j-mauro-r/SAT-Dengue-V2 / .agents/skills/deepworkplan
deepworkplan
VerifiedDeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, upgrade, and repo-onboarding sub-skills based on intent. Use when the developer wants to plan, execute, manage, or verify structured multi-task work, or make a repository AI-agent-ready.
examples/TEAM_AGENTS_TASK_TEMPLATE.md
View on GitHub# Team Agents Task Template
> **Usage:** Use this template when creating task files for DWP plans that include team agents parallel execution.
> This extends the standard task template with an optional "Team Agents Metadata" section.
>
> Non-Claude agents ignore the Team Agents Metadata section — it doesn't affect sequential execution.
---
## Standard Task Template (Required — All Agents)
````markdown
# Task {N}: {Task Title}
## 1. Context
[Standard context: what part of codebase, relevant files, conventions]
## 2. Read Before Starting (optional)
- Task {X} Completion & Log: {what to extract}
## 3. Goal
[Concise description of what this task must achieve]
## 4. Touched Surface
Required for any task that changes behavior (code, configuration, schemas,
templates, fixtures, migrations, generated inputs, agent instructions). Pure
prose or research tasks write `not applicable — <reason>`. Full field list
(planned surface, actual surface, affected consumers, risk class, test
mapping, selected gate): `guide/authoring.md` §5.1.
- **Planned surface:** {paths / modules this task intends to change}
- **Affected consumers:** {what imports/loads/renders the surface}
## 5. Instructions
> **Before starting:** Re-read the plan README section 1 (Goal) to ensure this task's work aligns with the overall objective.
[Detailed, actionable instructions for this single task]
## 6. Acceptance Criteria
[Explicit conditions for task completion]
## 7. Outputs (optional)
- `analysis_results/{FILE_NAME}.md` — {description}
## 8. Validation
```bash
[Validation commands that must pass]
```
## 9. Rollback (optional)
[Instructions if task fails]
## 10. Execution Checklist
- [ ] 1. Read this task file fully
- [ ] 2. [Task-specific steps]
- [ ] N. Update plan README `[x]`
- [ ] N+1. Update PROGRESS.md
- [ ] N+2. Commit changes
- [ ] N+3. Update Log below
## 11. Completion & Log
**Status:** Not started
````
---
## Team Agents Metadata Section (Optional — Claude Code Only)
Add this section **AFTER** all standard sections. It is **completely optional** — only include it when the plan uses team agents for parallel execution.
````markdown
## Team Agents Metadata (Claude Code Only)
- **Parallel Group:** {group_letter}
<!-- Which parallel group this task belongs to (e.g., A, B, C) -->
- **Teammate Role:** {role_name}
<!-- The specialized role assigned to this task's teammate -->
- **Can Run With:** Tasks {X}, {Y}
<!-- Other tasks in the same parallel group (no file conflicts) -->
- **Blocks:** Task {Z}
<!-- Tasks that cannot start until this task completes -->
- **Files Owned:** {directories_or_files}
<!-- Files this task will create or modify — no other parallel task should touch these -->
- **Spawn Prompt:** "{detailed_prompt}"
<!-- The prompt given to the teammate when spawned for this task.
Should include: role context, focus area, key file paths, expected output format -->
````
### Field Descriptions
| Field | Required? | Description |
|-------|-----------|-------------|
| Parallel Group | Yes (if using team agents) | Letter identifier for the parallel group (A, B, C...) |
| Teammate Role | Yes (if using team agents) | Human-readable role name for the teammate |
| Can Run With | Recommended | List of task numbers that can execute simultaneously |
| Blocks | Recommended | List of task numbers that depend on this task's completion |
| Files Owned | Recommended | Explicit file ownership to prevent conflicts |
| Spawn Prompt | Optional | Detailed prompt for the teammate; if omitted, the task file content is used |
### Important Rules
1. **NEVER put required information in this section** — all execution details must be in standard sections
2. **This section is purely optimization metadata** — removing it changes nothing about task execution
3. **File ownership must not overlap** between tasks in the same parallel group
4. **Spawn prompts should reference** the plan's AGENTS.md and relevant documentation
5. **Sequential tasks** (not in any parallel group) should NOT have this section
### Examples
**Research task (parallel):**
```markdown
## Team Agents Metadata (Claude Code Only)
- **Parallel Group:** A
- **Teammate Role:** Market Researcher
- **Can Run With:** Tasks 3, 4
- **Blocks:** Task 5 (synthesis)
- **Files Owned:** analysis_results/market_research.md
- **Spawn Prompt:** "Research the competitive landscape for feature X. Focus on how competitors Y and Z implement this. Document findings in analysis_results/market_research.md with comparison tables."
```
**Code implementation task (parallel):**
```markdown
## Team Agents Metadata (Claude Code Only)
- **Parallel Group:** B
- **Teammate Role:** API Developer
- **Can Run With:** Tasks 7, 8
- **Blocks:** Task 9 (integration tests)
- **Files Owned:** src/api/notifications/, tests/api/notifications/
- **Spawn Prompt:** "Implement notification API endpoints at src/api/notifications/. Follow patterns in src/api/users/ as reference. Run validation with npm run test before marking complete."
```
**Sequential task (no metadata needed):**
```
[No Team Agents Metadata section — this task runs sequentially]
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |