get-shit-done-cc 1.5.30 → 1.6.1

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.
@@ -1,134 +0,0 @@
1
- ---
2
- name: gsd:define-requirements
3
- description: Define what "done" looks like with checkable requirements
4
- allowed-tools:
5
- - Read
6
- - Write
7
- - Bash
8
- - Glob
9
- - AskUserQuestion
10
- ---
11
-
12
- <!--
13
- DEPRECATED: This command is now integrated into /gsd:new-project
14
-
15
- The unified /gsd:new-project flow includes requirements definition as Phase 7.
16
- This standalone command is kept for users who want to:
17
- - Redefine requirements mid-project
18
- - Add new requirements after initial project setup
19
- - Adjust v1/v2 scope boundaries
20
-
21
- For new projects, use /gsd:new-project instead.
22
-
23
- Deprecated: 2026-01-16
24
- -->
25
-
26
- <objective>
27
- Define concrete, checkable requirements for v1.
28
-
29
- Two modes:
30
- 1. **With research** — Transform FEATURES.md into scoped requirements
31
- 2. **Without research** — Gather requirements through questioning
32
-
33
- Output: `.planning/REQUIREMENTS.md`
34
-
35
- **Note:** For new projects, `/gsd:new-project` includes requirements definition. Use this command to redefine requirements later.
36
- </objective>
37
-
38
- <execution_context>
39
- @~/.claude/get-shit-done/workflows/define-requirements.md
40
- @~/.claude/get-shit-done/templates/requirements.md
41
- </execution_context>
42
-
43
- <context>
44
- @.planning/PROJECT.md
45
- @.planning/research/FEATURES.md (if exists)
46
- @.planning/research/SUMMARY.md (if exists)
47
- </context>
48
-
49
- <process>
50
-
51
- <step name="validate">
52
- ```bash
53
- # Verify project exists
54
- [ -f .planning/PROJECT.md ] || { echo "ERROR: No PROJECT.md found. Run /gsd:new-project first."; exit 1; }
55
-
56
- # Check for research
57
- [ -f .planning/research/FEATURES.md ] && echo "HAS_RESEARCH" || echo "NO_RESEARCH"
58
-
59
- # Check if requirements already exist
60
- [ -f .planning/REQUIREMENTS.md ] && echo "REQUIREMENTS_EXISTS" || echo "NO_REQUIREMENTS"
61
- ```
62
- </step>
63
-
64
- <step name="check_existing">
65
- **If REQUIREMENTS_EXISTS:**
66
-
67
- Use AskUserQuestion:
68
- - header: "Requirements exist"
69
- - question: "Requirements already defined. What would you like to do?"
70
- - options:
71
- - "View existing" — Show current requirements
72
- - "Replace" — Define requirements fresh (will overwrite)
73
- - "Cancel" — Keep existing requirements
74
-
75
- If "View existing": Read and display `.planning/REQUIREMENTS.md`, then exit
76
- If "Cancel": Exit
77
- If "Replace": Continue with workflow
78
- </step>
79
-
80
- <step name="execute">
81
- **If HAS_RESEARCH:**
82
- Follow the define-requirements.md workflow:
83
- - Load research features from FEATURES.md
84
- - Present features by category
85
- - Ask user to scope each category (v1 / v2 / out of scope)
86
- - Capture any additions research missed
87
- - Generate REQUIREMENTS.md with checkable list
88
-
89
- **If NO_RESEARCH:**
90
- Gather requirements through questioning:
91
- - Read PROJECT.md for core value and context
92
- - Ask: "What are the main things users need to be able to do?"
93
- - For each capability mentioned, probe for specifics
94
- - Group into categories (Authentication, Content, etc.)
95
- - For each category, ask what's v1 vs v2 vs out of scope
96
- - Generate REQUIREMENTS.md with checkable list
97
-
98
- Same output format either way — the difference is source (research vs conversation).
