Skills

Skills (recipes) are slash commands that define what to do. Each skill is described in a SKILL.md file with frontmatter metadata and instructions for agents. Brewcode includes 9 skills covering the full task lifecycle — from project analysis to E2E testing.

On top of those there is a dynamic tenth skill: it is not shipped with the plugin, it is generated into every target project by /brewcode:superreview-setup and invoked there as /superreview, tailored to that project’s tech stack, agents, rules and tracker. See the emitted skill page for details.

The -setup naming rule

Setup skills draw their verbs from one vocabulary, in this order:

status · install · upgrade · enable · disable · uninstall · purge

A bare invocation means status when the mechanism is installed and install when it is not — with one deliberate exception: semble-setup always defaults to status, because its install reaches outside the project to run brew install uv.

All eleven -setup skills implement all seven verbs, via one of two mechanisms: a live config flag the reader re-checks on every invocation, or entry-file parking, where the filename discovery keys on is renamed <name>.disabled with the body left byte-identical. teams-setup uses parking: enable/disable move each roster member’s agent file between <agent>.md and <agent>.md.disabled. Skill-specific extras come after the canonical set, never in place of it: reindex, optimize and resume on semble-setup.

Summary table

#	Skill	Command	Model	Purpose
1	agents	/brewcode:agents	opus	Creates, improves, syncs Claude Code subagents
2	convention	/brewcode:convention	opus	Extracts etalon classes, patterns, architecture into convention docs
3	e2e	/brewcode:e2e	opus	Orchestrates e2e testing: BDD scenarios, Playwright autotests
4	rules	/brewcode:rules	sonnet	Syncs KNOWLEDGE.jsonl or session learnings to project rules
5	semble-setup	/brewcode:semble-setup	opus	Installs, audits and maintains the semble_code semantic code-search MCP
6	setup-status	/brewcode:setup-status	sonnet	Read-only dashboard: which setup skills are installed, stale, partial or missing here
7	skills	/brewcode:skills	opus	Lists, improves, creates, syncs Claude Code skills
8	superreview-setup	/brewcode:superreview-setup	opus	Generates a project-tailored deep-review skill: domain-expert routing + scope discipline + mechanical gates + adversarial validation
9	teams-setup	/brewcode:teams-setup	opus	Creates and manages dynamic teams of domain agents
★	superreview (emitted)	/superreview	opus	Per-project deep review — written into your repo by /brewcode:superreview-setup

Test coverage

Delegation — one contract, all nine skills

Every skill here except read-only setup-status fans work out to subagents, and all of them follow the same sizing rule.

One subagent = ONE bounded unit: one deliverable, roughly 5 files, roughly 10 steps. Anything bigger is split into N tasks and spawned in ONE message, in parallel. That is why convention runs 10 layer agents instead of one, e2e partitions scenarios across parallel agents, and teams-setup creates agents one file per spawn.

Every spawn prompt carries six fields — a bare one-line task is never enough:

Field	Content
GOAL	the overall task and why it exists — the point beyond the file edit
ROLE	what this agent owns; what it must NOT touch
SCOPE	exact paths/commands in bounds + explicit out-of-bounds
CONTEXT	what is already done, by whom, what runs in parallel — trimmed to what THIS agent needs
CONSUMER	who or what uses the result next, and the shape it must fit
DONE	acceptance criteria + the exact report shape you want back

The same brief lives in the runtime templates these skills read — the e2e mode references, convention’s rules guide, teams-setup’s roster template, and superreview-setup’s emitted skill template — so a fan-out three levels deep still gets a full brief.

Lifecycle

The recommended skill execution order for a standard project cycle:

Skill dependencies

setup-status  (read-only: what is already here)
      |
superreview-setup --> /superreview (emitted into your repo)
      |
      +-- convention (optional)
      +-- rules
      +-- teams-setup (optional)
      +-- semble-setup (optional)

Independent Skills

These skills work standalone — no prerequisite steps required: