Cheatsheet

Every skill across all standr plugins. Each command is invoked as a namespaced slash command inside your agent.

Works with Claude, Codex, Cursor, Gemini, Kiro, OpenCode, Pi, and npx-compatible agents.

architecture

Code in context

Diagnostic

/architecture-scan

Diagnose structural issue category in an area.

/architecture-review

Diff-aware structural review of a PR, worktree, or change.

Placement

/architecture-place

Decide where new behavior belongs.

/architecture-reuse

Find what existing structure should be reused or extended.

/architecture-prep

Identify the minimum structural prep refactor before a feature.

/architecture-align

Create new structure in parallel with the closest repo analog.

Consistency

/architecture-boundary

Inspect responsibility separation.

/architecture-symmetry

Ensure similar concepts are represented similarly.

/architecture-hierarchy

Detect mixed abstraction levels.

Escalation

/architecture-pattern

Suggest a pattern only when it clearly pays rent.

/architecture-reshape

Explicit bigger redesign for ad-hoc or spaghetti zones.

Agent

architecture-reviewer

Deep structural review of placement, boundaries, and consistency.

Context

/architecture-doctrine

Conservative, repo-aware structural philosophy. Loaded automatically — not invocable.

refactor

Code that reads

Diagnostic

/refactor-scan

Diagnose craft issues and recommend the right cleanup skill.

/refactor-review

Pre-merge craft gate: Ready / Mostly ready / Not ready verdict by dimension.

Clarity

/refactor-distill

Remove noise and reduce accidental complexity.

/refactor-rename

Fix weak or misleading names.

/refactor-explicit

Improve clarity at slight cost to brevity.

/refactor-comment

Rewrite comments to explain reasoning.

/refactor-decomment

Delete useless comments.

Consistency

/refactor-normalize

Unify style across related code.

/refactor-idiomatize

Make code feel native to the language/framework.

/refactor-symmetry

Align parallel structures.

Context

/refactor-doctrine

Core code quality philosophy. Loaded automatically — not invocable.

testing

Code you trust

Diagnostic

/testing-scan

Diagnose why a suite passes but still does not buy confidence.

/testing-review

Final quality pass: would this test catch a real break?

Structure

/testing-fixtures

Replace inline test data with shared, composable fixtures that tests can reuse.

/testing-mocks

Choose what to mock, stub, or keep real.

/testing-determinism

Eliminate clocks, randomness, and shared state that make tests pass sometimes and fail others.

Coverage

/testing-scope

Decide what belongs in unit, integration, or end-to-end scope.

/testing-invariants

Add behavioral guarantees and edge cases the suite is missing.

/testing-contract

Protect public API, schema, and boundary behavior instead of implementation details.

/testing-regression

Turn bugs and incidents into durable tests.

Context

/testing-doctrine

Confidence over coverage theater. Loaded automatically — not invocable.