brief.md` exists → prompt complete
|
|
153
|
-
- `{context_path}plan.md` exists → planning complete
|
|
154
|
-
- `{context_path}design_spec_*.md` exist → design in progress or complete
|
|
155
|
-
- `{context_path}code_specs.md` exists → engineering complete
|
|
156
|
-
- Ask user to confirm if ambiguous.
|
|
123
|
+
**"Any context is complete"** = trunk.status == "complete" OR any branch has status == "complete".
|
|
124
|
+
**"No context is in-progress"** = no context has status in ["prompt","planning","design","engineering","building"].
|
|
157
125
|
|
|
158
|
-
|
|
126
|
+
**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.
|
|
159
127
|
|
|
160
|
-
|
|
128
|
+
## ROUTING TABLE (Step 5)
|
|
161
129
|
|
|
162
|
-
|
|
163
|
-
Welcome to Intuition!
|
|
130
|
+
Output one line of status, then the next command.
|
|
164
131
|
|
|
165
|
-
|
|
132
|
+
| Phase | Status Line | Route |
|
|
133
|
+
|-------|-------------|-------|
|
|
134
|
+
| first_time | "No project memory found." | `/intuition-prompt` |
|
|
135
|
+
| prompt_in_progress | "Prompt refinement in progress." | `/intuition-prompt` |
|
|
136
|
+
| ready_for_planning | "Discovery complete." | Run `/clear` then `/intuition-plan` |
|
|
137
|
+
| planning_in_progress | "Planning in progress." | `/intuition-plan` |
|
|
138
|
+
| design_in_progress | "Design exploration in progress." | See DESIGN ROUTING below |
|
|
139
|
+
| ready_for_engineering | "Planning complete." | Run `/clear` then `/intuition-engineer` |
|
|
140
|
+
| engineering_in_progress | "Engineering in progress." | `/intuition-engineer` |
|
|
141
|
+
| ready_for_build | "Code specs ready." | Run `/clear` then `/intuition-build` |
|
|
142
|
+
| build_in_progress | "Build in progress." | `/intuition-build` |
|
|
143
|
+
| post_completion | See POST-COMPLETION below | — |
|
|
166
144
|
|
|
167
|
-
|
|
168
|
-
I'll help you sharpen it into something the planning phase can run with.
|
|
169
|
-
```
|
|
145
|
+
**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.
|
|
170
146
|
|
|
171
|
-
|
|
147
|
+
Include `/clear` only for "ready_for" phases (transitioning between skills). Omit `/clear` for "in_progress" phases (resuming the same skill).
|
|
172
148
|
|
|
173
|
-
|
|
149
|
+
## POST-COMPLETION
|
|
174
150
|
|
|
175
|
-
Display:
|
|
151
|
+
Display a compact status tree:
|
|
176
152
|
|
|
177
153
|
```
|
|
178
|
-
Welcome back! Here's your project status:
|
|
179
|
-
|
|
180
154
|
Project Status:
|
|
181
|
-
├── Trunk: [status]
|
|
182
|
-
|
|
183
|
-
[
|
|
184
|
-
├── Branch: [display_name] (from [created_from]): [status]
|
|
185
|
-
│ └── "[purpose]"
|
|
155
|
+
├── Trunk: [status label]
|
|
156
|
+
[For each branch:]
|
|
157
|
+
├── Branch: [display_name] (from [created_from]): [status label]
|
|
186
158
|
```
|
|
187
159
|
|
|
188
|
-
Status labels:
|
|
160
|
+
Status labels: "Not started" | "Prompting..." | "Planning..." | "Designing..." | "Engineering..." | "Building..." | "Complete"
|
|
189
161
|
|
|
190
|
-
**If any context is in-progress:**
|
|
162
|
+
**If any context is in-progress:** Route to that context's next skill instead of showing choices.
|
|
191
163
|
|
|
192
|
-
|
|
193
|
-
|
|
194
|
-
|
|
195
|
-
|
|
196
|
-
|
|
197
|
-
Do NOT proceed to the two-choice prompt — resume the in-progress context instead.
|
|
198
|
-
|
|
199
|
-
**If all contexts are complete (or only complete + none):**
|
|
200
|
-
|
|
201
|
-
Use AskUserQuestion:
|
|
202
|
-
|
|
203
|
-
```
|
|
204
|
-
Question: "All current work is complete. What's next?"
