devkit.prompt-optimize
CommandProvides expert prompt optimization using advanced techniques (CoT, few-shot, constitutional AI) for LLM performance enhancement.…
Start a new coding session - reads progress, chooses next feature, runs basic tests
> /plugin marketplace add giuseppe-trisciuoglio/developer-kit> /plugin install developer-kit@developer-kit
description: Start a new coding session - reads progress, chooses next feature, runs basic tests argument-hint: "[optional-context]" allowed-tools: Read, Write, Edit, Bash, Grep, Glob
You are a **Coding Agent** starting a new session on an ongoing project. Your first priority is to understand the current state before making any changes.
Execute these steps IN ORDER:
pwd
Confirm you're in the correct project directory.
Read the progress file to understand what happened in previous sessions:
cat .lra/progress.txt
Pay attention to:
Review recent commits to understand code changes:
git log --oneline -15 git status
If there are uncommitted changes, understand what they are before proceeding.
Load the feature list and identify what needs to be done:
cat .lra/feature-list.json
Identify:
If an init script exists, consider running it:
if [ -f .lra/init.sh ]; then
source .lra/init.sh
fiRun a quick test to ensure the app is in a working state:
**If the app is broken**: Fix existing bugs BEFORE starting new features.
After completing the startup protocol, provide:
1. **Project Status**: Overall progress (X of Y features complete) 2. **Last Session**: What was accomplished 3. **Current State**: Is the app working? Any issues? 4. **Selected Feature**: The feature you will work on this session 5. **Approach**: Brief plan for implementing the feature
Once you've completed the startup protocol and planning, you may begin implementation. Remember:
1. Work incrementally with small, tested changes 2. Commit frequently with descriptive messages 3. If you encounter blockers, document them 4. Before ending the session, use `/developer-kit:devkit.lra.checkpoint` to save your progress
**Agent Selection**: To execute this LRA task, use the following approach:
Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python, PHP, AWS, and AI.
Provides expert prompt optimization using advanced techniques (CoT, few-shot, constitutional AI) for LLM performance enhancement.…
Provides guided feature development capability with codebase understanding and architecture focus. Use when implementing a new…
Provides guided bug fixing and debugging capability with systematic root cause analysis. Use when encountering bugs, errors, or…
Creates a GitHub pull request with branch creation, commits, and detailed description. Use when you need to submit changes for…
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a…
Provides guided code refactoring capability with deep codebase understanding, compatibility options, and comprehensive…
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.