plan-parallel-dev
Skill for creating parallel development plans with multiple developers. Leverages git worktree for branch strategy, task dependency analysis, critical path calculation, developer role assignment, and timeline creation. Use for requests like "create a parallel development plan", "I want to develop with multiple people simultaneously", "divide work with worktree", or "maximize development parallelization". Also supports on-demand parallel tasks for quick fixes with requests like "fix XX in parallel", "do YY with worktree", or "add parallel task".
What this skill does
# Parallel Development Planning
Create implementation plans to maximize parallelization of feature development with multiple developers.
Also supports on-demand parallel tasks (bug fixes, feature additions) for completed projects.
## Usage Modes
This skill has two modes:
### Mode A: Initial Parallel Development (Planning Mode)
Used immediately after project initialization (right after `uv init`, `create-react-app`, etc.) when developing multiple features in parallel.
**Trigger Phrases**:
- "Create a parallel development plan"
- "I want to develop with multiple people simultaneously"
- "Divide work with worktree"
- "Maximize development parallelization"
**Workflow**: 9-step workflow (described below) to create a plan and start multiple tasks simultaneously.
### Mode B: Maintenance Parallel Development (Quick Task Mode)
Used for bug fixes and feature additions to projects with existing implementations. Start work immediately without a plan document.
**Trigger Phrases**:
- "Fix XX in parallel"
- "Handle XX in parallel"
- "Do YY with worktree"
- "Add parallel task: XX"
- "Do this with worktree: XX"
**Workflow**: See "Quick Task Workflow" section for details.
### Mode Selection Guide
| Situation | Recommended Mode |
| ----------------------------------------------- | ------------------------------------------ |
| Right after project initialization, parallel features | A |
| Single bug fix to existing project | B (single task) |
| Medium-scale feature addition to existing project | B (multiple tasks + merge coordinator) |
---
## Workflow (Mode A: Initial Parallel Development)
```
1. Understand Requirements
└─→ Collect list of features to develop
└─→ Confirm tech stack (BE/FE/Infrastructure, etc.)
2. Task Decomposition
└─→ Split each feature into independent tasks
└─→ Granularity: whichever is smaller
├─→ 0.5-2 days in human time
├─→ Within 20 files changed
└─→ Independently testable feature unit
└─→ ⚠️ UI specs require human approval (see below)
3. Dependency Analysis
└─→ Identify blocking relationships between tasks
└─→ Calculate critical path
4. Determine Parallelism
└─→ Calculate number of Claude instances needed
└─→ Assignment to minimize wait time
5. Branch Strategy
└─→ Design integration branch
└─→ Feature branch naming convention
└─→ Determine merge order
6. Create Timeline
└─→ Gantt-style parallel schedule
7. Create Plan and Instruction Documents
└─→ Communicate plan content to user (present execution order, parallelism, and task content in table format)
└─→ Create files in .parallel-dev/
├─→ PLAN.md (plan document)
├─→ README.md (overall overview and progress management)
├─→ merge-coordinator.md (for merge coordinator)
├─→ tasks/*.md (for each task)
├─→ signals/ (completion notification directory)
└─→ issues/ (issue report directory)
8. Environment Setup
└─→ Create integration branch and push to remote
└─→ Create worktree for each task
└─→ Install dependencies in each worktree
└─→ Copy .env in each worktree
9. Launch merge coordinator Claude in tmux new-window
└─→ Create new window with tmux new-window -n "coordinator" and launch claude
└─→ Pass initial instructions to merge coordinator
```
## Quick Task Workflow (Mode B: Quick Task)
Mode for immediately starting bug fixes or feature additions to existing projects without a plan document.
**Features**:
- Start immediately without plan document
- Support multiple concurrent sessions with session files (`.parallel-dev/quick-session-{timestamp}.md`)
- Merge directly to main
→ **See [references/quick-mode-guide.md](references/quick-mode-guide.md) for details**
---
## Terminology
To avoid confusion, unify the following terms:
| Term | Description | Example |
| ----------------- | ----------------------------------------- | -------------------------------------- |
| **Task Name** | Identical to branch name. Work unit ID | `skill-files-api`, `recommendation-ui` |
| **Person/Role** | Worker identifier. Tech area + number | `BE-1`, `FE-1`, `INFRA-1` |
| **Integration Branch** | Target branch to merge all tasks | `feature/multi-file-skills` |
**Important**: Use **task name (branch name)** for completion reports and state management. Person name alone cannot identify the task when handling multiple tasks.
