These markdown files live inside a Claude Project. They give Claude persistent context about the job, people, infrastructure, and repeatable workflows. Claude reads them at the start of every conversation — like onboarding docs for a hire that never forgets.
| File | Purpose |
|---|---|
| Reference — loaded first, every session | |
| ref-context.md | Who I am, career trajectory, daily cadence, what to watch for |
| ref-project-instructions.md | API endpoints, credentials, key people, facility context, commands |
| ref-debrief-protocol.md | Post-meeting extraction format and strategic analysis structure |
| Skills — slash commands Claude executes like scripts | |
| skill-morning.md | /morning — pull stats, surface overdue, check drift, flag cold relationships |
| skill-debrief.md | /debrief — extract tasks and intel from transcript, review gate, push to database |
| skill-close.md | /close — capture decisions, update state, prevent context loss |
| skill-weekly.md | /weekly — full audit: contradictions, stale data, duplicates, drift |
| skill-1on1-prep.md | /1on1-prep — 1-on-1 meeting prep with open items and talking points |
| skill-status.md | /status — quick pulse on tasks, blocked items, priorities |
| skill-tribal.md | /tribal — quick-capture undocumented knowledge to the database |
| skill-floorform.md | /floorform — opens a mobile data collection form for floor walkthroughs |
| skill-audit.md | /audit — semantic audit and drift scan across the whole system |
| Knowledge base — what doesn't exist in any official system | |
| kb-tribal-knowledge.md | Legacy snapshot — live data now in D1 database via API |
| kb-people-intel.md | Legacy snapshot — relationship dynamics now in D1 via API |
| kb-lessons.md | Dead ends and mistakes only. Force-read every morning to prevent repeats. |
| Infrastructure — the code that connects everything | |
| infra-worker-api.mjs | Live Cloudflare Worker source — the API Claude reads and writes to |
| infra-deploy-notes.md | Deploy patterns, gotchas, credential locations |
| Tools — interactive artifacts | |
| tool-floor-form.jsx | Mobile React form for machine walkthrough data collection |
| tool-floor-form.html | Same form as standalone HTML for phone browser |
| tool-1on1-coach.jsx | Interactive 1-on-1 meeting prep coach |
| Meta | |
| 00-index.md | This file list. Naming convention, rules, what goes where. |
The markdown files are static context. These two layers hold dynamic state — tasks, people, knowledge — that changes every day.
Tasks, people directory, tribal knowledge, relationship intel. Claude reads and writes via API calls during conversations. A cron job emails a weekly digest every Friday.
Visual command center — kanban board, people directory, task filters. Opens in a browser when you need the big picture without starting a Claude chat.
Nothing hits the database without approval. Claude extracts, you review, then it pushes. This single rule prevents most of the problems people run into with AI assistants.
Each command is a markdown file with step-by-step instructions Claude follows exactly. You type the command, Claude runs the playbook.
/morningDaily, before first meetingPull task stats, surface overdue and blocked items, check for data drift, flag cold relationships/debriefAfter every meetingPull transcript, extract tasks and people intel, present for review, push approved items to database/closeEnd of each sessionCapture decisions, update state, ensure nothing is lost before the context window resets/weeklyFridayFull semantic audit — contradictions, stale data, orphaned references, relationship gaps, duplicatesClaude's in-app artifacts don't survive closing the app. It creates a new instance every time. Anything that needs to persist goes to an external host or gets exported before the session ends.
Claude will assign you tasks that were merely mentioned in conversation, not directed at you. Build a review gate — nothing hits the database without explicit approval. Default ambiguous items to FYI.
Otter, Whisper, and other transcription tools frequently get names wrong. Always search for name variants before creating a new person record or you'll create duplicates.
Session logs hit noise threshold within two months. Build monthly archiving into your workflow from day one.
Your lessons file should capture dead ends and mistakes. The rest of the system tracks wins. The lessons file prevents repeat mistakes and gets force-read every morning.
Every debrief adds knowledge, every correction trains better behavior, every weekly audit cleans accumulated drift.
/morning — pull stats, surface overdue, check drift, flag cold relationships/debrief — extract tasks and intel from transcript, review, push to database/close — capture decisions, update state, prevent context loss/weekly — full audit: contradictions, stale data, duplicates, relationship gapsCreate a Claude Project. Add a context file (who you are, what you do, your daily rhythm), an index file, and one skill file for your most common workflow. This alone — before any infrastructure — makes Claude dramatically more useful.
Ask Claude to write a Cloudflare Worker with a D1 database. Start with tasks and people tables. Claude can write the Worker, the SQL schema, and walk you through the Cloudflare dashboard setup.
Add your Worker URL and auth token to your project instructions file. Now Claude can read from and write to your database during conversations. Start with a /morning skill that pulls your open tasks.
Ask Claude to build a single-file HTML dashboard that pulls from your API. Deploy to Netlify. This gives you a visual view of everything Claude manages for you.
Connect a transcription tool (Otter.ai, Granola, or manual paste). Build a /debrief skill that extracts tasks and knowledge from meetings — with a review gate. Every meeting now feeds the system.