원클릭으로
build
Full SDLC pipeline. Runs all phases end-to-end with human gates on phases 1-3.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Full SDLC pipeline. Runs all phases end-to-end with human gates on phases 1-3.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Autonomous build loop with Karpathy ratcheting, GAN evaluator, and session chaining. Iterates story groups until all features pass or stopping criteria met.
Change the behavior of existing code — story-driven by default, or --issue N for a GitHub bug fix. Test-first, full verification, code review.
Code generation quality principles — TDD, typing, error handling, logging, API integration, LLM integration.
Brownfield change route — take an existing-code feature request from intent to a reviewed PR, scaling from a single /change to an epic via /spec→/design→/auto. Linear-tracked, backed by a committed DeepWiki.
[Internal pipeline stage — run by /auto self-heal and /implement validation when lint/type error volume is high; invoke directly only as a power user.] Turn compiler/linter output into a sharded work queue; fix per package with optional adversarial review — no full monorepo suite mid-shard.
[Internal pipeline stage — run by /auto (follow with /gate); invoke directly only as a power user.] Generate production code and tests for a story group using agent teams for parallel execution.
| name | build |
| description | Full SDLC pipeline. Runs all phases end-to-end with human gates on phases 1-3. |
| argument-hint | [path-to-BRD] [--mode full|lean] |
| context | fork |
Full software development lifecycle pipeline. Orchestrates BRD creation, story specification, architecture design, state initialization, and autonomous build execution across sequential phases (Phase 0 through Phase 10).
This skill is an orchestrator index. Load only the section file for the step you are on.
| When | Read |
|---|---|
| Usage | references/section-01-usage.md |
| Step 0 — Resolve the invocation (run this FIRST, before anything else) | references/section-02-step-0-resolve-invocation.md |
| Approval model | references/section-03-approval-model.md |
| Pipeline Phases (0–11) | references/section-04-pipeline-phases.md |
| Mode Reference | references/section-05-mode-reference.md |
| Gotchas | references/section-06-gotchas.md |
references/section-02-step-0-resolve-invocation.md) — resolve flags via build-lane.js.references/lite-lane.md, references/autonomous-lane.md.Headless modes use plan-confidence.js (and --gate), build-lane.js, budget-state.js, build-chain.js, /auto, /gate, /pr-respond. Full procedure is in the section files. Wiring tests scan entry + references/*.md as one corpus.
--auto / --autonomous (never stop after planning)When the invocation includes --auto (or --autonomous after its single plan gate is satisfied, or is headless with no human):
/auto (with --mode if set) so production code and the project test suite exist.specs/ written. A successful --auto leaves a green app (or a machine-gate failure with code attempted) — never “plan only” unless --plan-only was passed.references/autonomous-lane.md and references/section-04-pipeline-phases.md for the tail (Phases 4–11).