99
- </step>
100
-
101
- <step name="done">
102
- ```
103
- Requirements defined:
104
-
105
- - Requirements: .planning/REQUIREMENTS.md
106
- - v1 scope: [N] requirements across [M] categories
107
- - v2 scope: [X] requirements deferred
108
- - Out of scope: [Y] requirements excluded
109
-
110
- ---
111
-
112
- ## ▶ Next Up
113
-
114
- **Create roadmap** — phases mapped to requirements
115
-
116
- `/gsd:create-roadmap`
117
-
118
- <sub>`/clear` first → fresh context window</sub>
119
-
120
- ---
121
- ```
122
- </step>
123
-
124
- </process>
125
-
126
- <success_criteria>
127
- - [ ] PROJECT.md validated
128
- - [ ] Features gathered (from research OR questioning)
129
- - [ ] User scoped each category (v1/v2/out of scope)
130
- - [ ] User had opportunity to add missing requirements
131
- - [ ] REQUIREMENTS.md created with checkable list
132
- - [ ] Requirements committed to git
133
- - [ ] User knows next step (create-roadmap)
134
- </success_criteria>
@@ -1,47 +0,0 @@
1
- ---
2
- name: gsd:discuss-milestone
3
- description: Gather context for next milestone through adaptive questioning
4
- ---
5
-
6
- <objective>
7
- Help you figure out what to build in the next milestone through collaborative thinking.
8
-
9
- Purpose: After completing a milestone, explore what features you want to add, improve, or fix. Features first — scope and phases derive from what you want to build.
10
- Output: Context gathered, then routes to /gsd:new-milestone
11
- </objective>
12
-
13
- <execution_context>
14
- @~/.claude/get-shit-done/workflows/discuss-milestone.md
15
- </execution_context>
16
-
17
- <context>
18
- **Load project state first:**
19
- @.planning/STATE.md
20
-
21
- **Load project:**
22
- @.planning/PROJECT.md
23
-
24
- **Load milestones (if exists):**
25
- @.planning/MILESTONES.md
26
- </context>
27
-
28
- <process>
29
- 1. Verify previous milestone complete (or acknowledge active milestone)
30
- 2. Present context from previous milestone (accomplishments, phase count)
31
- 3. Follow discuss-milestone.md workflow with **ALL questions using AskUserQuestion**:
32
- - Use AskUserQuestion: "What do you want to add, improve, or fix?" with feature categories
33
- - Use AskUserQuestion to dig into features they mention
34
- - Use AskUserQuestion to help them articulate what matters most
35
- - Use AskUserQuestion for decision gate (ready / ask more / let me add context)
36
- 4. Hand off to /gsd:new-milestone with gathered context
37
-
38
- **CRITICAL: ALL questions use AskUserQuestion. Never ask inline text questions.**
39
- </process>
40
-
41
- <success_criteria>
42
-
43
- - Project state loaded and presented
44
- - Previous milestone context summarized
45
- - Milestone scope gathered through adaptive questioning
46
- - Context handed off to /gsd:new-milestone
47
- </success_criteria>
@@ -1,323 +0,0 @@
1
- ---
2
- name: gsd:research-project
3
- description: Research domain ecosystem before creating roadmap
4
- allowed-tools:
5
- - Read
6
- - Write
7
- - Bash
8
- - Task
9
- - AskUserQuestion
10
- ---
11
-
12
- <!--
13
- DEPRECATED: This command is now integrated into /gsd:new-project
14
-
15
- The unified /gsd:new-project flow includes optional research as Phase 6.
16
- This standalone command is kept for users who want to:
17
- - Re-research a domain mid-project
18
- - Research without running full new-project flow
19
- - Add research after skipping it initially
20
-
21
- For new projects, use /gsd:new-project instead.
22
-
23
- Deprecated: 2026-01-16
24
- -->
25
-
26
- <objective>
27
- Research domain ecosystem. Spawns 4 parallel gsd-project-researcher agents for comprehensive coverage.
28
-
29
- **Orchestrator role:** Analyze project, generate research questions, spawn 4 parallel agents, synthesize SUMMARY.md.
30
-
31
- **Why subagents:** Research burns context fast. Fresh 200k context per domain. Main context stays lean.
32
-
33
- **Note:** For new projects, `/gsd:new-project` includes research as an optional step. Use this command to re-research or add research later.
34
- </objective>
35
-
36
- <context>
37
- @.planning/PROJECT.md
38
- @.planning/config.json (if exists)
39
- </context>
40
-
41
- <process>
42
-
43
- ## 1. Validate Prerequisites
44
-
45
- ```bash
46
- [ -f .planning/PROJECT.md ] || { echo "ERROR: No PROJECT.md. Run /gsd:new-project first."; exit 1; }
47
- [ -f .planning/ROADMAP.md ] && echo "WARNING: ROADMAP.md exists. Research is typically done before roadmap."
