jimiryquai/pi-agent/work
Claude Code and agent skill by jimiryquai/pi-agent
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Execute work plans efficiently while maintaining quality and finishing features
Install
npx vskill@latest install jimiryquai/pi-agent/workSKILL.md
Work Plan Execution Command
Execute a work plan efficiently while maintaining quality and finishing features.
Introduction
This command takes a work document (plan, specification, or todo file) and executes it systematically. The focus is on shipping complete features by understanding requirements quickly, following existing patterns, and maintaining quality throughout.
Input Document
<input_document> #$ARGUMENTS </input_document>
Execution Workflow
Phase 1: Orchestration and Tasking
- Assign Persona: The tdm (Technical Delivery Manager) expert handles this phase.
- Setup Environment:
- Branching: Check/Create the feature branch.
- Worktrees: Use the
git-worktreeskill to create isolated environments for each parallel expert if needed. - Parallel Panes: Use the
spawn_teamtool to open separate Zellij panes for the required engineers, pointing each to their respective worktreecwdif applicable.
- Create Todo List:
- Break the plan into units.
- Assign data and API units to the backend-engineer.
- Assign UI and design units to the frontend-engineer.
- Assign verification and integration testing to the tester.
Phase 2: Execute in Parallel
- Backend & Frontend Collaboration:
- The backend-engineer implements core logic and APIs.
- The frontend-engineer builds the UI following project design standards.
- Both work autonomously in their own Zellij panes.
- High-Fidelity Testing:
- The tester writes integration tests (Real > Fake > Mock).
- The tester verifies both Backend logic and Frontend visual/UX integrity.
Phase 3: Finish and Ship
- Final Quality Check:
- Full test suite run.
- Linting check.
- Verification against requirements.
- Ship it:
- Squash/Commit with conventional messages.
- Create PR with visual evidence (screenshots for UI).
- Cleanup: Remove temporary worktrees if used.
Phase 4: Next Steps
- Document Learning: Run
/compoundto capture the solution for future reference.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/work/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jimiryquai/pi-agent/work)