|
|
205
|
-
Header: "Next Step"
|
|
206
|
-
Options:
|
|
207
|
-
- "Create a new branch (new feature or change)"
|
|
208
|
-
- "Debug an issue (/intuition-debugger)"
|
|
209
|
-
```
|
|
210
|
-
|
|
211
|
-
**If "Create a new branch":**
|
|
164
|
+
**If all contexts are complete:** Use AskUserQuestion:
|
|
165
|
+
- Question: "All current work is complete. What's next?"
|
|
166
|
+
- Header: "Next Step"
|
|
167
|
+
- Options: "Create a new branch" | "Debug an issue"
|
|
212
168
|
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
3. Parent context (only if multiple completed contexts exist): "Which completed context should this branch build from?" with options listing each completed context. (Header: "Branch From")
|
|
218
|
-
- If only one completed context exists, auto-select it and tell the user.
|
|
219
|
-
|
|
220
|
-
Then tell the user:
|
|
169
|
+
**If "Create a new branch":** Collect via AskUserQuestion:
|
|
170
|
+
1. Branch name (Header: "Branch Name")
|
|
171
|
+
2. Branch purpose — one sentence (Header: "Branch Purpose")
|
|
172
|
+
3. Parent context (only ask if multiple completed contexts; auto-select if one)
|
|
221
173
|
|
|
174
|
+
Then output:
|
|
222
175
|
```
|
|
223
|
-
|
|
224
|
-
|
|
225
|
-
Run /intuition-handoff to register the branch and begin.
|
|
176
|
+
Branch "[name]" will [purpose], building from [parent].
|
|
177
|
+
Run /intuition-handoff to register the branch.
|
|
226
178
|
Pass along: branch name "[name]", purpose "[purpose]", parent "[parent]".
|
|
227
179
|
```
|
|
228
180
|
|
|
229
|
-
**If "
|
|
230
|
-
|
|
231
|
-
```
|
|
232
|
-
Run /intuition-debugger to investigate and debug issues in any completed context.
|
|
233
|
-
The debugger specializes in hard problems — causal chain bugs, cross-context failures,
|
|
234
|
-
performance issues, and cases where the plan or design was wrong.
|
|
235
|
-
```
|
|
236
|
-
|
|
237
|
-
### Prompt In Progress
|
|
238
|
-
|
|
239
|
-
Check if `{context_path}discovery_brief.md` exists.
|
|
240
|
-
|
|
241
|
-
```
|
|
242
|
-
Welcome back! Prompt refinement is in progress.
|
|
243
|
-
|
|
244
|
-
[If brief exists]: Progress saved at {context_path}discovery_brief.md
|
|
245
|
-
[If no brief yet]: No brief saved yet — still early in refinement.
|
|
246
|
-
|
|
247
|
-
Run /intuition-prompt to continue.
|
|
248
|
-
```
|
|
249
|
-
|
|
250
|
-
### Ready for Planning
|
|
251
|
-
|
|
252
|
-
Read and curate from:
|
|
253
|
-
- `{context_path}discovery_brief.md` — extract problem, goals, constraints
|
|
254
|
-
- `{context_path}planning_brief.md` — reference location (don't read in detail)
|
|
255
|
-
- `docs/project_notes/decisions.md` — extract 2-4 recent ADRs
|
|
256
|
-
|
|
257
|
-
```
|
|
258
|
-
Welcome back! Discovery is complete.
|
|
259
|
-
|
|
260
|
-
Here's what was discovered:
|
|
261
|
-
- Problem: [1-2 sentences from discovery]
|
|
262
|
-
- Goals: [2-3 key goals]
|
|
263
|
-
- Key constraints: [3-5 bullets]
|
|
264
|
-
|
|
265
|
-
Relevant Decisions:
|
|
266
|
-
- [ADR titles if any exist]
|
|
267
|
-
|
|
268
|
-
Planning brief ready at: {context_path}planning_brief.md
|
|
269
|
-
|
|
270
|
-
Run /intuition-plan to create a structured plan.
|
|
271
|
-
```
|
|
272
|
-
|
|
273
|
-
### Planning In Progress
|
|
274
|
-
|
|
275
|
-
Read `{context_path}plan.md` for task count and scope.
|
|
276
|
-
|
|
277
|
-
```
|
|
278
|
-
Welcome back! Planning is in progress.
