binayshaw7777/Leaflekt-Maps / .agents/skills/orchestrator
orchestrator
VerifiedALWAYS invoke this skill when delegating, planning, or managing any development task. Do not implement features, fix bugs, or start coding directly without first loading and following this orchestrator pipeline. Use when implementing features, fixing bugs, managing tasks, reviewing code, orchestrating work, or any task that needs structured delegation. Trigger on words like orchestrate, manage, implement, build, develop, organize, delegate, team lead, pipeline, or project manage.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.8 KB |
| references/prompt-templates.md | markdown | 2.7 KB |
| references/tmux-worktree.md | markdown | 1.7 KB |
| scripts/load-orchestrator.sh | script | 1.6 KB |
references/prompt-templates.md
View on GitHub# Prompt Templates
Fill in `<placeholders>`. Send completed prompt to the corresponding pane.
---
## Worker Prompt (Pane 0)
```
Follow the spec-kit workflow to implement this task:
1. Run /speckit.specify with the task description below
2. Run /speckit.plan with the constraints below
3. Run /speckit.tasks to break down the work
4. Run /speckit.implement to execute
## Task
<what to build β clear, one paragraph>
## Acceptance Criteria
- <testable criterion 1>
- <testable criterion 2>
## Constraints
- Follow existing architecture: <pattern>
- DI: <framework>
- Target directory: <path>
- Clean code: small functions, meaningful names, SRP
- Testability: inject dependencies, no static state
- UI tasks: use framelink MCP for implementation reference
## Context
- Worktree: ../worktrees/<task-slug>
- Branch: feature/<task-slug>
- Key files: <2-5 files to read first>
Use multiple subagents and parallel execution wherever possible to move fast.
Stage only. Do NOT commit.
```
---
## Tester Prompt (Pane 1)
```
Use /phone-driver to test this implementation:
## What Was Built
<1-2 sentence summary>
## Scenarios
1. Happy path: <main flow>
2. Edge case: <boundary>
3. Error state: <failure handling>
4. UI/UX: <visual check>
## Steps
- Build: ./gradlew assembleDebug
- Use /phone-driver to navigate to <screen>
- Execute each scenario, capture screenshots
## Output β TEST_REPORT.md
| # | Scenario | Status | Notes |
|---|----------|--------|-------|
For failures: steps to reproduce, expected vs actual, screenshots.
Save to: ../worktrees/<task-slug>/TEST_REPORT.md
Use subagents to run independent test scenarios in parallel where possible.
```
---
## Reviewer Prompt (Pane 2)
```
Review changes using /clean-code principles:
## Scope
- Branch: feature/<task-slug>
- Files: run `git diff --name-only`
- Feature: <one line summary>
## Check
- Names reveal intent, functions do one thing (5-20 lines)
- No duplication, no magic numbers, proper error handling
- Architecture conventions followed, deps injected
- No main thread blocking, no memory leaks, lifecycle-safe
- Scales to 10x data, forward-compatible contracts
## Output β REVIEW_REPORT.md
Rating: π’ Ship It / π‘ Minor Changes / π΄ Rework
Issues table: severity, file, issue, suggestion
Save to: ../worktrees/<task-slug>/REVIEW_REPORT.md
Use subagents to review different files in parallel where possible.
```
---
## Fix Prompt (Worker β Failures)
```
Use /speckit.plan and /speckit.implement to fix these issues:
## Issues
1. <from TEST_REPORT.md or REVIEW_REPORT.md>
## Requirements
- Fix each issue
- No regressions on passing tests
- Use subagents to fix independent issues in parallel
- Stage only. Do NOT commit.
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path β even casually (like "the xlsx in my downloads") β and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |