learnship

Save a handoff file when stopping mid-phase so you can resume seamlessly later

Create fix phases for all gaps found by audit-milestone

Research + create + verify plans for a phase — spawns specialist subagents where supported

Show project progress, current position, and what to do next

Execute an ad-hoc task with full agentic guarantees — atomic commits, state tracking, no full planning ceremony

Restore local workflow customizations after updating the platform

Cut a new learnship release — bump version, update changelog, push to public-main, tag, create GitHub release

Remove a planned (not yet executed) phase and renumber subsequent phases

Deep-dive domain research for a phase without immediately creating plans

Restore full project context and continue from where you left off

Quick model profile switch without opening full settings

Interactive settings editor for .planning/config.json

Hand off a project context to a new session or collaborator — writes a HANDOFF.md with full state snapshot

Update the learnship platform itself to the latest version

Retroactive test coverage audit for a completed phase — fill validation gaps without modifying implementation

Manual user acceptance testing — walk through what was built, log issues, create fix plans

Archive a completed milestone, tag the release, and prepare for the next version

Systematic debugging with persistent state — triage, diagnose root cause, plan fix, execute

Capture an architectural or scope decision with its context, alternatives, and rationale into DECISIONS.md

Append a new phase to the current milestone roadmap when scope grows after initial planning

Generate and add test coverage for a specific plan or phase post-execution

Capture a todo/idea mid-session without interrupting flow

Verify milestone met its definition of done — requirement coverage, integration check, stub detection

Review and act on all pending todos captured with add-todo

Archive completed milestone phase directories to keep .planning/phases/ clean

Batch-diagnose multiple UAT issues after verify-work — groups by root cause, proposes fix plan

Structured codebase discovery before working on an unfamiliar area — reads code, maps dependencies, surfaces risks

Capture milestone-level goals, constraints, and anti-goals before new-milestone starts

Capture implementation decisions for a phase before planning starts

Execute all plans in a phase with wave-based ordered execution, spawning subagents per plan where supported

Run a single PLAN.md file in isolation — useful for re-running a failed plan

Project health check — stale files, uncommitted changes, missing artifacts, config drift

Show all available learnship workflows with descriptions and when to use them

Insert a new phase between existing phases for urgent work discovered mid-milestone

Aggregate key learnings and decisions across all sessions into a searchable KNOWLEDGE.md

Surface the intended approach for a phase before planning starts — validate direction early

Show project status, next step, and offer to run it — start every session here

Analyze an existing codebase and produce structured reference docs before starting a new project on top of it

Structured learning retrospective at end of milestone — 5 questions, produces RETROSPECTIVE.md

Start a new milestone cycle on an existing project after a prior milestone is complete

Initialize a new project — questioning → research → requirements → roadmap

Auto-pilot — reads project state and runs the correct next workflow automatically