@brunosps00/dev-workflow 0.3.0 → 0.4.0

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.
Files changed (29) hide show
  1. package/README.md +9 -2
  2. package/lib/constants.js +2 -0
  3. package/package.json +1 -1
  4. package/scaffold/en/commands/dw-analyze-project.md +2 -0
  5. package/scaffold/en/commands/dw-autopilot.md +216 -0
  6. package/scaffold/en/commands/dw-code-review.md +1 -1
  7. package/scaffold/en/commands/dw-create-prd.md +1 -1
  8. package/scaffold/en/commands/dw-create-techspec.md +1 -1
  9. package/scaffold/en/commands/dw-help.md +10 -0
  10. package/scaffold/en/commands/dw-intel.md +2 -0
  11. package/scaffold/en/commands/dw-quick.md +2 -0
  12. package/scaffold/en/commands/dw-redesign-ui.md +2 -0
  13. package/scaffold/en/commands/dw-refactoring-analysis.md +1 -1
  14. package/scaffold/en/commands/dw-resume.md +15 -0
  15. package/scaffold/en/commands/dw-run-plan.md +2 -0
  16. package/scaffold/en/commands/dw-run-task.md +1 -1
  17. package/scaffold/pt-br/commands/dw-analyze-project.md +2 -0
  18. package/scaffold/pt-br/commands/dw-autopilot.md +216 -0
  19. package/scaffold/pt-br/commands/dw-code-review.md +1 -1
  20. package/scaffold/pt-br/commands/dw-create-prd.md +1 -1
  21. package/scaffold/pt-br/commands/dw-create-techspec.md +1 -1
  22. package/scaffold/pt-br/commands/dw-help.md +10 -0
  23. package/scaffold/pt-br/commands/dw-intel.md +2 -0
  24. package/scaffold/pt-br/commands/dw-quick.md +2 -0
  25. package/scaffold/pt-br/commands/dw-redesign-ui.md +2 -0
  26. package/scaffold/pt-br/commands/dw-refactoring-analysis.md +1 -1
  27. package/scaffold/pt-br/commands/dw-resume.md +15 -0
  28. package/scaffold/pt-br/commands/dw-run-plan.md +2 -0
  29. package/scaffold/pt-br/commands/dw-run-task.md +1 -1
package/README.md CHANGED
@@ -10,7 +10,7 @@ npx @brunosps00/dev-workflow init
10
10
 
11
11
  This will:
12
12
  1. Ask you to select a language (English or Portuguese)
13
- 2. Create `.dw/commands/` with 22 workflow commands
13
+ 2. Create `.dw/commands/` with 23 workflow commands
14
14
  3. Create `.dw/templates/` with document templates
15
15
  4. Create `.dw/rules/` (populated by `/dw-analyze-project`)
16
16
  5. Install bundled skills (ui-ux-pro-max, security-review, etc.) to `.agents/skills/`
@@ -29,6 +29,9 @@ npx @brunosps00/dev-workflow install-deps
29
29
  #### `/dw-brainstorm`
30
30
  Facilitates structured ideation before opening a PRD or implementation. Explores multiple directions — conservative, balanced, and bold — with trade-offs for each, then converges on concrete next steps. No code is written or files modified.
31
31
 
32
+ #### `/dw-autopilot`
33
+ Full pipeline orchestrator that takes a wish and automatically runs the entire development flow: codebase intelligence, research (conditional), brainstorm, PRD, techspec, tasks, execution, QA, review, and commit. Stops at 3 gates: PRD approval, tasks approval, and PR confirmation. With GSD installed, leverages plan verification and parallel execution.
34
+
32
35
  #### `/dw-create-prd`
33
36
  Creates a Product Requirements Document by first asking at least 7 clarification questions to fully understand the feature. Generates a structured PRD with numbered functional requirements focused on what and why, saved to `.dw/spec/prd-[feature-name]/prd.md`.
34
37
 
@@ -105,6 +108,10 @@ Displays the complete guide of available commands, integration flows, and when t
105
108
  ```
106
109
  /dw-resume (pick up where you left off)
107
110
  |
111
+ /dw-autopilot "wish" ------> Runs entire pipeline automatically
112
+ (gates: PRD approval, Tasks approval, PR confirmation)
113
+ --- OR ---
114
+
108
115
  /dw-brainstorm ------> /dw-create-prd --> .dw/spec/prd-{name}/prd.md
109
116
  |
110
117
  /dw-create-techspec --> .dw/spec/prd-{name}/techspec.md
@@ -147,7 +154,7 @@ All wrappers point to `.dw/commands/` as the single source of truth.
147
154
  ```
148
155
  your-project/
149
156
  ├── .dw/
150
- │ ├── commands/ # 22 workflow command files
157
+ │ ├── commands/ # 23 workflow command files
151
158
  │ ├── templates/ # Document templates (PRD, TechSpec, etc.)
152
159
  │ ├── rules/ # Project-specific rules (run /dw-analyze-project)
153
160
  │ ├── references/ # Reference documentation
package/lib/constants.js CHANGED
@@ -1,6 +1,7 @@
1
1
  const COMMANDS = {
2
2
  en: [
3
3
  { name: 'dw-analyze-project', description: 'Analyze repository stack, patterns, and conventions to generate project rules' },
4
+ { name: 'dw-autopilot', description: 'Full pipeline orchestrator: from a wish to a PR with minimal intervention (research, PRD, tasks, execution, QA, review, commit)' },
4
5
  { name: 'dw-brainstorm', description: 'Explore ideas and directions before starting implementation' },
5
6
  { name: 'dw-bugfix', description: 'Analyze and fix bugs with automatic triage (bug vs feature vs scope)' },
6
7
  { name: 'dw-code-review', description: 'Formal code review (Level 3) with persisted report' },
@@ -25,6 +26,7 @@ const COMMANDS = {
25
26
  ],
26
27
  'pt-br': [
27
28
  { name: 'dw-analyze-project', description: 'Analisa stack, patterns e convencoes do repositorio para gerar regras do projeto' },
29
+ { name: 'dw-autopilot', description: 'Orquestrador completo: de um desejo ate o PR com minima intervencao (pesquisa, PRD, tasks, execucao, QA, review, commit)' },
28
30
  { name: 'dw-brainstorm', description: 'Explorar ideias e direcoes antes de comecar a implementacao' },
29
31
  { name: 'dw-bugfix', description: 'Analisar e corrigir bugs com triagem automatica (bug vs feature vs escopo)' },
30
32
  { name: 'dw-code-review', description: 'Code review formal (Nivel 3) com relatorio persistido' },
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@brunosps00/dev-workflow",
3
- "version": "0.3.0",
3
+ "version": "0.4.0",
4
4
  "description": "AI-driven development workflow commands for any project. Scaffolds a complete PRD-to-PR pipeline with multi-platform AI assistant support.",
5
5
  "bin": {
6
6
  "dev-workflow": "./bin/dev-workflow.js"
@@ -230,6 +230,8 @@ For each module/project detected, identify:
230
230
  When React is detected, run `npx react-doctor@latest --verbose` and include the health score in the generated rules as a baseline metric.
231
231
  For Angular projects, run `ng lint` and document any warnings as baseline.
232
232
 
233
+ <critical>If GSD is installed, running /gsd-map-codebase is MANDATORY. The command CANNOT be considered complete without executing ALL applicable steps, including generating the index in .planning/intel/.</critical>
234
+
233
235
  #### Codebase Intelligence (GSD)
234
236
 
235
237
  If GSD (get-shit-done-cc) is installed in the project:
@@ -0,0 +1,216 @@
1
+ <system_instructions>
2
+ You are a full pipeline orchestrator. This command receives a user's wish and automatically executes the entire development flow, from research to commit, stopping only at critical gates.
3
+
4
+ <critical>This command MUST execute ALL applicable pipeline steps. Do NOT skip any step. If a step is conditional, evaluate the condition and execute if applicable.</critical>
5
+ <critical>The ONLY pause moments are the 3 gates defined below. Between gates, execute everything automatically without asking for confirmation.</critical>
6
+ <critical>Each step MUST follow the complete instructions from the corresponding command in `.dw/commands/`. Read and execute the full command, not a summarized version.</critical>
7
+
8
+ ## When to Use
9
+ - Use when you want to go from an idea to a PR with minimal manual intervention
10
+ - Use for complete features that go through the entire pipeline (research, planning, execution, quality)
11
+ - Do NOT use for one-off changes (use `/dw-quick`)
12
+ - Do NOT use to fix bugs (use `/dw-bugfix`)
13
+ - Do NOT use when you want manual control between each phase (use individual commands)
14
+
15
+ ## Pipeline Position
16
+ **Predecessor:** (user's wish) | **Successor:** (PR merge)
17
+
18
+ ## Input Variables
19
+
20
+ | Variable | Description | Example |
21
+ |----------|-------------|---------|
22
+ | `{{WISH}}` | Description of what the user wants to build | "push notification system with per-channel preferences" |
23
+
24
+ ## Approval Gates
25
+
26
+ The autopilot stops ONLY at these 3 moments:
27
+
28
+ 1. **GATE 1 — PRD**: Presents the generated PRD and awaits user approval before generating techspec/tasks
29
+ 2. **GATE 2 — Tasks**: Presents the task list and awaits approval before starting execution
30
+ 3. **GATE 3 — PR**: After automatic commit, asks if the user wants to generate the Pull Request
31
+
32
+ ## Session Resumption
33
+
34
+ If this command is invoked to resume an interrupted autopilot (via `/dw-resume`):
35
+
36
+ <critical>Read the `autopilot-state.json` file in the PRD directory. Skip ALL steps listed in `completed_steps`. Resume execution from `current_step`. Gates already passed (listed in `gates_passed`) MUST NOT be re-presented.</critical>
37
+
38
+ 1. Read `.dw/spec/prd-[name]/autopilot-state.json`
39
+ 2. Report: "Resuming autopilot from step [N] ([name]). Steps 1-[N-1] already completed."
40
+ 3. Continue execution normally from the indicated step
41
+
42
+ ## Full Pipeline
43
+
44
+ ### Step 1: Codebase Intelligence
45
+
46
+ <critical>If `.planning/intel/` exists, querying it is MANDATORY before starting.</critical>
47
+
48
+ - Query `.planning/intel/` via `/gsd-intel` (if available) or `.dw/rules/` to understand project context
49
+ - Identify: tech stack, existing patterns, related features
50
+
51
+ ### Step 2: Research (Conditional)
52
+
53
+ Evaluate whether the topic requires deep research:
54
+ - **YES** (run `/dw-deep-research`): new technology for the project, unknown domain, external API integrations, critical architectural decisions
55
+ - **NO** (skip to step 3): simple feature in an already mapped domain, refactoring existing code, basic CRUD
56
+
57
+ If executed, use `standard` mode by default. Incorporate findings into subsequent steps.
58
+
59
+ ### Step 3: Brainstorm
60
+
61
+ Run `/dw-brainstorm` with accumulated context (intel + research).
62
+ - Generate 3 directions
63
+ - Automatically converge on the most pragmatic option for the project context
64
+ - Do NOT wait for user approval (brainstorm is automatic in autopilot)
65
+
66
+ ### Step 4: PRD
67
+
68
+ Run `/dw-create-prd` using brainstorm findings.
69
+ - Follow all command instructions (clarification questions answered based on accumulated context)
70
+ - Generate the complete PRD in `.dw/spec/prd-[name]/prd.md`
71
+
72
+ ### === GATE 1: PRD Approval ===
73
+
74
+ Present to the user:
75
+ - Summary of functional requirements
76
+ - Decisions made automatically
77
+ - Open questions (if any)
78
+
79
+ **Wait for explicit approval.** If the user requests changes, adjust and re-present.
80
+
81
+ ### Step 5: TechSpec
82
+
83
+ Run `/dw-create-techspec` from the approved PRD.
84
+ - Follow all command instructions
85
+ - Generate in `.dw/spec/prd-[name]/techspec.md`
86
+
87
+ ### Step 6: Tasks
88
+
89
+ Run `/dw-create-tasks` from PRD + TechSpec.
90
+ - Follow all command instructions
91
+ - Generate individual tasks in `.dw/spec/prd-[name]/`
92
+
93
+ ### === GATE 2: Tasks Approval ===
94
+
95
+ Present to the user:
96
+ - Task list with brief descriptions
97
+ - Dependencies between tasks
98
+ - Total effort estimate
99
+
100
+ **Wait for explicit approval.** If the user requests changes, adjust and re-present.
101
+
102
+ ### Step 7: Design Contract (Conditional)
103
+
104
+ Evaluate whether tasks involve frontend:
105
+ - **YES** (run `/dw-redesign-ui`): if there are tasks with visual components AND the `ui-ux-pro-max` skill is available
106
+ - Generate the design contract in `.dw/spec/prd-[name]/design-contract.md`
107
+ - Do NOT wait for approval (contract is automatic in autopilot, based on PRD requirements)
108
+ - **NO** (skip to step 8): purely backend/infra tasks
109
+
110
+ ### Step 8: Execution
111
+
112
+ Run `/dw-run-plan` with the PRD path.
113
+ - Follow ALL command instructions, including GSD integration (plan verification, parallel execution)
114
+ - Each task follows `/dw-run-task` with Level 1 validation
115
+
116
+ ### Step 9: Implementation Review (Loop)
117
+
118
+ Run `/dw-review-implementation` to verify PRD compliance (Level 2).
119
+ - If gaps found: fix automatically and re-run the review
120
+ - Maximum 3 correction cycles
121
+ - Do NOT advance to QA until the review passes
122
+
123
+ ### Step 10: Visual QA
124
+
125
+ Run `/dw-run-qa` with Playwright MCP.
126
+ - Test happy paths, edge cases, negative flows, accessibility
127
+ - Document bugs with screenshots
128
+
129
+ ### Step 11: Fix QA (Conditional)
130
+
131
+ If QA found bugs:
132
+ - Run `/dw-fix-qa` to fix and retest
133
+ - Loop until stable
134
+
135
+ ### Step 12: Implementation Review (Post-QA)
136
+
137
+ Run `/dw-review-implementation` again to confirm QA fixes did not break PRD compliance.
138
+ - If gaps found: fix and re-run
139
+ - Maximum 3 cycles
140
+
141
+ ### Step 13: Code Review
142
+
143
+ Run `/dw-code-review` (Level 3) for formal review.
144
+ - Generate persisted report
145
+
146
+ ### Step 14: Commit
147
+
148
+ Run `/dw-commit` automatically.
149
+ - Semantic commits following Conventional Commits
150
+ - Do NOT wait for approval
151
+
152
+ ### === GATE 3: Pull Request ===
153
+
154
+ Ask the user: **"Commits completed. Do you want to generate the Pull Request?"**
155
+
156
+ - **YES**: run `/dw-generate-pr` with the target branch
157
+ - **NO**: inform that commits are ready and the user can generate the PR manually later
158
+
159
+ ## GSD Integration
160
+
161
+ <critical>When GSD is installed, ALL GSD integrations from each individual command MUST be executed. The autopilot is not an excuse to skip GSD steps.</critical>
162
+
163
+ If GSD (get-shit-done-cc) is installed:
164
+ - Step 1: use `/gsd-intel` for querying
165
+ - Step 8: use plan verification + parallel execution
166
+ - All commands: follow their individual GSD sections
167
+
168
+ If GSD is NOT installed:
169
+ - All commands work normally without GSD
170
+
171
+ ## State Persistence
172
+
173
+ <critical>The autopilot MUST save its state after each completed step to allow resumption via `/dw-resume` in case of interruption.</critical>
174
+
175
+ Save the file `.dw/spec/prd-[name]/autopilot-state.json` with the following format:
176
+
177
+ ```json
178
+ {
179
+ "mode": "autopilot",
180
+ "wish": "original user description",
181
+ "prd_path": ".dw/spec/prd-[name]",
182
+ "current_step": 8,
183
+ "completed_steps": [1, 2, 3, 4, 5, 6, 7],
184
+ "skipped_steps": [2],
185
+ "gates_passed": ["prd", "tasks"],
186
+ "started_at": "2026-04-10T14:30:00Z",
187
+ "last_updated": "2026-04-10T15:45:00Z"
188
+ }
189
+ ```
190
+
191
+ - Update `current_step` and `completed_steps` BEFORE starting each step
192
+ - If the session drops, `/dw-resume` will read this file and continue from the correct step
193
+ - When the pipeline finishes (after commit or PR), remove the file or mark `"status": "completed"`
194
+
195
+ ## Progress Format
196
+
197
+ During execution, report progress in this format:
198
+
199
+ ```
200
+ === AUTOPILOT =====================================
201
+ OK [1/14] Codebase Intelligence
202
+ OK [2/14] Research (skipped — known domain)
203
+ OK [3/14] Brainstorm
204
+ OK [4/14] PRD
205
+ PAUSE [GATE 1] Awaiting PRD approval...
206
+ ===================================================
207
+ ```
208
+
209
+ ## Closing
210
+
211
+ At the end, present:
212
+ - PR link (if generated)
213
+ - Summary: steps executed, steps skipped, estimated time saved
214
+ - Suggested next steps (merge, deploy, etc.)
215
+
216
+ </system_instructions>
@@ -26,7 +26,7 @@ When available in the project under `./.agents/skills/`, use these skills as ana
26
26
 
27
27
  ## Codebase Intelligence
28
28
 
29
- If `.planning/intel/` exists, query before analysis:
29
+ <critical>If `.planning/intel/` exists, querying it is MANDATORY before writing requirements. Do NOT skip this step.</critical>
30
30
  - Internally run: `/gsd-intel "documented conventions, anti-patterns, and decision spaces"`
31
31
  - Prioritize findings that violate documented conventions
32
32
  - Check if questionable architectural decisions are intentional (documented as decision spaces)
@@ -34,7 +34,7 @@
34
34
 
35
35
  ## Codebase Intelligence
36
36
 
37
- If `.planning/intel/` exists, query before writing requirements:
37
+ <critical>If `.planning/intel/` exists, querying it is MANDATORY before writing requirements. Do NOT skip this step.</critical>
38
38
  - Internally run: `/gsd-intel "existing features in the [PRD topic] domain"`
39
39
  - Use findings to avoid duplicating existing functionality and reference established patterns
40
40
 
