Skip to content
Michi v2026.11.16
Save the Tokens

Skills Overview

Michi’s skills are Claude Code slash commands that guide different phases of development. They range from rigid (follow every step) to flexible (a posture, not a checklist).

Most milestone work follows a three-skill cycle:

/michi-planning → /michi-session → /michi-debrief

Plan the work, execute it with verification discipline, review what happened. This is the load-bearing structure. Bootstrap happens once before the first cycle. Everything else supports or supplements this loop.

SkillTypeWhen to use
michi-bootstrapFlexibleBefore first session — onboard a project, scaffold docs
michi-exploreFlexibleResearch, brainstorming, cold starts, pre-planning
michi-planningFlexibleBefore implementation — write the milestone plan
michi-sessionRigidDuring implementation — execute with verification
michi-debriefFlexibleAfter implementation — review, capture, calibrate
michi-sustainabilityFlexibleBetween milestones — health checks at scaled depth
michi-scenario-test-builderFlexibleDuring planning — generate Kaner-style scenarios
michi-workshopFlexibleEveryday work — bug fixes, small features, quick tasks
michi-expeditionFlexibleLearning-mode work — open-ended exploration where the end isn’t known
michi-loopRigidAutonomous loops — gate, contract, verifier, stop conditions, lights-off launch
michi-awayFlexibleStepping away mid-work — keep the cycle running Entrusted; guesses and blocks logged for your return
michi-second-lookRigidIndependent review from a separate session — delivered work against the accepted criteria, read-only; audit mode asks what should change
michi-pr-prepFlexibleBefore PR review — prepare a review guide
michi-libraryFlexibleAt handoff — a project library for observers, practitioners and contributors (with an HTML site), a standalone handoff, or an epic overview, derived from the working docs
michi-diagramsFlexibleWhen a doc needs a figure — Mermaid diagrams true to the source, readable in light and dark on GitHub and in IDEs
michi-docs-siteFlexibleDocs infrastructure — an internal docs browser or a PDF build recipe

Only michi-session, michi-loop and michi-second-look are rigid. The rest adapt to the situation.

The core loop is the production lane — convergent work marching toward a known deliverable. Two other lanes exist, and the form of verification you can answer routes between them:

  • Convergent (“how do I know I’m done?”) → the production lane. When done-criteria are measurable, a trustworthy verifier exists, and autonomy has been earned, michi-loop can run the work lights-off.
  • Progress (“am I making progress, or spinning?”) → michi-expedition, the learning-mode lane — spiral toward clarity, accreting a portrait instead of shipping a deliverable.
michi-bootstrap (once)
└── Creates: Michi doc structure, CLAUDE.md, PROJECT.md, STATUS.md
michi-explore (as needed)
└── Produces: research findings, epic docs, shared understanding
michi-planning
├── Explores codebase, surfaces assumptions
├── Co-designs verification scenarios
└── Produces: milestone plan doc
michi-session
├── Executes against the plan
├── Logs decisions, notes, discussion items
└── Produces: committed milestone, verified code
michi-debrief
├── Reviews decisions and discussion items
├── Promotes learnings to journal, patterns, CLAUDE.md
└── Produces: journal entry, trust assessment
michi-sustainability (between milestones/epics)
└── Assesses: code quality, test quality, architecture, knowledge gaps

Skills aren’t silos — work flows between them naturally.

Workshop → full lifecycle. In one project, a session started with /michi-workshop to investigate a Python export tool. The question “should it move to JS and add tests?” grew the scope. The human initiated a transition: workshop → bootstrap → planning → session → debrief. The workshop skill’s guidance says “know when you’ve outgrown it” — this was that moment.

Explore → planning. Research often precedes planning. /michi-explore builds the shared context that makes a plan grounded rather than speculative. When the exploration produces enough to plan against, transition to /michi-planning.

Planning → session. When the plan is reviewed and approved, /michi-session executes it. The plan doc is the handoff artifact.

Debrief → next planning. The debrief’s trust assessment, captured learnings, and updated scenarios feed directly into the next milestone’s planning. This is the spiral — each debrief makes the next plan better.

A few behaviors recur across the skills. The skill pages don’t repeat them.

  • Your overrides come first. Every skill except michi-loop reads docs/reference/extensions.md when it exists, and its instructions take priority over the skill’s defaults. /michi-bootstrap customize creates it (local customizations). michi-expedition also looks for extensions.md at the expedition root.
  • STATUS stays current. Skills that change what’s active (planning, session, debrief, workshop, explore, sustainability, expedition, library, away) update STATUS.md before they close, and the epic’s journal.md when they wrote to it.
  • Your collaboration notes are read. Bootstrap, explore, session, debrief and sustainability read docs/memory.md when it exists.
  • Epic north stars. When an epic has north-stars.md (document types), planning quotes it into each plan, session re-reads it at scope changes and before claiming done, and workshop, debrief, away and second-look check their work against it. Explore offers to capture one when an exploration opens an epic. A trade against a north star goes to you, never into the work.
  • Multi-project repos. In a repo marked multi-project: true, bootstrap, planning, session, debrief and sustainability ask which project the work is for, and write under docs/ROOT/ (the umbrella) or docs/<name>/ (a sub-project).
  • Invoked by name only. michi-away, michi-loop and michi-second-look never start on their own; type the command.
  • Quick task, minimal ceremony? → michi-workshop
  • Need to understand something first? → michi-explore
  • Ready to build a milestone? → michi-planning → michi-session → michi-debrief
  • Between milestones, want a health check? → michi-sustainability
  • Need verification scenarios? → michi-scenario-test-builder (during planning)
  • Preparing a PR for review? → michi-pr-prep
  • Open-ended discovery, no known deliverable? → michi-expedition
  • Convergent work with a verifier you trust, run unattended? → michi-loop
  • Stepping away, want the work to keep moving? → michi-away
  • Want delivered work checked by an agent that wasn’t there? → michi-second-look, from a separate session
  • Handing work to someone who wasn’t in the sessions? → michi-library
  • A doc needs a diagram? → michi-diagrams
  • Want to browse your project docs as a site? → michi-docs-site

Individual skill details are in the Skills Reference.