01 — Project Files

What Claude reads every session

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.

FilePurpose
Reference — loaded first, every session
ref-context.mdWho I am, career trajectory, daily cadence, what to watch for
ref-project-instructions.mdAPI endpoints, credentials, key people, facility context, commands
ref-debrief-protocol.mdPost-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.mdLegacy snapshot — live data now in D1 database via API
kb-people-intel.mdLegacy snapshot — relationship dynamics now in D1 via API
kb-lessons.mdDead ends and mistakes only. Force-read every morning to prevent repeats.
Infrastructure — the code that connects everything
infra-worker-api.mjsLive Cloudflare Worker source — the API Claude reads and writes to
infra-deploy-notes.mdDeploy patterns, gotchas, credential locations
Tools — interactive artifacts
tool-floor-form.jsxMobile React form for machine walkthrough data collection
tool-floor-form.htmlSame form as standalone HTML for phone browser
tool-1on1-coach.jsxInteractive 1-on-1 meeting prep coach
Meta
00-index.mdThis file list. Naming convention, rules, what goes where.

02 — Database + Dashboard

The memory that survives between chats

The markdown files are static context. These two layers hold dynamic state — tasks, people, knowledge — that changes every day.

Database + API

Cloudflare D1 + Workers

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.

Dashboard

Netlify, single HTML file

Visual command center — kanban board, people directory, task filters. Opens in a browser when you need the big picture without starting a Claude chat.


03 — Data Flow

Meeting to database in one command

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.

MeetingOtter.ai records
/debriefSlash command
ExtractTasks + intel
ReviewYou approve
D1 PushAPI writes
DashboardAuto-updates

04 — Commands

Slash commands turn Claude into an executor

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, duplicates

05 — Lessons

Things that will bite you if nobody warns you

Artifact persistence is fake

Claude'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.

AI over-attributes tasks to you

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.

Transcript tools misspell names

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.

Log files grow fast

Session logs hit noise threshold within two months. Build monthly archiving into your workflow from day one.

Only log failures, not successes

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.


06 — Daily Routine

It compounds. Every meeting makes it smarter.

Every debrief adds knowledge, every correction trains better behavior, every weekly audit cleans accumulated drift.

AM/morning — pull stats, surface overdue, check drift, flag cold relationships
POST-MTG/debrief — extract tasks and intel from transcript, review, push to database
EOD/close — capture decisions, update state, prevent context loss
FRIDAY/weekly — full audit: contradictions, stale data, duplicates, relationship gaps

07 — Cost

Total cost: $100/month. Infrastructure is free.

Claude Max$100/moProjects give persistent file context. 5x more usage than Pro.
CloudflareFree tierD1 database (SQLite at the edge) + Workers (serverless API). 100K reads/day free.
NetlifyFree tierStatic site hosting for the dashboard. Single HTML file, no build step.

08 — Getting Started

Where to begin if you want to build your own

Start with the markdown files

Create 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.

Use Claude to build the API

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.

Connect Claude to the API

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.

Build the dashboard

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.

Add the debrief loop

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.