what-claude-did-for-melisted

Generates a personal impact report showing what someone actually used Claude for over a period, the jobs that work was doing, estimated time saved, and its expert-equivalent dollar value, rendered as a polished single-file HTML report they can share or print to PDF. Harvests the person's own Claude conversation history automatically when available, falls back to a short guided interview, and can also import a usage CSV export. Use this skill whenever someone wants to know what Claude or AI has done for them, build a personal AI impact or ROI report, justify their AI subscription or budget, prepare for a performance review or renewal conversation, or asks "what did Claude do for me," "was my subscription worth it," "how much time has AI saved me," or "build my AI receipt."
kadns/agentic-roi-reports · ★ 0 · AI & Automation · score 67

Install: claude install-skill kadns/agentic-roi-reports

# What Claude Did for Me Turns a period of Claude usage into a personal impact report: what the person worked on, the job each piece of work was doing, estimated time saved, and what that time is worth. Output is a self-contained HTML file they can open, adjust, share, or print to PDF. The person should never need admin access, a Console login, or an export file to get a useful report. Those are optional upgrades, not prerequisites. ## Pick a mode Try these in order. Do not ask the person to choose, just start with harvest and fall back silently if it is unavailable. 1. **Harvest** (best): read the person's own recent Claude conversations to see what they actually worked on. 2. **Interview** (always available): a short guided conversation, no data needed. 3. **Import** (optional): a usage CSV from Claude Console, OpenAI, Azure, or Copilot, for anyone who has one. --- ## Mode 1: Harvest Use `recent_chats` to pull the person's conversations across the reporting window, and `conversation_search` if you need to fill in specific topics. Ask first which period to cover, defaulting to the last 30 days. Paginate with `recent_chats` using the `before` parameter to walk back through the window, up to about 5 calls. If the window is not fully covered, say so plainly rather than presenting a partial picture as complete. If these tools are unavailable or return nothing, do not announce a failure. Just move to interview mode: "Let me ask you a few quick questions instead."