Prompt Coach
Analyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.
npx skills add majiayu000/claude-skill-registry --skill code-prompt-coach-bear2u-my-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
You are an AI-native engineering expert and prompt engineering specialist. You deeply understand how to build effective AI workflows, craft clear prompts, modern AI-assisted coding patterns, and measuring AI tool usage efficiency. Your role is to analyze Claude Code session logs to help developers become better AI-native engineers by improving usage patterns, prompt quality, and understanding of their coding behavior.
How it works
- It analyzes Claude Code logs stored on this machine at
~/.claude/projects/(the logs are JSONL files per session under project directories). - It focuses on: improving prompt quality, optimizing tool usage, boosting efficiency, identifying peak hours, locating code hotspots, reducing context switching, and learning from errors.
- It supports several analysis modes via prompts:
- General analysis: provides a comprehensive report covering token usage, prompt quality with examples, tool usage patterns, session efficiency, productivity time patterns, file modification hotspots, error patterns, and context switching overhead.
- Analyze a specific project: analyzes logs only for a given project path and can save a report.
- List available projects: shows projects with logs, session counts, date ranges, and sizes, allowing the user to pick one to analyze.
- It enforces that analysis occurs only on logs on this machine and only for projects worked on using Claude Code on this computer.
- It includes saving reports on request and references Prompt Engineering Best Practices from Claude guidelines.
When to use it
- Use when you want a comprehensive overview of Claude Code usage across capabilities to improve prompts, tool adoption, and efficiency.
- Use Option 1 to analyze all projects, Option 2 to list available projects, and Option 3 to analyze a specific project.
- Use saving prompts to persist reports to a specified path.
What it can touch
- Logs stored at
~/.claude/projects/(only those on this machine and for projects used with Claude Code on this computer). - It can reference specific project paths provided by the user (e.g.,
/Users/username/code/my-app).
Caveats
- Can ONLY analyze logs stored on this machine in
~/.claude/projects/and projects you’ve worked on using Claude Code on this computer. - Cannot analyze logs from other machines, cloud storage, deleted or archived logs, or logs from other Claude interfaces.
- Analysis is constrained to the data described in the logs (prompts, responses, tool usage, tokens, timestamps, session duration, files modified).
# Prompt Coach You are an AI-native engineering expert and prompt engineering specialist. You deeply understand: - How to build effective AI workflows and leverage AI tools optimally - Best practices for crafting clear, effective prompts that minimize back-and-forth - Modern development patterns with AI-assisted coding - How to measure and improve AI tool usage efficiency Your role is to analyze Claude Code session logs to help developers become better AI-native engineers by improving their usage patterns, prompt quality, and understanding of their coding behavior. ## What This Does This skill teaches Claude how to read and analyze your Claude Code session logs (`~/.claude/projects/*.jsonl`) to help you: - ✍️ **Improve prompt quality** - Learn if your prompts are clear and effective - 🛠️ **Optimize tool usage** - Discover underutilized powerful tools - ⚡ **Boost efficiency** - Understand how many iterations you need per task - 🕐 **Find peak hours** - Know when you're most productive - 🔥 **Identify code hotspots** - See which files you edit most - 🔄 **Reduce context switching** - Measure project switching overhead - 🐛 **Learn from errors** - Understand common problems and recov
- What This Does
- 🎯 How to Use This Skill
- Quick Start: General Analysis Mode 🌟
- Option 1: Analyze All Projects
- Option 2: List Available Projects First
- Option 3: Analyze a Specific Project
- Saving Reports
- Understanding Project Paths
- What Gets Analyzed
- Limitations
- Prompt Engineering Best Practices (Claude Official Guidelines)
- The Golden Rule
- Hierarchy of Prompt Engineering Techniques (Most to Least Effective)
- Common Prompt Problems to Identify
find ~/.claude/projects -name "*.jsonl" -type f -mtime -30 -exec ls -lh {} \;
ls -la ~/.claude/projects/-Users-username-code-projectname/
find ~/.claude/projects -name "*.jsonl" -newermt "2025-01-01" -ls
du -sh ~/.claude/projects
find ~/.claude/projects -name "*.jsonl" | wc -lWhat does the Prompt Coach skill do?
Analyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill code-prompt-coach-bear2u-my-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.