@@ -23,7 +23,7 @@
23
23
 
24
24
  ## Codebase Intelligence
25
25
 
26
- If `.planning/intel/` exists, query before proposing architecture:
26
+ <critical>If `.planning/intel/` exists, querying it is MANDATORY before writing requirements. Do NOT skip this step.</critical>
27
27
  - Internally run: `/gsd-intel "architectural patterns and technical decisions in the project"`
28
28
  - Align proposals with existing patterns; flag deviations explicitly
29
29
 
@@ -105,6 +105,7 @@ This workspace uses an AI command system that automates the full development cyc
105
105
  | `/dw-quick` | Execute a one-off task with workflow guarantees without PRD | Change description | Code + commit |
106
106
  | `/dw-resume` | Restore session context and suggest next step | (none) | Summary + suggestion |
107
107
  | `/dw-intel` | Query codebase intelligence about patterns and architecture | Question | Answer with sources |
108
+ | `/dw-autopilot` | Full pipeline orchestrator: from a wish to a PR with minimal intervention | Wish description | PRD + code + commits + PR |
108
109
 
109
110
  ### Research
110
111
 
@@ -237,6 +238,11 @@ LEVEL 3 - Formal Code Review (/dw-code-review)
237
238
  /dw-generate-pr main # 5. PR
238
239
  ```
239
240
 
241
+ ### Autopilot (Full Pipeline)
242
+ ```bash
243
+ /dw-autopilot "description of what you want to build" # Research → PRD → Tasks → Code → QA → PR
244
+ ```
245
+
240
246
  ### Quick Task
241
247
  ```bash
242
248
  /dw-quick "change description" # Implement + validate + commit
@@ -275,6 +281,7 @@ your-project/
275
281
  │ │ ├── dw-refactoring-analysis.md
276
282
  │ │ ├── dw-review-implementation.md
277
283
  │ │ ├── dw-analyze-project.md
284
+ │ │ ├── dw-autopilot.md
278
285
  │ │ ├── dw-deep-research.md
279
286
  │ │ ├── dw-intel.md
280
287
  │ │ ├── dw-quick.md
@@ -348,4 +355,7 @@ Commands work across multiple AI tools, all pointing to the same source `.dw/com
348
355
  **Q: Does `/dw-quick` replace `/dw-run-task`?**
349
356
  - No. `/dw-quick` is for one-off changes without a PRD. `/dw-run-task` executes tasks from a structured plan with PRD and TechSpec.
350
357
 
358
+ **Q: Does `/dw-autopilot` replace all other commands?**
359
+ - No. It orchestrates existing commands in sequence. You can still use each command individually for manual control. Autopilot is for when you want to go from a wish to a PR with minimal intervention.
360
+
351
361
  </system_instructions>
@@ -31,6 +31,8 @@ You are a codebase intelligence assistant. This command exists to answer questio
31
31
 
32
32
  ## GSD Integration
33
33
 
34
+ <critical>When .planning/intel/ exists, querying via /gsd-intel is MANDATORY as the primary source. Do NOT skip this query.</critical>
35
+
34
36
  If GSD (get-shit-done-cc) is installed and `.planning/intel/` exists:
35
37
  - Delegate to `/gsd-intel "{{QUERY}}"` for indexed lookup
36
38
  - GSD returns information from: architectural assumptions, decision spaces, behavioral references, UI patterns
@@ -31,6 +31,8 @@ You are a quick task executor. This command exists to implement one-off changes
31
31
 
32
32
  ## GSD Integration
33
33
 
34
+ <critical>When GSD is installed, delegation to /gsd-quick is MANDATORY for tracking.</critical>
35
+
34
36
  If GSD (get-shit-done-cc) is installed in the project:
35
37
  - Delegate to `/gsd-quick` for tracking in `.planning/quick/`
36
38
  - The task is registered in history for future lookup via `/dw-intel`
@@ -65,6 +65,8 @@ Use diagnostic tools based on the project's framework:
65
65
 
66
66
  ## GSD Integration
67
67
 
68
+ <critical>When GSD is installed, registering the design contract in .planning/ and querying .planning/intel/ are MANDATORY.</critical>
69
+
68
70
  If GSD (get-shit-done-cc) is installed in the project:
69
71
  - After generating the design contract, register in `.planning/` for cross-session persistence
70
72
  - Query `.planning/intel/` in the audit phase for existing UI patterns
@@ -30,7 +30,7 @@ For Angular projects, use `ng lint` as an analytical complement.
30
30
 
31
31
  ## Codebase Intelligence
32
32
 
33
- If `.planning/intel/` exists, query before the audit:
33
+ <critical>If `.planning/intel/` exists, querying it is MANDATORY before writing requirements. Do NOT skip this step.</critical>
34
34
  - Internally run: `/gsd-intel "tech debt, decision spaces, and known technical debt"`
35
35
  - Contextualize findings with already documented decisions
36
36
  - Avoid flagging as a smell something that is an intentional recorded decision
@@ -13,6 +13,19 @@ You are a session continuity assistant. This command exists to restore context f
13
13
 
14
14
  ## Required Behavior
15
15
 
16
+ <critical>BEFORE any analysis, check for an interrupted autopilot. Look for `autopilot-state.json` in ALL directories inside `.dw/spec/`. If you find one without `"status": "completed"`, autopilot resumption takes PRIORITY over any other suggestion.</critical>
17
+
18
+ ### Interrupted Autopilot Detection
19
+
20
+ 1. Search for `.dw/spec/*/autopilot-state.json`
21
+ 2. If you find a file with `"mode": "autopilot"` and no `"status": "completed"`:
22
+ - Present: original wish, step where it stopped, steps already completed
23
+ - Ask: **"Found an interrupted autopilot at step [N] ([step name]). Do you want to continue where you left off?"**
24
+ - If **YES**: run `/dw-autopilot` instructing it to resume from `current_step` using the state file. The autopilot must read the state and skip already completed steps.
25
+ - If **NO**: continue with the normal resume flow below
26
+
27
+ ### Normal Flow (no pending autopilot)
28
+
16
29
  1. Read `.dw/spec/` and identify PRDs with pending tasks (`- [ ]` checkboxes in tasks.md)
17
30
  2. Read `git log --oneline -10` to identify the last work performed
18
31
  3. Identify the active branch and whether there are uncommitted changes
@@ -22,6 +35,8 @@ You are a session continuity assistant. This command exists to restore context f
22
35
 
