TRW skills
Use a skill when you want a documented workflow rather than a single MCP operation. The catalog below lists user-invocable workflows; internal skills support other workflows and are not user commands.
Run a skill
In a client that supports the installed skill surface, invoke its command by name, for example /trw-prd-ready. Availability and invocation syntax depend on the client profile. See client guides; if your client does not expose skills, follow the workflow steps directly.
Sprint and delivery
Workflows for sprint setup and completion.
| Command | What it does |
|---|---|
| /trw-commit | Commit requested work with scoped changes and verified evidence |
| /trw-sprint-init | Initialize a new sprint with PRD selection and tracking |
| /trw-sprint-finish | Complete sprint with build gate verification |
| /trw-deliver | Persist learnings and close the session |
| /trw-reflect | End-of-session reflection over the session's own signals - events, diffs, build results, corrections. Run it before /trw-deliver |
Requirements
Workflows for authoring and preparing requirements.
| Command | What it does |
|---|---|
| /trw-prd-new | Create a new PRD and run the full readiness pipeline (groom, review, plan) |
| /trw-prd-ready | Full PRD lifecycle: create or pick up, groom, review, execution plan |
Memory and knowledge
Workflows for inspecting and maintaining stored learnings.
| Command | What it does |
|---|---|
| /trw-memory-audit | Audit learning health: staleness, duplicates, tag distribution |
| /trw-memory-optimize | Prune stale entries, consolidate duplicates, rebalance tags |
| /trw-learn | Record a discovery for future sessions |
Quality and review
Workflows for audits, review, and test strategy.
| Command | What it does |
|---|---|
| /trw-audit | Adversarial spec-vs-code audit against PRD acceptance criteria |
| /trw-self-review | Pre-audit self-review checklist - catches 60%+ of typical findings before formal audit |
| /trw-dry-check | Scan for duplicated code blocks |
| /trw-security-check | OWASP-focused security audit |
| /trw-test-strategy | Audit test coverage and suggest improvements |
| /trw-code-search | Token-efficient code indexing, lexical search, and symbol lookup before broad file reads |
| /trw-delegate | Dispatch an isolated, read-only second-opinion review to another coding-agent CLI |
| /trw-plan-review | Put a plan up for a peer agent to review before the work starts, and check the plan being worked from is still the approved one |
Framework and health
Workflows for checking project setup and framework state.
| Command | What it does |
|---|---|
| /trw-framework-check | Check TRW ceremony compliance and phase gate status |
| /trw-project-health | Audit TRW health in the current project |
| /trw-ceremony-guide | Full ceremony and tool usage guide |
| /trw-feedback | Report a bug, install issue, feature request, or feedback to the TRW maintainers |
Skills describe multi-step workflows. MCP tools are callable operations; host-native agents and hooks depend on client support. Hooks are optional adapters, not a correctness gate.