← ClaudeAtlas

cortex-setup-projectlisted

Bootstrap Cortex for a new project or import existing session history. Use when the user says 'set up Cortex', 'seed this project', 'import my history', 'backfill memories', 'bootstrap memory', 'initialize Cortex for this project', or when starting to use Cortex on an existing codebase that already has Claude Code conversation history.
cdeust/Cortex · ★ 48 · AI & Automation · score 73
Install: claude install-skill cdeust/Cortex
# Setup Project — Fully Autonomous Bootstrap Execute all four phases sequentially without asking the user any questions. If a phase fails, attempt automatic recovery before reporting the error. Never ask the user to run commands manually or choose between options. ## Phase 1: Infrastructure Verification 1. Run `pg_isready` via bash to check if PostgreSQL is running. 2. Call `cortex:memory_stats({})` to verify database connectivity. 3. If **either** check fails: - Run `bash "${CLAUDE_PLUGIN_ROOT}/scripts/setup.sh"` automatically. Do not ask for permission. - After setup.sh completes, call `cortex:memory_stats({})` again to verify. - If it still fails, report the error output and **stop**. Do not continue to later phases. 4. If both checks pass, proceed to Phase 2. ## Phase 2: Build Methodology Profiles 1. Call `cortex:rebuild_profiles({"force": true})` to scan all session history and build cognitive profiles per domain. 2. This creates the domain hubs that memories, entities, and discussions link to. It must run before seeding. 3. Record the domain count for the final summary. ## Phase 3: Codebase Seeding 1. Call `cortex:seed_project({"directory": "<cwd>"})` where `<cwd>` is the current working directory. 2. Record the count of discoveries for the final summary. ### Phase 3b: Pipeline Codebase Analysis (Optional) The ai-automatised-pipeline MCP server provides structured codebase analysis (symbol graph, processes, communities, cross-file impact). It is option