23
36
  ## GSD Integration
24
37
 
38
+ <critical>When GSD is installed, delegation to /gsd-resume-work is MANDATORY, not optional.</critical>
39
+
25
40
  If GSD (get-shit-done-cc) is installed in the project:
26
41
  - Delegate to `/gsd-resume-work` for cross-session state restoration from `.planning/STATE.md`
27
42
  - Incorporate additional context: persistent threads, backlog, notes
@@ -143,6 +143,8 @@ If a task FAILS during execution:
143
143
 
144
144
  ## GSD Integration
145
145
 
146
+ <critical>When GSD is installed, plan verification and parallel execution are MANDATORY, not optional. The command MUST NOT skip these steps.</critical>
147
+
146
148
  ### Plan Verification (Pre-Execution)
147
149
 
148
150
  If GSD (get-shit-done-cc) is installed in the project:
@@ -23,7 +23,7 @@ When available in the project at `./.agents/skills/`, use these skills as specia
23
23
 
24
24
  ## Codebase Intelligence
25
25
 
26
- If `.planning/intel/` exists, query before implementing:
26
+ <critical>If `.planning/intel/` exists, querying it is MANDATORY before writing requirements. Do NOT skip this step.</critical>
27
27
  - Internally run: `/gsd-intel "implementation patterns in [task target area]"`
28
28
  - Follow conventions found for file structure, naming, and error handling
29
29
 
@@ -218,6 +218,8 @@ Para cada projeto/módulo detectado, identificar:
218
218
  Quando React for detectado, execute `npx react-doctor@latest --verbose` e inclua o health score nas rules geradas como métrica baseline.
219
219
  Para projetos Angular, execute `ng lint` e documente warnings como baseline.
220
220
 
221
+ <critical>Se o GSD estiver instalado, a execução do /gsd-map-codebase é OBRIGATÓRIA. O comando NÃO pode ser considerado completo sem executar TODOS os passos aplicáveis, incluindo a geração do índice em .planning/intel/.</critical>
222
+
221
223
  #### Inteligência do Codebase (GSD)
222
224
 
