ypxing

crew-address-findings

Triage and fix findings from a crew-afk sprint review report using TDD.

solve-issue

Implement a single issue end-to-end: read it, explore context, install deps, build with TDD, verify checks, and commit. Platform-agnostic — works in worktrees or branches.

Fetch all review comments on the current branch's open PR, challenge each one critically, implement sensible ones using TDD, commit touched files, and print a summary. Trigger with /address-pr-comments.

crew-afk

Implements all ready-for-agent issues by dispatching each to a crew-coder subagent (a separate pi process per worktree), then housekeeping the result. Loops until no issues remain or all stall; reviews every branch before merge. Optional: --model <alias|inherit>; --prd-audit off|report|fix; --fix-findings critical|high|medium|none.

tdd

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

dep-install

Detect the project's install mode (host or docker) and install dependencies once. Used as a shared step by solve-issue, crew-address-findings, and address-pr-comments.

configure-tracker

Select and install an issue tracker template. If only one template is available it is applied automatically; otherwise presents a numbered menu. Writes the chosen template to the project-level config path. Use when setting up a new project's issue tracker or switching tracker backends.

to-issues

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

to-prd

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Testing & QA Listed

add-tests

Discover the project's coverage command, rank under-covered files by risk, resolve a mocking convention per ecosystem, and hand the findings to to-issues as ready-for-agent issues. Use when the user wants to close testing-coverage gaps or asks to find where test coverage is weakest.

upgrade-deps

Audit outdated npm/yarn/pnpm dependencies across a monorepo — security-advisory exploitability, transitive conflicts, real call-site usage, and targeted changelog review for major bumps — then publish issues (batched for trivial in-range bumps, one per package or coupled group otherwise; every major-version bump defaults to ready-for-human, minor/patch range-edits stay ready-for-agent unless a conflict or advisory can't be resolved cleanly) with required test additions and a safety checklist, for crew-afk or solve-issue to execute. Use when the user wants to upgrade dependencies, audit outdated packages, or plan a safe dependency bump. Does not perform the upgrade itself.

crew-grill

Full design pipeline — grill the user about a plan (lite by default; add "with docs" to also update CONTEXT.md and ADRs via domain-modeling), produce a PRD, then break it into issues. Use when starting a new feature from scratch.

caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

crew-brainstorm

Use when starting a complex or exploratory feature and you want a thorough design pipeline before implementation — explores intent, proposes approaches, builds a full technical spec, then auto-transitions to PRD and issues.

domain-modeling

Updates CONTEXT.md glossary and creates ADRs inline as design decisions crystallise. Use when you want to capture resolved domain terms or record architectural decisions during any session.

improve-codebase-architecture

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.