|
|
279
|
-
|
|
280
|
-
Discovery: Complete
|
|
281
|
-
Plan: In progress ({context_path}plan.md)
|
|
282
|
-
- [N] tasks identified so far
|
|
283
|
-
- Scope: [Simple/Moderate/Complex if determinable]
|
|
284
|
-
|
|
285
|
-
Run /intuition-plan to continue.
|
|
286
|
-
```
|
|
287
|
-
|
|
288
|
-
### Design In Progress
|
|
289
|
-
|
|
290
|
-
Read `.project-memory-state.json` for design queue status. Read `{context_path}design_brief.md` for current item context.
|
|
291
|
-
|
|
292
|
-
```
|
|
293
|
-
Welcome back! Design exploration is in progress.
|
|
294
|
-
|
|
295
|
-
Discovery: Complete
|
|
296
|
-
Plan: Approved
|
|
297
|
-
Design: In progress
|
|
298
|
-
|
|
299
|
-
Design Queue:
|
|
300
|
-
[For each item in context_workflow.workflow.design.items:]
|
|
301
|
-
- [x] [Item Name] (completed) → {context_path}design_spec_[name].md
|
|
302
|
-
- [>] [Item Name] (in progress)
|
|
303
|
-
- [ ] [Item Name] (pending)
|
|
304
|
-
|
|
305
|
-
[If current item is in_progress]: Run /intuition-design to continue designing [current item].
|
|
306
|
-
[If current item just completed]: Run /intuition-handoff to process the design and move to the next item.
|
|
307
|
-
```
|
|
308
|
-
|
|
309
|
-
### Ready for Engineering
|
|
310
|
-
|
|
311
|
-
Read and curate from:
|
|
312
|
-
- `{context_path}plan.md` — extract objective, task count
|
|
313
|
-
- `{context_path}engineering_brief.md` — reference location
|
|
314
|
-
- `docs/project_notes/decisions.md` — relevant ADRs
|
|
315
|
-
- `{context_path}design_spec_*.md` — list any design specs
|
|
316
|
-
|
|
317
|
-
```
|
|
318
|
-
Welcome back! Ready for engineering.
|
|
319
|
-
|
|
320
|
-
Discovery: Complete
|
|
321
|
-
Plan: Approved
|
|
322
|
-
[If design specs exist]: Design: Complete ([N] specs)
|
|
323
|
-
Engineering: Ready
|
|
324
|
-
|
|
325
|
-
- [N] tasks to spec
|
|
326
|
-
- Objective: [1 sentence]
|
|
327
|
-
|
|
328
|
-
Engineering brief ready at: {context_path}engineering_brief.md
|
|
329
|
-
|
|
330
|
-
Run /intuition-engineer to create code specs.
|
|
331
|
-
```
|
|
332
|
-
|
|
333
|
-
### Engineering In Progress
|
|
334
|
-
|
|
181
|
+
**If "Debug an issue":**
|
|
335
182
|
```
|
|
336
|
-
|
|
337
|
-
|
|
338
|
-
Discovery: Complete
|
|
339
|
-
Plan: Approved
|
|
340
|
-
[If design specs exist]: Design: Complete
|
|
341
|
-
Engineering: In progress
|
|
342
|
-
|
|
343
|
-
Run /intuition-engineer to continue creating code specs.
|
|
183
|
+
Run /intuition-debugger to investigate issues in any completed context.
|
|
344
184
|
```
|
|
345
185
|
|
|
346
|
-
### Ready for Build
|
|
347
|
-
|
|
348
|
-
Read and curate from:
|
|
349
|
-
- `{context_path}plan.md` — extract objective, task count, approach
|
|
350
|
-
- `{context_path}code_specs.md` — reference location
|
|
351
|
-
- `{context_path}build_brief.md` — reference location
|
|
352
|
-
- `docs/project_notes/decisions.md` — relevant ADRs
|
|
353
|
-
|
|
354
|
-
```
|
|
355
|
-
Welcome back! Code specs are ready.
|
|
356
|
-
|
|
357
|
-
Discovery: Complete
|
|
358
|
-
Plan: Approved
|
|
359
|
-
[If design specs exist]: Design: Complete ([N] specs)
|
|
360
|
-
Engineering: Complete
|
|
361
|
-
Build: Ready
|
|
362
|
-
|
|
363
|
-
- [N] tasks
|
|
364
|
-
- Approach: [1 sentence]
|
|
365
|
-
- Scope: [Simple/Moderate/Complex]
|
|
366
|
-
|
|
367
|
-
Key context:
|
|
368
|
-
- Problem: [1 sentence from discovery]
|
|
369
|
-
- Main constraint: [most limiting]
|
|
370
|
-
|
|
371
|
-
Build brief ready at: {context_path}build_brief.md
|
|
372
|
-
|
|
373
|
-
Run /intuition-build to begin implementation.
|
|
374
|
-
```
|
|
375
|
-
|
|
376
|
-
### Build In Progress
|
|
377
|
-
|
|
378
|
-
Read `{context_path}plan.md` for total tasks and any build state available.
|
|
379
|
-
|
|
380
|
-
```
|
|
381
|
-
Welcome back! Build is in progress.
|
|
382
|
-
|
|
383
|
-
Discovery: Complete
|
|
384
|
-
Plan: Approved
|
|
385
|
-
[If design specs exist]: Design: Complete
|
|
386
|
-
Engineering: Complete
|
|
387
|
-
Build: In progress
|
|
388
|
-
|
|
389
|
-
Run /intuition-build to continue.
|
|
390
|
-
```
|
|
391
|
-
|
|
392
|
-
## BRIEF CURATION RULES
|
|
393
|
-
|
|
394
|
-
You are curating information for the user, not dumping files. Follow these rules:
|
|
395
|
-
|
|
396
|
-
**For discovery summaries:**
|
|
397
|
-
- Problem: 1-2 sentences
|
|
398
|
-
- Goals: 2-3 bullet points (most important first)
|
|
399
|
-
- Constraints: 3-5 bullets (most limiting first)
|
|
400
|
-
- Decisions: 2-4 recent ADRs
|
|
401
|
-
- Reference to full brief location
|
|
402
|
-
|
|
403
|
-
**For plan summaries:**
|
|
404
|
-
- Objective: 1 sentence
|
|
405
|
-
- Task count: just a number
|
|
406
|
-
- Approach: 1-2 sentences
|
|
407
|
-
- Scope: Simple/Moderate/Complex
|
|
408
|
-
- One key constraint
|
|
409
|
-
|
|
410
|
-
**For design summaries:**
|
|
411
|
-
- Design queue status (completed/in-progress/pending)
|
|
412
|
-
- Current item name
|
|
413
|
-
- Number of specs produced
|
|
414
|
-
|
|
415
|
-
**NEVER include:**
|
|
416
|
-
- Every assumption from discovery
|
|
417
|
-
- All context details
|
|
418
|
-
- Full risk lists
|
|
419
|
-
- Complete task breakdowns
|
|
420
|
-
- Commentary on quality of outputs
|
|
421
|
-
|
|
422
186
|
## EDGE CASES
|
|
423
187
|
|
|
424
|
-
- **
|
|
425
|
-
- **
|
|
426
|
-
- **
|
|
427
|
-
- **Old v2.0 state schema detected** (has `discovery` instead of `prompt`): Treat `discovery` fields as `prompt` fields. Suggest running `/intuition-initialize` to update to current schema.
|
|
428
|
-
- **State file exists but active_context is null or missing**: Treat as v3.0 — output the upgrade warning and stop.
|
|
429
|
-
- **Branch referenced in active_context but not found in branches map**: Report the inconsistency and suggest `/intuition-handoff` to reconcile state.
|
|
430
|
-
- **v4.0 state detected** (has `execution` instead of `build`): Warn user: "State uses v4.0 schema. Run `/intuition-handoff` to migrate to v5.0."
|
|
431
|
-
|
|
432
|
-
## VOICE
|
|
433
|
-
|
|
434
|
-
- Welcoming — "Welcome back!" / "Welcome to Intuition!"
|
|
435
|
-
- Concise and status-focused — get to the point quickly
|
|
436
|
-
- Action-oriented — always end with a clear next step
|
|
437
|
-
- Respectful of completed work — acknowledge what's been done
|
|
438
|
-
- Never evaluative — report status, don't judge quality
|
|
188
|
+
- **State file exists but active_context is null/missing**: Treat as incompatible schema — output upgrade warning and stop.
|
|
189
|
+
- **active_context references a branch not in branches map**: Report the inconsistency and suggest `/intuition-handoff` to reconcile.
|
|
190
|
+
- **Missing files referenced by state**: Report what's missing. Suggest `/intuition-handoff` to regenerate briefs.
|