223
225
  Se o GSD (get-shit-done-cc) estiver instalado no projeto:
@@ -0,0 +1,216 @@
1
+ <system_instructions>
2
+ Voce e um orquestrador de pipeline completo. Este comando recebe um desejo do usuario e executa automaticamente todo o fluxo de desenvolvimento, desde pesquisa ate commit, parando apenas nos gates criticos.
3
+
4
+ <critical>Este comando DEVE executar TODAS as etapas aplicaveis do pipeline. NAO pule nenhuma etapa. Se uma etapa e condicional, avalie a condicao e execute se aplicavel.</critical>
5
+ <critical>Os UNICOS momentos de pausa sao os 3 gates definidos abaixo. Entre os gates, execute tudo automaticamente sem pedir confirmacao.</critical>
6
+ <critical>Cada etapa DEVE seguir as instrucoes completas do comando correspondente em `.dw/commands/`. Leia e execute o comando inteiro, nao uma versao resumida.</critical>
7
+
8
+ ## Quando Usar
9
+ - Use quando quiser ir de uma ideia ate um PR com minima intervencao manual
10
+ - Use para features completas que passam por todo o pipeline (pesquisa, planejamento, execucao, qualidade)
11
+ - NAO use para mudancas pontuais (use `/dw-quick`)
12
+ - NAO use para corrigir bugs (use `/dw-bugfix`)
13
+ - NAO use quando quiser controle manual entre cada fase (use os comandos individuais)
14
+
15
+ ## Posicao no Pipeline
16
+ **Antecessor:** (desejo do usuario) | **Sucessor:** (merge do PR)
17
+
18
+ ## Variaveis de Entrada
19
+
20
+ | Variavel | Descricao | Exemplo |
21
+ |----------|-----------|---------|
22
+ | `{{WISH}}` | Descricao do que o usuario quer construir | "sistema de notificacoes push com preferencias por canal" |
23
+
24
+ ## Gates de Aprovacao
25
+
26
+ O autopilot para APENAS nestes 3 momentos:
27
+
28
+ 1. **GATE 1 — PRD**: Apresenta o PRD gerado e aguarda aprovacao do usuario antes de gerar techspec/tasks
29
+ 2. **GATE 2 — Tasks**: Apresenta a lista de tasks e aguarda aprovacao antes de iniciar a execucao
30
+ 3. **GATE 3 — PR**: Apos commit automatico, pergunta se o usuario quer gerar o Pull Request
31
+
32
+ ## Retomada de Sessao
33
+
34
+ Se este comando for invocado para retomar um autopilot interrompido (via `/dw-resume`):
35
+
36
+ <critical>Leia o arquivo `autopilot-state.json` no diretorio do PRD. Pule TODAS as etapas listadas em `completed_steps`. Retome a execucao a partir de `current_step`. Gates ja passados (listados em `gates_passed`) NAO devem ser reapresentados.</critical>
37
+
38
+ 1. Leia `.dw/spec/prd-[nome]/autopilot-state.json`
39
+ 2. Reporte: "Retomando autopilot da etapa [N] ([nome]). Etapas 1-[N-1] ja completadas."
40
+ 3. Continue a execucao normalmente a partir da etapa indicada
41
+
42
+ ## Pipeline Completo
43
+
44
+ ### Etapa 1: Inteligencia do Codebase
45
+
46
+ <critical>Se `.planning/intel/` existir, a consulta e OBRIGATORIA antes de iniciar.</critical>
47
+
48
+ - Consulte `.planning/intel/` via `/gsd-intel` (se disponivel) ou `.dw/rules/` para entender o contexto do projeto
49
+ - Identifique: stack tecnologica, padroes existentes, features relacionadas
50
+
51
+ ### Etapa 2: Pesquisa (Condicional)
52
+
53
+ Avalie se o topico necessita de pesquisa profunda:
54
+ - **SIM** (execute `/dw-deep-research`): tecnologia nova para o projeto, dominio desconhecido, integracoes com APIs externas, decisoes arquiteturais criticas
55
+ - **NAO** (pule para etapa 3): feature simples no dominio ja mapeado, refatoracao de algo existente, CRUD basico
56
+
57
+ Se executar, use modo `standard` por padrao. Incorpore os findings nas etapas seguintes.
58
+
59
+ ### Etapa 3: Brainstorm
60
+
61
+ Execute `/dw-brainstorm` com o contexto acumulado (intel + pesquisa).
62
+ - Gere 3 direcoes
63
+ - Convirja automaticamente na opcao mais pragmatica para o contexto do projeto
64
+ - NAO aguarde aprovacao do usuario (brainstorm e automatico no autopilot)
65
+
66
+ ### Etapa 4: PRD
67
+
68
+ Execute `/dw-create-prd` usando os findings do brainstorm.
69
+ - Siga todas as instrucoes do comando (perguntas de esclarecimento respondidas com base no contexto acumulado)
70
+ - Gere o PRD completo em `.dw/spec/prd-[nome]/prd.md`
71
+
72
+ ### ═══ GATE 1: Aprovacao do PRD ═══
73
+
74
+ Apresente ao usuario:
75
+ - Resumo dos requisitos funcionais
76
+ - Decisoes tomadas automaticamente
77
+ - Questoes em aberto (se houver)
78
+
79
+ **Aguarde aprovacao explicita.** Se o usuario pedir mudancas, ajuste e reapresente.
80
+
81
+ ### Etapa 5: TechSpec
82
+
83
+ Execute `/dw-create-techspec` a partir do PRD aprovado.
84
+ - Siga todas as instrucoes do comando
85
+ - Gere em `.dw/spec/prd-[nome]/techspec.md`
86
+
87
+ ### Etapa 6: Tasks
88
+
89
+ Execute `/dw-create-tasks` a partir do PRD + TechSpec.
90
+ - Siga todas as instrucoes do comando
91
+ - Gere tasks individuais em `.dw/spec/prd-[nome]/`
92
+
93
+ ### ═══ GATE 2: Aprovacao das Tasks ═══
94
+
95