## Task Decomposition Rules
Task splitting principles:
1. **Single Responsibility**: 1 task = 1 feature/1 component
2. **Appropriate Granularity**: whichever is smaller
- 0.5-2 days in human time
- Within 20 files changed
- Independently testable feature unit
3. **Clear Deliverables**: Each task has concrete deliverables like API/component/file
4. **Testable**: Unit that can be independently tested and reviewed
5. **Minimize Conflicts**: Minimize file edit overlaps, consolidate common file changes (routing, type definitions, etc.) into one task
Branch naming:
```
feature/recommendation-api # Feature name based
feature/notification-api
feature/project-card-enhance
```
Role (person) naming:
```
BE-1, BE-2, ... # Backend
FE-1, FE-2, ... # Frontend
INFRA-1, ... # Infrastructure
```
## Dependency Analysis
Dependency types:
| Dependency Type | Symbol | Description |
| --------------- | ------ | --------------------- |
| Blocking | `→` | Must complete |
| Parallel | `//` | Can proceed independently |
| Waiting for integration | `↓` | Start after merge |
Critical path calculation:
```
Longest path = max(total effort of each path)
Optimal number of people = ceil(total effort / critical path)
```
Create dependency matrix:
```
BE-01 BE-02 FE-01 FE-02
BE-01 - // ↓ //
BE-02 // - // ↓
FE-01 Wait // - //
FE-02 // Wait // -
```
## Developer Role Assignment
Role definition template:
| Role | Assigned Branch | Required Skills |
| ---- | --------------- | ----------------- |
| BE-1 | feature/xxx-api | Python, FastAPI |
| FE-1 | feature/xxx-ui | React, TypeScript |
Principles for minimizing wait time:
1. Assign dependent tasks to the dependency source worker
2. Fill wait time with independent tasks
3. Utilize idle time for review and support
## Branch Strategy with Worktree
Git worktree basics for parallel development:
```
main
└── feature/integration (integration branch)
├── feature/xxx-api → worktree/xxx-api/
├── feature/yyy-api → worktree/yyy-api/
└── feature/xxx-ui → worktree/xxx-ui/
```
→ **See [references/worktree-guide.md](references/worktree-guide.md) for details**
## Agent Instruction Files
For parallel development with Claude, place instruction documents for each Claude in `.parallel-dev/`.
**Directory Structure**:
| Directory/File | Purpose |
| ------------------------------------ | ------------------------ |
| `.parallel-dev/` | Parallel dev management (git-managed) |
| `.parallel-dev/PLAN.md` | Plan document |
| `.parallel-dev/merge-coordinator.md` | For merge coordinator |
| `.parallel-dev/tasks/*.md` | Instruction docs per task |
| `.parallel-dev-signals/` | Completion notifications (.gitignore) |
| `.parallel-dev-issues/` | Issue reports (.gitignore) |
**Templates**:
- [references/templates/parallel-dev-readme.md](references/templates/parallel-dev-readme.md)
- [references/templates/merge-coordinator.md](references/templates/merge-coordinator.md)
- [references/templates/task-instruction.md](references/templates/task-instruction.md)
## Task Completion Flow
**Role Division**Related in Productivity
gitea-workflow
IncludedOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
microsoft-graph-gateway
IncludedRoute Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft Graph for write actions and gap-read scenarios that need exact Graph properties, filters, permissions, or endpoints.
copilotkit
IncludedUse when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
wordly-wisdom
IncludedProvides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
swain-session
IncludedSession management and project status dashboard. Owns the full session lifecycle (start/work/close/resume), focus lane, bookmarks, worktree detection, and tab naming. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, tasks, GitHub issues, and recommendations. Worktree creation is deferred to swain-do task dispatch (SPEC-195). Triggers on: 'session', 'status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'bookmark', 'focus on', 'session info'.
gandi
IncludedComprehensive Gandi domain registrar integration for domain and DNS management. Register and manage domains, create/update/delete DNS records (A, AAAA, CNAME, MX, TXT, SRV, and more), configure email forwarding and aliases, check SSL certificate status, create DNS snapshots for safe rollback, bulk update zone files, and monitor domain expiration. Supports multi-domain management, zone file import/export, and automated DNS backups. Includes both read-only and destructive operations with safety controls.