← ClaudeAtlas

planlisted

Use when the user has an idea, feature, or fix that is more than a one-sitting edit and says "plan this", "write a plan for X", "/nightshift:plan", or "what would it take to build X". Sizes the work (trivial → no artifact; medium → a lean plan; large → a short spec first), asks one question at a time until the design is settled, then writes a plan the overnight landing loop can land unattended — self-contained `# Task N` sections, empty Open Questions — proves each task extracts with `loop/task-brief`, runs one Codex pass, and opens the plan as its own pull request. Do NOT use to execute a plan (the loop does that at night, or a human by day), for ad-hoc edits, or when the design is already settled and written down (go straight to the task).
jasonm4130/claude-skills · ★ 5 · AI & Automation · score 72
Install: claude install-skill jasonm4130/claude-skills
# Plan by day A plan is the only thing Nightshift reads. What this skill produces is read at 2 a.m. by a generator that cannot ask anyone anything, so every task must be complete on its own, and every open question must be closed before the plan merges. Announce: "Using nightshift:plan to turn this into a landable plan." ## 1. Size it, and stop early when you can | Size | Looks like | Do | |---|---|---| | Trivial | one sitting, one file or one clear edit, no design choice | No artifact. Say so and do it now, or hand it to the user. | | Medium | a few files, one design choice or none, a day's work | A lean plan: header, constraints, tasks. No spec. | | Large | several subsystems, choices that are hard to reverse, more than a day | A short spec first (`docs/specs/YYYY-MM-DD-<slug>.md`: problem, decision, what is out), user-approved, then the plan. | If the work spans independent subsystems, propose one plan per subsystem; each must produce working software on its own. ## 2. Settle the design, one question at a time Read the code the change touches before asking anything. Then ask only what the code cannot answer, one question per turn, preferring multiple choice. State your interpretation and proceed when a wrong guess is cheap; ask when it is not. Two or three questions is typical; ten means the size was wrong. **HARD GATE:** no implementation, no scaffolding, no "quick spike" before the user has approved the design (large) or the task list (medium). The loop lands what