← ClaudeAtlas

agentic-project-bootstraplisted

The day-one instantiation runbook for the whole human-directs-AI-agents workflow system. Use when starting a new project; when adopting this workflow on an existing project; for day-one setup; when standing up a spec, memory files, GitHub-backed planning and delivery, quality gates, a review cadence, and an evolution ledger together; when someone says "set up the workflow", "bootstrap this repo", "start a project the agentic way", or "instantiate the agentic workflow". This is the ROUTER — it sequences the sibling skills and gets out of the way. Do not trigger it for ordinary mid-project Issue, PR, documentation, or implementation work. Premise: the workflow is the product, as much as the code.
gidde032/agentic-workflow · ★ 0 · AI & Automation · score 63
Install: claude install-skill gidde032/agentic-workflow
# Agentic Project Bootstrap The instantiation runbook. In one session you stand up a **spec with phases, a memory architecture, GitHub-backed planning and delivery, quality gates, a review cadence, and an evolution ledger** — then hand off to the per-phase loop and stay out of the way. **The key promise:** a new project starts at the *end state* of a reference project rather than deriving it, skipping ten documented workflow revisions of trial and error. You inherit the matured loop, not the derivation. These are **solo-maintainer defaults**, calibrated on one agent-heavy project and extended through two documentation-and-GitHub migrations. They are not a validated team-scale claim. Where this skill gives a number or default, preserve its evidence boundary rather than upgrading it — see `examples.md`. --- ## The bootstrap sequence A numbered runbook. A **CHECKPOINT** is a hard stop only when the human must ratify a consequential decision or grant external-write authority. Once a project profile, spec, and authorized action boundary have been ratified, continue through mechanical setup without repeating approval requests. Stop again only when evidence contradicts the approved profile, a new consequential choice appears, or an external action falls outside the granted authority. The checkpoint rationale lives in `agentic-collaboration-cadence`. ### Discovery gate — resolve product uncertainty before Step 0 If the product's problem, audience, scope, core workflow, build-