+ Apresente ao usuario:
96
+ - Lista de tasks com descricao resumida
97
+ - Dependencias entre tasks
98
+ - Estimativa de esforco total
99
+
100
+ **Aguarde aprovacao explicita.** Se o usuario pedir mudancas, ajuste e reapresente.
101
+
102
+ ### Etapa 7: Design Contract (Condicional)
103
+
104
+ Avalie se as tasks envolvem frontend:
105
+ - **SIM** (execute `/dw-redesign-ui`): se houver tasks com componentes visuais E a skill `ui-ux-pro-max` estiver disponivel
106
+ - Gere o design contract em `.dw/spec/prd-[nome]/design-contract.md`
107
+ - NAO aguarde aprovacao (o contract e automatico no autopilot, baseado nos requisitos do PRD)
108
+ - **NAO** (pule para etapa 8): tasks puramente backend/infra
109
+
110
+ ### Etapa 8: Execucao
111
+
112
+ Execute `/dw-run-plan` com o path do PRD.
113
+ - Siga TODAS as instrucoes do comando, incluindo integracao GSD (verificacao de plano, execucao paralela)
114
+ - Cada task segue `/dw-run-task` com validacao Level 1
115
+
116
+ ### Etapa 9: Review de Implementacao (Loop)
117
+
118
+ Execute `/dw-review-implementation` para verificar PRD compliance (Level 2).
119
+ - Se encontrar gaps: corrija automaticamente e re-execute o review
120
+ - Maximo 3 ciclos de correcao
121
+ - NAO avance para QA ate que o review passe
122
+
123
+ ### Etapa 10: QA Visual
124
+
125
+ Execute `/dw-run-qa` com Playwright MCP.
126
+ - Teste happy paths, edge cases, fluxos negativos, acessibilidade
127
+ - Documente bugs com screenshots
128
+
129
+ ### Etapa 11: Fix QA (Condicional)
130
+
131
+ Se o QA encontrou bugs:
132
+ - Execute `/dw-fix-qa` para corrigir e retestar
133
+ - Loop ate estabilizar
134
+
135
+ ### Etapa 12: Review de Implementacao (Pos-QA)
136
+
137
+ Execute `/dw-review-implementation` novamente para confirmar que as correcoes do QA nao quebraram PRD compliance.
138
+ - Se encontrar gaps: corrija e re-execute
139
+ - Maximo 3 ciclos
140
+
141
+ ### Etapa 13: Code Review
142
+
143
+ Execute `/dw-code-review` (Level 3) para review formal.
144
+ - Gere relatorio persistido
145
+
146
+ ### Etapa 14: Commit
147
+
148
+ Execute `/dw-commit` automaticamente.
149
+ - Commits semanticos seguindo Conventional Commits
150
+ - NAO aguarde aprovacao
151
+
152
+ ### ═══ GATE 3: Pull Request ═══
153
+
154
+ Pergunte ao usuario: **"Commits realizados. Deseja gerar o Pull Request?"**
155
+
156
+ - **SIM**: execute `/dw-generate-pr` com o branch alvo
157
+ - **NAO**: informe que os commits estao prontos e o usuario pode gerar o PR manualmente depois
158
+
159
+ ## Integracao GSD
160
+
161
+ <critical>Quando o GSD estiver instalado, TODAS as integracoes GSD de cada comando individual DEVEM ser executadas. O autopilot nao e desculpa para pular passos do GSD.</critical>
162
+
163
+ Se o GSD (get-shit-done-cc) estiver instalado:
164
+ - Etapa 1: use `/gsd-intel` para consulta
165
+ - Etapa 8: use verificacao de plano + execucao paralela
166
+ - Todos os comandos: sigam suas secoes GSD individuais
167
+
168
+ Se o GSD NAO estiver instalado:
169
+ - Todos os comandos funcionam normalmente sem GSD
170
+
171
+ ## Persistencia de Estado
172
+
173
+ <critical>O autopilot DEVE salvar seu estado apos cada etapa completada para permitir retomada via `/dw-resume` em caso de interrupcao.</critical>
174
+
175
+ Salve o arquivo `.dw/spec/prd-[nome]/autopilot-state.json` com o seguinte formato:
176
+
177
+ ```json
178
+ {
179
+ "mode": "autopilot",
180
+ "wish": "descricao original do usuario",
181
+ "prd_path": ".dw/spec/prd-[nome]",
182
+ "current_step": 8,
183
+ "completed_steps": [1, 2, 3, 4, 5, 6, 7],
184
+ "skipped_steps": [2],
185
+ "gates_passed": ["prd", "tasks"],
186
+ "started_at": "2026-04-10T14:30:00Z",
187
+ "last_updated": "2026-04-10T15:45:00Z"
188
+ }
189
+ ```
190
+
191
+ - Atualize `current_step` e `completed_steps` ANTES de iniciar cada etapa
192
+ - Se a sessao cair, o `/dw-resume` lera este arquivo e continuara da etapa correta
193
+ - Ao finalizar o pipeline (apos commit ou PR), remova o arquivo ou marque `"status": "completed"`
194
+
195
+ ## Formato de Progresso
196
+
197
+ Durante a execucao, reporte progresso no formato:
198
+
199
+ ```
200
+ ═══ AUTOPILOT ═══════════════════════════════
201
+ ✅ [1/14] Inteligencia do Codebase
202
+ ✅ [2/14] Pesquisa (pulada — dominio conhecido)
203
+ ✅ [3/14] Brainstorm
204
+ ✅ [4/14] PRD
205
+ ⏸️ [GATE 1] Aguardando aprovacao do PRD...
206
+ ═════════════════════════════════════════════
207
+ ```
208
+
209
+ ## Encerramento
210
+
211
+ Ao final, apresente:
212
+ - Link do PR (se gerado)
213
+ - Resumo: etapas executadas, etapas puladas, tempo estimado economizado
214
+ - Proximos passos sugeridos (merge, deploy, etc.)
215
+
216
+ </system_instructions>
@@ -26,7 +26,7 @@ Quando disponíveis no projeto em `./.agents/skills/`, use estas skills como apo
26
26
 