48
- [ -d .planning/research ] && echo "RESEARCH_EXISTS" || echo "NO_RESEARCH"
49
- ```
50
-
51
- ## 2. Handle Existing Research
52
-
53
- **If RESEARCH_EXISTS:** Use AskUserQuestion (View existing / Replace / Cancel)
54
-
55
- ## 3. Analyze Project
56
-
57
- Read PROJECT.md, extract domain/stack/core value/constraints. Present for approval:
58
- ```
59
- Domain analysis:
60
- - Type: [domain]
61
- - Stack: [stated or TBD]
62
- - Core: [core value]
63
- Does this look right? (yes / adjust)
64
- ```
65
-
66
- ## 4. Generate Research Questions
67
-
68
- | Dimension | Question |
69
- |-----------|----------|
70
- | Stack | "What's the standard 2025 stack for [domain]?" |
71
- | Features | "What features do [domain] products have?" |
72
- | Architecture | "How are [domain] systems structured?" |
73
- | Pitfalls | "What do [domain] projects get wrong?" |
74
-
75
- Present for approval.
76
-
77
- ## 5. Spawn Research Agents
78
-
79
- ```bash
80
- mkdir -p .planning/research
81
- ```
82
-
83
- **Determine milestone context:**
84
- - If no "Validated" requirements in REQUIREMENTS.md → Greenfield (v1.0)
85
- - If "Validated" requirements exist → Subsequent milestone (v1.1+)
86
-
87
- Spawn all 4 in parallel with rich context:
88
-
89
- ```
90
- Task(prompt="
91
- <research_type>
92
- Project Research — Stack dimension for [domain].
93
- </research_type>
94
-
95
- <milestone_context>
96
- {greenfield OR subsequent}
97
-
98
- Greenfield: Research the standard stack for building [domain] from scratch.
99
- Subsequent: Research what's needed to add [target features] to an existing [domain] app. Don't re-research the existing system.
100
- </milestone_context>
101
-
102
- <question>
103
- [stack question from step 4]
104
- </question>
105
-
106
- <project_context>
107
- [PROJECT.md summary]
108
- </project_context>
109
-
110
- <downstream_consumer>
111
- Your STACK.md feeds into /gsd:create-roadmap. Be prescriptive:
112
- - Specific libraries with versions
113
- - Clear rationale for each choice
114
- - What NOT to use and why
115
- </downstream_consumer>
116
-
117
- <quality_gate>
118
- - [ ] Versions are current (not Claude's training data)
119
- - [ ] Rationale explains WHY, not just WHAT
120
- - [ ] Confidence levels assigned
121
- </quality_gate>
122
-
123
- <output>
124
- Write to: .planning/research/STACK.md
125
- Use template: ~/.claude/get-shit-done/templates/research-project/STACK.md
126
- </output>
127
- ", subagent_type="gsd-project-researcher", description="Stack research")
128
-
129
- Task(prompt="
130
- <research_type>
131
- Project Research — Features dimension for [domain].
132
- </research_type>
133
-
134
- <milestone_context>
135
- {greenfield OR subsequent}
136
-
137
- Greenfield: What features do [domain] products have? What's table stakes vs differentiating?
138
- Subsequent: How do [target features] typically work? What's expected behavior?
139
- </milestone_context>
140
-
141
- <question>
142
- [features question from step 4]
143
- </question>
144
-
145
- <project_context>
146
- [PROJECT.md summary]
147
- </project_context>
148
-
149
- <downstream_consumer>
150
- Your FEATURES.md feeds into /gsd:define-requirements. Categorize clearly:
151
- - Table stakes (must have or users leave)
152
- - Differentiators (competitive advantage)
153
- - Anti-features (things to deliberately NOT build)
154
- </downstream_consumer>
155
-
156
- <quality_gate>
157
- - [ ] Categories are clear
158
- - [ ] Complexity noted for each
159
- - [ ] Dependencies between features identified
160
- </quality_gate>
161
-
162
- <output>
163
- Write to: .planning/research/FEATURES.md
164
- Use template: ~/.claude/get-shit-done/templates/research-project/FEATURES.md
165
- </output>
166
- ", subagent_type="gsd-project-researcher", description="Features research")
167
-
168
- Task(prompt="
169
- <research_type>
170
- Project Research — Architecture dimension for [domain].
