← ClaudeAtlas

phasinglisted

Orchestrate multi-phase work across fresh Claude sessions with mandatory plan-mode gating and self-verification. Use this skill whenever a user has a plan or task that touches multiple subsystems, has natural break points, would benefit from re-grounding mid-execution, or when the user wants to stay in the loop on every decision instead of dispatching subagents. Trigger this when a presented plan looks too big for one execution, when the user invokes /phase, or when a user mentions phasing, breaking work into chunks, multi-step implementation, or wanting fresh context between work units. Even if the user doesn't explicitly say "phase it," consider this skill whenever a plan spans backend + frontend + DB, has 8+ task items across different domains, or where context rot in a single session is likely.
unifylabs-dev/unify-kit · ★ 0 · Code & Development · score 63
Install: claude install-skill unifylabs-dev/unify-kit
# Phasing — Multi-phase orchestration with fresh sessions This skill orchestrates large work across multiple fresh `claude` sessions, with plan mode gating every session and self-verification gating every plan-mode exit. The user stays in the loop at every decision; no subagents do the work. The framework's whole value is harnessing **plan mode in a fresh session**. Each phase opens its own session with clean context, brainstorms/asks/researches, drafts a plan, self-verifies the plan, gets user approval, then executes. The orchestrator session (where `/phase` was invoked) tracks state, polls for completion, and gates progression. ## §4. When to use (three trigger paths) ### §4.1 Auto-offer after a plan is presented When you draft a plan for the user, evaluate "too big for one execution" against four criteria. Two-of-four = include `Phase it?` in the approval menu. - Criterion A: Touches >1 distinct subsystem (e.g., DB + API + frontend; or auth + email + billing) - Criterion B: Has natural break points where re-grounding on completed predecessor work would help - Criterion C: Single execution likely runs into context pressure - Criterion D: Downstream steps would benefit from grounding on verified prior output **Auto-offer menu shape** (use this exact shape via `AskUserQuestion`, adapted from the post-plan-mode menu in §5.4 because at this moment no plan is drafted yet): ``` AskUserQuestion( question: "<one-sentence summary of why phasing might apply>. Phase it?",