Project Onboard
Run an automated filesystem diagnosis so Claude knows which onboarding commands to run next in a new or messy repo.
Overview
project-onboard is a journey-wide agent skill that diagnoses Claude project configuration from the file tree and prescribes the exact slash-command sequence for one of six onboarding cases—usable whenever a solo builder
Install
npx skills add https://github.com/fearovex/claude-config --skill project-onboardWhat is this skill?
- 5-check waterfall in strict priority order—reads real files, never interrogates the user
- Maps the repo to one of 6 onboarding cases with a concrete recommended command sequence
- Accepts `.claude/CLAUDE.md` or root `CLAUDE.md` for global-config layouts
- Check 4 is non-blocking so a healthy project can still surface local skill issues
- Triggers on `/project-onboard`, “what do I run first,” and project setup help
- 5-check waterfall diagnosis
Adoption & trust: 1 installs on skills.sh; 1 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You opened a repo with Claude Code but cannot tell whether you need setup, memory initialization, audit, or fixes—and guessing the wrong `/project-*` command wastes time and leaves context inconsistent.
Who is it for?
Solo builders onboarding to an existing or empty Claude-configured repo who want a read-only diagnosis and scripted next steps instead of ad-hoc exploration.
Skip if: Teams that already completed project-setup and audit with a green report and only need feature implementation—skip repeat onboarding unless files changed materially.
When should I use this skill?
/project-onboard, what do I run first, project setup help, diagnose project state.
What do I get? / Deliverables
You get a labeled case diagnosis, detected file facts, warnings, and a numbered command sequence tailored to the repo so you can invoke project-setup or follow-on fixes without manual triage.
- Case-labeled diagnosis block
- Detected file inventory
- Ordered recommended command sequence
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Scope whether an acquired repo already has CLAUDE.md and ai-context before you commit to a build plan.
Detect Case 1 brand-new projects and chain `/project-setup` then `/memory-init` without manual checklists.
Route to `/project-audit` when configuration exists but quality is unknown before a release push.
Re-diagnose after drift when local skills break while the core project is otherwise healthy (Case 6 plus warnings).
How it compares
Use instead of asking the agent open-ended “how should I configure this project?” when you want case-based routing tied to fearovex/claude-config slash commands.
Common Questions / FAQ
Who is project-onboard for?
Claude Code users maintaining agent-ready repos—especially indie devs juggling multiple codebases who need a fast, file-based state machine before deeper setup skills run.
When should I use project-onboard?
At idea/validate when scoping a inherited codebase; at build when agent-tooling is missing; at ship before audits; at operate when returning to a stale `.claude/` tree—any time triggers like `/project-onboard` or “what do I run first” apply.
Is project-onboard safe to install?
It is procedural read-only diagnosis by design, but review the Security Audits panel on this Prism page and confirm you are comfortable with the companion commands it recommends before running automated fixes.
Workflow Chain
Then invoke: skill fearovex claude config project setup
SKILL.md
READMESKILL.md - Project Onboard
# project-onboard > Reads the current project's file system and determines which of 6 onboarding cases applies, then recommends the exact command sequence. **Triggers**: `/project-onboard`, onboard project, diagnose project state, what do I run first, project setup help --- ## Process I run a 5-check waterfall in strict priority order. I read real files — I never ask the user questions. The first failing check determines the primary case assignment. Check 4 is non-blocking: a project can simultaneously be Case 6 (healthy) and have local skill issues. ### Check 1 — CLAUDE.md exists Read `.claude/CLAUDE.md` (also accept `CLAUDE.md` at project root for global-config repos). **If absent → Case 1: Brand-new project** ``` ## Diagnosis Project state: Case 1 — Brand-New Project Detected: - .claude/CLAUDE.md: NOT FOUND - No Claude configuration present in this project Warnings: - None ## Recommended Command Sequence 1. /project-setup — creates .claude/CLAUDE.md, ai-context/ skeleton, persists context to engram 2. /memory-init — generates ai-context/ files from real project content 3. /project-audit — produces audit-report.md with score and findings 4. /project-fix — applies all corrections from the audit report ## Notes After /project-fix, re-run /project-audit to verify score ≥ 75 and SDD Readiness = FULL or PARTIAL. See ai-context/scenarios.md → Case 1 for failure modes and recovery steps. ``` Stop here if Case 1. --- ### Check 2 — Engram MCP reachable Check if Engram MCP is reachable (call `mem_context`). - If Engram is reachable → SDD infrastructure lives in Engram. Treat the project as healthy for this check and continue to Check 3. - If Engram is NOT reachable → **Case 2** (below). **If Engram not reachable → Case 2: CLAUDE.md present but no SDD persistence** ``` ## Diagnosis Project state: Case 2 — CLAUDE.md Without SDD Persistence Detected: - .claude/CLAUDE.md: FOUND - Engram MCP: NOT REACHABLE - SDD cannot persist artifacts without Engram Warnings: - [list any ai-context/ files found or note if ai-context/ is absent] ## Recommended Command Sequence 1. Ensure Engram MCP server is running and configured 2. /project-audit — diagnose the full scope of what is missing 3. /project-fix — adds SDD section to CLAUDE.md 4. /memory-init — if ai-context/ is empty or absent 5. /project-audit — verify score improved ## Notes project-fix will ask before every change — review each proposed action carefully. See ai-context/scenarios.md → Case 2 for failure modes and recovery steps. ``` Stop here if Case 2. --- ### Check 3 — ai-context/ has ≥ 3 populated files Read `ai-context/` directory. Count files that exist AND have more than 10 lines. Expected files: `stack.md`, `architecture.md`, `conventions.md`, `known-issues.md`, `changelog-ai.md`. **If fewer than 3 populated files → Case 3: Partial SDD, sparse memory layer** ``` ## Diagnosis Project state: Case 3 — Partial SDD (ai-context/ is sparse) Detected: - .claude/CLAUDE.md: FOUND - Engram MCP: REACHABLE - ai-context/ populated files: [N] of 5 (minimum needed: 3) - Missing or empty: [list each absent/stub file] Warnings: - [list any other issues found, e.g. stale onboarding.md] ## Recommended Command Sequence 1. /memory-init — regenerates all ai-context/ files from real project state 2. /project-audit — verify D2 score improved 3. /project-fix — address any remaining findings ## Notes /memory-init does not overwrite files that already have substantial content. See ai-context/scenarios.md → Case 3 for failure modes and recovery steps. ``` Stop here if Case 3. --- ### Check 4 — Local skills review (non-blocking) Read `.claude/skills/