171
- </research_type>
172
-
173
- <milestone_context>
174
- {greenfield OR subsequent}
175
-
176
- Greenfield: How are [domain] systems typically structured? What are major components?
177
- Subsequent: How do [target features] integrate with existing [domain] architecture?
178
- </milestone_context>
179
-
180
- <question>
181
- [architecture question from step 4]
182
- </question>
183
-
184
- <project_context>
185
- [PROJECT.md summary]
186
- </project_context>
187
-
188
- <downstream_consumer>
189
- Your ARCHITECTURE.md informs phase structure in roadmap. Include:
190
- - Component boundaries (what talks to what)
191
- - Data flow (how information moves)
192
- - Suggested build order (dependencies between components)
193
- </downstream_consumer>
194
-
195
- <quality_gate>
196
- - [ ] Components clearly defined
197
- - [ ] Boundaries explicit
198
- - [ ] Build order implications noted
199
- </quality_gate>
200
-
201
- <output>
202
- Write to: .planning/research/ARCHITECTURE.md
203
- Use template: ~/.claude/get-shit-done/templates/research-project/ARCHITECTURE.md
204
- </output>
205
- ", subagent_type="gsd-project-researcher", description="Architecture research")
206
-
207
- Task(prompt="
208
- <research_type>
209
- Project Research — Pitfalls dimension for [domain].
210
- </research_type>
211
-
212
- <milestone_context>
213
- {greenfield OR subsequent}
214
-
215
- Greenfield: What do [domain] projects commonly get wrong? Critical mistakes?
216
- Subsequent: What are common mistakes when adding [target features] to [domain]?
217
- </milestone_context>
218
-
219
- <question>
220
- [pitfalls question from step 4]
221
- </question>
222
-
223
- <project_context>
224
- [PROJECT.md summary]
225
- </project_context>
226
-
227
- <downstream_consumer>
228
- Your PITFALLS.md prevents mistakes in roadmap/planning. For each pitfall:
229
- - Warning signs (how to detect early)
230
- - Prevention strategy (how to avoid)
231
- - Which phase should address it
232
- </downstream_consumer>
233
-
234
- <quality_gate>
235
- - [ ] Pitfalls are specific, not generic
236
- - [ ] Prevention is actionable
237
- - [ ] Phase mapping included
238
- </quality_gate>
239
-
240
- <output>
241
- Write to: .planning/research/PITFALLS.md
242
- Use template: ~/.claude/get-shit-done/templates/research-project/PITFALLS.md
243
- </output>
244
- ", subagent_type="gsd-project-researcher", description="Pitfalls research")
245
- ```
246
-
247
- **Announce:** "Spawning 4 research agents... may take 2-3 minutes."
248
-
249
- ## 6. Synthesize Results
250
-
251
- After all agents complete, read their outputs and write `.planning/research/SUMMARY.md`:
252
- - Read template: `~/.claude/get-shit-done/templates/research-project/SUMMARY.md`
253
- - Synthesize executive summary from all 4 files
254
- - Add confidence assessment
255
-
256
- **Critical: Include "Implications for Roadmap" section:**
257
-
258
- ```markdown
259
- ## Implications for Roadmap
260
-
261
- Based on research, suggested phase structure:
262
-
263
- 1. **[Phase name]** — [rationale from research]
264
- - Addresses: [features from FEATURES.md]
265
- - Avoids: [pitfall from PITFALLS.md]
266
- - Uses: [stack element from STACK.md]
267
-
268
- 2. **[Phase name]** — [rationale from research]
269
- - Implements: [architecture component from ARCHITECTURE.md]
270
- ...
271
-
272
- **Phase ordering rationale:**
273
- - [Why this order based on dependencies discovered in ARCHITECTURE.md]
274
- - [Why this grouping based on PITFALLS.md prevention strategies]
275
-
276
- **Research flags for phases:**
277
- - Phase [X]: Likely needs deeper research (reason)
278
- - Phase [Y]: Standard patterns, unlikely to need research
279
- ```
280
-
281
- This section directly feeds into `/gsd:create-roadmap`.
