← ClaudeAtlas

fastapi-rest-of-the-owllisted

Use when the user hands you a task definition and wants the ENTIRE development loop run end-to-end — plan, implement, review and fix, QA the change with evidence appropriate to it, open a humanized PR, then poll CI and code review, fixing and resolving until the PR is green and clean. Does everything except merge. Long-running and autonomous; the human keeps the merge button.
steph-dove/klaussy-agents · ★ 16 · API & Backend · score 78
Install: claude install-skill steph-dove/klaussy-agents
## Task `$ARGUMENTS` If `$ARGUMENTS` is empty, use the task definition the user pasted into the conversation (a ticket, a design note, a one-line ask). If there is none, stop and ask for one — this skill needs a target. ## The bit *How to draw an owl: (1) draw two circles. (2) draw the rest of the owl.* The user just handed you the two circles — a task definition. This skill draws the rest of the owl: the whole lifecycle from "here's what I want" to "here's a green, reviewed PR waiting for your merge." It is a genuine end-to-end run, not a gag — but it earns the name by doing the enormous unglamorous middle the meme skips over. **It does everything except merge.** The merge button stays with the human. Never merge, never force-push over someone else's work, never mark the PR ready-to-merge on the user's behalf. ## How this skill works You orchestrate the repo's other skills as a pipeline. Each phase below names the sibling skill whose playbook you follow — open that skill's `SKILL.md` and run its steps, then come back here for the next phase. Track the whole run with TodoWrite: one todo per phase, `in_progress` when you start it, `completed` when it's done. The flow is long and mostly unattended; the todo list is how the user follows along. Stop and hand back to the user (do not barrel ahead) if any phase hits something a human must decide: a missing secret or env var, an ambiguous requirement the task definition doesn't settle, a destructive migration, or a test fail