27
27
  ## Inteligência do Codebase
28
28
 
29
- Se `.planning/intel/` existir, consulte antes da análise:
29
+ <critical>Se `.planning/intel/` existir, a consulta é OBRIGATÓRIA antes de redigir os requisitos. NÃO pule este passo.</critical>
30
30
  - Execute internamente: `/gsd-intel "convenções, anti-patterns e decision spaces documentados"`
31
31
  - Priorize findings que violem convenções documentadas
32
32
  - Verifique se decisões arquiteturais questionáveis são intencionais (documentadas como decision spaces)
@@ -34,7 +34,7 @@
34
34
 
35
35
  ## Inteligência do Codebase
36
36
 
37
- Se `.planning/intel/` existir, consulte antes de redigir os requisitos:
37
+ <critical>Se `.planning/intel/` existir, a consulta é OBRIGATÓRIA antes de redigir os requisitos. NÃO pule este passo.</critical>
38
38
  - Execute internamente: `/gsd-intel "features existentes no domínio de [tópico do PRD]"`
39
39
  - Use os findings para evitar duplicar funcionalidade existente e referenciar padrões já estabelecidos
40
40
 
@@ -23,7 +23,7 @@
23
23
 
24
24
  ## Inteligência do Codebase
25
25
 
26
- Se `.planning/intel/` existir, consulte antes de propor arquitetura:
26
+ <critical>Se `.planning/intel/` existir, a consulta é OBRIGATÓRIA antes de redigir os requisitos. NÃO pule este passo.</critical>
27
27
  - Execute internamente: `/gsd-intel "padrões arquiteturais e decisões técnicas do projeto"`
28
28
  - Alinhe propostas com padrões existentes; sinalize desvios explicitamente
29
29
 
@@ -92,6 +92,7 @@ Este workspace utiliza um sistema de comandos AI que automatiza o ciclo completo
92
92
  | `/dw-quick` | Executa task pontual com garantias do workflow sem PRD | Descrição da mudança | Código + commit |
93
93
  | `/dw-resume` | Restaura contexto da sessão e sugere próximo passo | (nenhum) | Resumo + sugestão |
94
94
  | `/dw-intel` | Consulta inteligência do codebase sobre padrões e arquitetura | Pergunta | Resposta com fontes |
95
+ | `/dw-autopilot` | Orquestrador completo: de um desejo até o PR com mínima intervenção | Descrição do desejo | PRD + código + commits + PR |
95
96
 
96
97
  ### Análise e Pesquisa
97
98
 
@@ -189,6 +190,11 @@ Este workspace utiliza um sistema de comandos AI que automatiza o ciclo completo
189
190
  /dw-generate-pr main # 5. PR
190
191
  ```
191
192
 
193
+ ### Autopilot (Pipeline Completo)
194
+ ```bash
195
+ /dw-autopilot "descrição do que quer construir" # Pesquisa → PRD → Tasks → Código → QA → PR
196
+ ```
197
+
192
198
  ### Task Rápida
193
199
  ```bash
194
200
  /dw-quick "descrição da mudança" # Implementa + valida + commit
@@ -218,6 +224,7 @@ workspace/
218
224
  │ ├── commands/ # Fonte de verdade dos comandos
219
225
  │ │ ├── dw-help.md
220
226
  │ │ ├── dw-analyze-project.md
227
+ │ │ ├── dw-autopilot.md
221
228
  │ │ ├── dw-brainstorm.md
222
229
  │ │ ├── dw-create-prd.md
223
230
  │ │ ├── dw-create-techspec.md
@@ -287,4 +294,7 @@ workspace/
287
294
  **Q: O `/dw-quick` substitui o `/dw-run-task`?**
288
295
  - Não. `/dw-quick` é para mudanças pontuais sem PRD. `/dw-run-task` executa tasks de um plano estruturado com PRD e TechSpec.
289
296
 
