caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Analyze your Claude Code usage from local transcripts: an HTML report on cost, caching, context, sessions, tools, subagents and hooks with an efficiency score and a grade per area, Claude-written insights with what each change would have saved, optimizations you can apply one by one, a short video of your highlights, the whole report as one file to send, and a company report combining many people's files.
Plugin usage-optimizer from marketplace claude-usage-optimizer in yuval-sosman/claude-usage-optimizer. Commands read from the repo's manifest — 22 days ago.
brainstormThink through your Claude Code usage with Claude — explore the report's numbers, challenge or extend the insights, test what-if ideas on the extracted data, and turn what you agree on into updated insights or optimizations.
clearRemove this plugin's report files (the report and its data, the insights and optimizations, your score history, videos, share files, reports others sent you, the company report) to start from scratch. Your Claude Code setup and any applied optimizations stay as they are.
companyCombine many people's share files (from /usage-optimizer:share) into one company report - totals and trends, how people compare per 30 days, and which savings levers are worth the most across everyone - and summarise it.
openOpen a usage report you already have in your browser (yours, the company report, or one someone sent you), without counting anything again or writing new insights.
optimizeTurn the usage report's insights into concrete Claude Code optimizations (settings, hooks, status line, CLAUDE.md, agent and habit changes), each with its theoretical saving (all time and per 30 days), a one-command apply (preview, backup, undo) where possible and exact manual steps otherwise, shown
reportBuild and open the Claude Code usage report from the local transcripts (cost, caching, context, sessions, tools, hooks), with Claude-written insights on what each change would have saved and the optimizations to apply. Use when the user asks to analyze, audit or explain their Claude Code usage, cost
sharePack your whole Claude Code usage report (every number, chart, table and miss trace, the insights, the optimizations, your setup and every CSV row) into one JSON file to send to someone who collects and compares usage, or open a share file someone sent you. Run after /usage-optimizer:report.
videoMake a 30–60 second video of your own Claude Code usage highlights (cost, a costly cache miss, insights, optimizations and what they would save) to share, as an MP4 and a self-playing HTML page in the report's style. Run after /usage-optimizer:report.
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.