282
-
283
- ## 7. Commit Research
284
-
285
- ```bash
286
- git add .planning/research/
287
- git commit -m "docs: research [domain] ecosystem
288
-
289
- Key findings:
290
- - Stack: [one-liner]
291
- - Architecture: [one-liner]
292
- - Critical pitfall: [one-liner]"
293
- ```
294
-
295
- ## 8. Present Results
296
-
297
- ```
298
- Research complete:
299
-
300
- Files: SUMMARY.md, STACK.md, FEATURES.md, ARCHITECTURE.md, PITFALLS.md
301
-
302
- Key findings:
303
- - Stack: [one-liner]
304
- - Architecture: [one-liner]
305
- - Critical pitfall: [one-liner]
306
-
307
- ---
308
- ## > Next Up
309
- **Define requirements** - `/gsd:define-requirements`
310
- <sub>`/clear` first</sub>
311
- ---
312
- ```
313
-
314
- </process>
315
-
316
- <success_criteria>
317
- - [ ] PROJECT.md validated
318
- - [ ] Domain identified and approved
319
- - [ ] 4 gsd-project-researcher agents spawned in parallel
320
- - [ ] All research files created
321
- - [ ] SUMMARY.md synthesized with roadmap implications
322
- - [ ] Research committed
323
- </success_criteria>
@@ -1,93 +0,0 @@
1
- # Milestone Context Template
2
-
3
- Template for `.planning/MILESTONE-CONTEXT.md` - temporary handoff file from discuss-milestone to create-milestone.
4
-
5
- **Purpose:** Persist milestone discussion context so `/clear` can be used between commands. This file is consumed by `/gsd:new-milestone` and deleted after the milestone is created.
6
-
7
- ---
8
-
9
- ## File Template
10
-
11
- ```markdown
12
- # Milestone Context
13
-
14
- **Generated:** [date]
15
- **Status:** Ready for /gsd:new-milestone
16
-
17
- <features>
18
- ## Features to Build
19
-
20
- [Features identified during discussion - the substance of this milestone]
21
-
22
- - **[Feature 1]**: [description]
23
- - **[Feature 2]**: [description]
24
- - **[Feature 3]**: [description]
25
-
26
- </features>
27
-
28
- <scope>
29
- ## Scope
30
-
31
- **Suggested name:** v[X.Y] [Theme Name]
32
- **Estimated phases:** [N]
33
- **Focus:** [One sentence theme/focus]
34
-
35
- </scope>
36
-
37
- <phase_mapping>
38
- ## Phase Mapping
39
-
40
- [How features map to phases - rough breakdown]
41
-
42
- - Phase [N]: [Feature/goal]
43
- - Phase [N+1]: [Feature/goal]
44
- - Phase [N+2]: [Feature/goal]
45
-
46
- </phase_mapping>
47
-
48
- <constraints>
49
- ## Constraints
50
-
51
- [Any constraints or boundaries mentioned during discussion]
52
-
53
- - [Constraint 1]
54
- - [Constraint 2]
55
-
56
- </constraints>
57
-
58
- <notes>
59
- ## Additional Context
60
-
61
- [Anything else captured during discussion that informs the milestone]
62
-
63
- </notes>
64
-
65
- ---
66
-
67
- *This file is temporary. It will be deleted after /gsd:new-milestone creates the milestone.*
68
- ```
69
-
70
- <guidelines>
71
- **This is a handoff artifact, not permanent documentation.**
72
-
73
- The file exists only to pass context from `discuss-milestone` to `create-milestone` across a `/clear` boundary.
74
-
75
- **Lifecycle:**
76
- 1. `/gsd:discuss-milestone` creates this file at end of discussion
77
- 2. User runs `/clear` (safe now - context is persisted)
78
- 3. `/gsd:new-milestone` reads this file
79
- 4. `/gsd:new-milestone` uses context to populate milestone
80
- 5. `/gsd:new-milestone` deletes this file after successful creation
81
-
82
- **Content should include:**
83
- - Features identified (the core of what to build)
84
- - Suggested milestone name/theme
85
- - Rough phase mapping
86
- - Any constraints or scope boundaries
87
- - Notes from discussion
88
-
89
- **Content should NOT include:**
90
- - Technical analysis (that comes during phase research)
91
- - Detailed phase specifications (create-milestone handles that)
92
- - Implementation details
93
- </guidelines>