jat-onboard

Solid

Onboard a new client project — analyze client docs, create knowledge bases, write Supabase migration, generate PRD and tasktree. Run after jst-new has set up the mechanical scaffolding.

AI & Automation 240 stars 23 forks Updated today MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
79
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# /jat:onboard — New Client Onboarding AI-powered onboarding for new client projects. Handles the steps that need intelligent analysis after `jst-new` has done the mechanical setup. ## Prerequisites Run `jst-new <project>` first. It creates: - Project directory cloned from JST template - JAT project registration - Standard data tables (team, integrations, open_questions) - Bootstrap CLAUDE.md - Initial git commit ## Usage ``` /jat:onboard # Interactive — prompts for client docs /jat:onboard docs/client-prd.md # Analyze specific doc /jat:onboard ~/Downloads/intake.pdf # Analyze from any path ``` --- ## STEP 1: Locate Client Documents Check for input docs in this order: 1. File path provided as argument 2. Files in `docs/` directory 3. Files in `~/Downloads/` matching project name 4. Ask user to provide docs **Supported formats:** Markdown, PDF, DOCX (converted to .md), plain text Read ALL provided documents thoroughly before proceeding. --- ## STEP 2: Extract Structured Data From the client documents, extract: ### 2A: Team Information Parse out all people mentioned with roles and responsibilities. ```bash # Populate the team data table jt data exec "INSERT INTO team (name, role, title, email, decision_authority, portal_role, notes) VALUES (...)" --force ``` ### 2B: Integrations Inventory Identify all external services, APIs, and tools mentioned. Classify each as: `keep` (integrate), `replacing` (build bespoke), or `new` (we'r...

Details

Author
joewinke
Repository
joewinke/jat
Created
6 months ago
Last Updated
today
Language
Svelte
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category