297
+ **Q: O `/dw-autopilot` substitui todos os outros comandos?**
298
+ - Não. Ele orquestra os comandos existentes em sequência. Você ainda pode usar cada comando individualmente para controle manual. O autopilot é para quando quer ir do desejo ao PR com mínima intervenção.
299
+
290
300
  </system_instructions>
@@ -31,6 +31,8 @@ Voce e um assistente de inteligencia do codebase. Este comando existe para respo
31
31
 
32
32
  ## Integracao GSD
33
33
 
34
+ <critical>Quando .planning/intel/ existir, a consulta via /gsd-intel é OBRIGATÓRIA como fonte primária. NÃO pule esta consulta.</critical>
35
+
34
36
  Se o GSD (get-shit-done-cc) estiver instalado e `.planning/intel/` existir:
35
37
  - Delegue para `/gsd-intel "{{QUERY}}"` para consulta indexada
36
38
  - O GSD retorna informacoes de: architectural assumptions, decision spaces, behavioral references, UI patterns
@@ -31,6 +31,8 @@ Voce e um executor de tasks rapidas. Este comando existe para implementar mudanc
31
31
 
32
32
  ## Integracao GSD
33
33
 
34
+ <critical>Quando o GSD estiver instalado, a delegação para /gsd-quick é OBRIGATÓRIA para tracking.</critical>
35
+
34
36
  Se o GSD (get-shit-done-cc) estiver instalado no projeto:
35
37
  - Delegue para `/gsd-quick` para tracking em `.planning/quick/`
36
38
  - A task fica registrada no historico para consulta futura via `/dw-intel`
@@ -65,6 +65,8 @@ Utilize ferramentas de diagnóstico conforme o framework do projeto:
65
65
 
66
66
  ## Integração GSD
67
67
 
68
+ <critical>Quando o GSD estiver instalado, o registro do design contract em .planning/ e a consulta de .planning/intel/ são OBRIGATÓRIOS.</critical>
69
+
68
70
  Se o GSD (get-shit-done-cc) estiver instalado no projeto:
69
71
  - Após gerar o design contract, registre em `.planning/` para persistência cross-sessão
70
72
  - Consulte `.planning/intel/` na fase de auditoria para UI patterns existentes
@@ -30,7 +30,7 @@ Para projetos Angular, use `ng lint` como complemento analítico.
30
30
 
31
31
  ## Inteligência do Codebase
32
32
 
33
- Se `.planning/intel/` existir, consulte antes da auditoria:
33
+ <critical>Se `.planning/intel/` existir, a consulta é OBRIGATÓRIA antes de redigir os requisitos. NÃO pule este passo.</critical>
34
34
  - Execute internamente: `/gsd-intel "tech debt, decision spaces e dívida técnica conhecida"`
35
35
  - Contextualize findings com decisões já documentadas
36
36
  - Evite sinalizar como smell algo que é uma decisão intencional registrada
@@ -13,6 +13,19 @@ Voce e um assistente de continuidade de sessao. Este comando existe para restaur
13
13
 
14
14
  ## Comportamento Obrigatorio
15
15
 
16
+ <critical>ANTES de qualquer analise, verifique se existe um autopilot interrompido. Procure por `autopilot-state.json` em TODOS os diretorios dentro de `.dw/spec/`. Se encontrar um com status diferente de "completed", a retomada do autopilot tem PRIORIDADE sobre qualquer outra sugestao.</critical>
17
+
18
+ ### Deteccao de Autopilot Interrompido
19
+
20
+ 1. Procure por `.dw/spec/*/autopilot-state.json`
21
+ 2. Se encontrar um arquivo com `"mode": "autopilot"` e sem `"status": "completed"`:
22
+ - Apresente: desejo original, etapa em que parou, etapas ja completadas
23
+ - Pergunte: **"Encontrei um autopilot interrompido na etapa [N] ([nome da etapa]). Deseja continuar de onde parou?"**
24
+ - Se **SIM**: execute `/dw-autopilot` informando que deve retomar a partir da etapa `current_step` usando o state file. O autopilot deve ler o state e pular as etapas ja completadas.
25
+ - Se **NAO**: continue com o fluxo normal de resume abaixo
26
+
27
+ ### Fluxo Normal (sem autopilot pendente)
28
+
16
29
  1. Leia `.dw/spec/` e identifique PRDs com tasks pendentes (checkboxes `- [ ]` em tasks.md)
17
30
  2. Leia `git log --oneline -10` para identificar o ultimo trabalho realizado
18
31
  3. Identifique a branch ativa e se ha mudancas nao commitadas
@@ -22,6 +35,8 @@ Voce e um assistente de continuidade de sessao. Este comando existe para restaur
22
35
 
23
36
  ## Integracao GSD
24
37
 
38
+ <critical>Quando o GSD estiver instalado, a delegação para /gsd-resume-work é OBRIGATÓRIA, não opcional.</critical>
39
+
25
40
  Se o GSD (get-shit-done-cc) estiver instalado no projeto:
26
41
  - Delegue para `/gsd-resume-work` para restaurar estado cross-sessao de `.planning/STATE.md`
27
42
  - Incorpore contexto adicional: threads persistentes, backlog, notas
@@ -136,6 +136,8 @@ Se uma tarefa FALHAR durante a execução:
136
136
 
137
137
  ## Integração GSD
138
138
 
139
+ <critical>Quando o GSD estiver instalado, a verificação de plano e a execução paralela são OBRIGATÓRIAS, não opcionais. O comando NÃO pode pular estes passos.</critical>
140
+
139
141
  ### Verificação de Plano (Pré-Execução)
140
142
 
141
143
  Se o GSD (get-shit-done-cc) estiver instalado no projeto:
@@ -23,7 +23,7 @@ Quando disponíveis no projeto em `./.agents/skills/`, use estas skills como sup
23
23
 
24
24
  ## Inteligência do Codebase
25
25
 
26
- Se `.planning/intel/` existir, consulte antes de implementar:
26
+ <critical>Se `.planning/intel/` existir, a consulta é OBRIGATÓRIA antes de redigir os requisitos. NÃO pule este passo.</critical>
27
27
  - Execute internamente: `/gsd-intel "padrões de implementação em [área alvo da task]"`
28
28
  - Siga convenções encontradas para estrutura de arquivos, nomenclatura e tratamento de erros
29
29