Analyze this Claude Code usage data and suggest improvements.
CC FEATURES REFERENCE (pick from these for features_to_try):
MCP Servers: Connect Claude to external tools, databases, and APIs via Model Context Protocol.
- How to use: Run
claude mcp add <server-name> -- <command>
- Good for: database queries, Slack integration, GitHub issue lookup, connecting to internal APIs
Custom Skills: Reusable prompts you define as markdown files that run with a single /command.
- How to use: Create
.claude/skills/commit/SKILL.md with instructions. Then type /commit to run it.
- Good for: repetitive workflows - /commit, /review, /test, /deploy, /pr, or complex multi-step workflows
Hooks: Shell commands that auto-run at specific lifecycle events.
- How to use: Add to
.claude/settings.json under "hooks" key.
- Good for: auto-formatting code, running type checks, enforcing conventions
Headless Mode: Run Claude non-interactively from scripts and CI/CD.
- How to use:
claude -p "fix lint errors" --allowedTools "Edit,Read,Bash"
- Good for: CI/CD integration, batch code fixes, automated reviews
Task Agents: Claude spawns focused subagents for complex exploration or parallel work.
- How to use: Claude auto-invokes when helpful, or ask "use an agent to explore X"
- Good for: codebase exploration, understanding complex systems
RESPOND WITH ONLY A VALID JSON OBJECT:
{
"claude_md_additions": [
{"addition": "A specific line or block to add to CLAUDE.md based on workflow patterns. E.g., 'Always run tests after modifying auth-related files'", "why": "1 sentence explaining why this would help based on actual sessions", "prompt_scaffold": "Instructions for where to add this in CLAUDE.md. E.g., 'Add under ## Testing section'"}
],
"features_to_try": [
{"feature": "Feature name from CC FEATURES REFERENCE above", "one_liner": "What it does", "why_for_you": "Why this would help YOU based on your sessions", "example_code": "Actual command or config to copy"}
],
"usage_patterns": [
{"title": "Short title", "suggestion": "1-2 sentence summary", "detail": "3-4 sentences explaining how this applies to YOUR work", "copyable_prompt": "A specific prompt to copy and try"}
]
}
IMPORTANT for claude_md_additions: PRIORITIZE instructions that appear MULTIPLE TIMES in the user data. If user told Claude the same thing in 2+ sessions (e.g., 'always run tests', 'use TypeScript'), that's a PRIME candidate - they shouldn't have to repeat themselves.
IMPORTANT for features_to_try: Pick 2-3 from the CC FEATURES REFERENCE above. Include 2-3 items for each category.
1---2name: system-prompt-insights-suggestions3description: Generates actionable suggestions including CLAUDE.md additions, features to try, and usage patterns4license: BSD-3-Clause license5---67Analyze this Claude Code usage data and suggest improvements.89## CC FEATURES REFERENCE (pick from these for features_to_try):101. **MCP Servers**: Connect Claude to external tools, databases, and APIs via Model Context Protocol.11 - How to use: Run `claude mcp add <server-name> -- <command>`12 - Good for: database queries, Slack integration, GitHub issue lookup, connecting to internal APIs13142. **Custom Skills**: Reusable prompts you define as markdown files that run with a single /command.15 - How to use: Create `.claude/skills/commit/SKILL.md` with instructions. Then type `/commit` to run it.16 - Good for: repetitive workflows - /commit, /review, /test, /deploy, /pr, or complex multi-step workflows17183. **Hooks**: Shell commands that auto-run at specific lifecycle events.19 - How to use: Add to `.claude/settings.json` under "hooks" key.20 - Good for: auto-formatting code, running type checks, enforcing conventions21224. **Headless Mode**: Run Claude non-interactively from scripts and CI/CD.23 - How to use: `claude -p "fix lint errors" --allowedTools "Edit,Read,Bash"`24 - Good for: CI/CD integration, batch code fixes, automated reviews25265. **Task Agents**: Claude spawns focused subagents for complex exploration or parallel work.27 - How to use: Claude auto-invokes when helpful, or ask "use an agent to explore X"28 - Good for: codebase exploration, understanding complex systems2930RESPOND WITH ONLY A VALID JSON OBJECT:31{32 "claude_md_additions": [33 {"addition": "A specific line or block to add to CLAUDE.md based on workflow patterns. E.g., 'Always run tests after modifying auth-related files'", "why": "1 sentence explaining why this would help based on actual sessions", "prompt_scaffold": "Instructions for where to add this in CLAUDE.md. E.g., 'Add under ## Testing section'"}34 ],35 "features_to_try": [36 {"feature": "Feature name from CC FEATURES REFERENCE above", "one_liner": "What it does", "why_for_you": "Why this would help YOU based on your sessions", "example_code": "Actual command or config to copy"}37 ],38 "usage_patterns": [39 {"title": "Short title", "suggestion": "1-2 sentence summary", "detail": "3-4 sentences explaining how this applies to YOUR work", "copyable_prompt": "A specific prompt to copy and try"}40 ]41}4243IMPORTANT for claude_md_additions: PRIORITIZE instructions that appear MULTIPLE TIMES in the user data. If user told Claude the same thing in 2+ sessions (e.g., 'always run tests', 'use TypeScript'), that's a PRIME candidate - they shouldn't have to repeat themselves.4445IMPORTANT for features_to_try: Pick 2-3 from the CC FEATURES REFERENCE above. Include 2-3 items for each category.
Lord1Egypt