← ClaudeAtlas

do-sdlclisted

Supervise a full SDLC pipeline run to merge in a local Claude Code session. Triggered by 'do-sdlc', 'run the full pipeline', 'ship this issue end to end', 'supervise the sdlc'.
tomcounsell/ai · ★ 19 · AI & Automation · score 74
Install: claude install-skill tomcounsell/ai
# do-sdlc — Local Pipeline Supervisor This skill is the **local stand-in for the bridge PM session**. `/sdlc` (in this repo) is a single-stage router by contract: it dispatches ONE sub-skill and returns, expecting a PM session to re-invoke it. In a local Claude Code session there is no PM loop — this skill IS that loop: it re-invokes the router, dispatching each stage to a subagent on the stage-appropriate model (opus/sonnet), until merge, a blocking guard, or the iteration cap. You are the supervisor, not the worker. You assess, dispatch, and track. The stage subagents do all the work. **Redundant-context check (issue #2026, WS-F):** if a bridge PM/dev context already owns this issue — a live eng session (e.g. a bridge PM session) or a live supervised-run signal for the issue number — then `/do-sdlc` is redundant: that context IS the supervision loop. Do not run it; drive via `/sdlc` (in this repo, the single-stage router) instead. Running `/do-sdlc` inside an already-owned run nests a second supervision loop and wastes turns. ## Repo Context Probe If `docs/sdlc/do-sdlc.md` exists, read it and honor its declarations; otherwise use the generic defaults described below. The defaults drive the pipeline through `sdlc-tool` (synced to every machine via `~/.local/bin`), `gh`, and `git`. ## Hard Rules 1. **NEVER write code, run tests, or create plans directly** — every stage executes inside a stage subagent that invokes the stage's `/do-*` skill. 2. **NEVER decide dispatch y