Skip to content
Development
Skill

/test

Guidelines describing how to test the code. Use whenever writing new or updating existing code, for example after implementing a new feature or fixing a bug.

From plugin
claude-toolbox
15525 skills9 agents4 commands1 MCP

Claude Code

$ npx -y skills add serpro69/claude-toolbox --skill test --agent claude-code

SKILL.md

test.SKILL.md
name: test
description: |
  Guidelines describing how to test the code.
  Use whenever writing new or updating existing code, for example after implementing a new feature or fixing a bug.

Testing & Quality Assurance Process

Conventions

  • **Read capy knowledge base conventions** at [shared-capy-knowledge-protocol.md](shared-capy-knowledge-protocol.md).
  • **Read verification policy** at [shared-verification-policy.md](shared-verification-policy.md).
  • **Read profile detection** at [shared-profile-detection.md](shared-profile-detection.md). When an active profile contributes a `test/` subdirectory (e.g., `${TOOLBOX_PLUGIN_ROOT}/profiles/k8s/test/`), its `index.md` lists validators, check categories, and any binary-presence or auto-detection protocols the skill must apply. See Step 2 of the Workflow.

Workflow

**Mandatory order — instructions before action.** The flow below is strictly sequential. Load this skill and its shared protocols, then complete profile detection and load all resolved profile content before investigating subject files or running validators/tests. Only bounded inspection to resolve a declared routing predicate may precede profile loading.

1. **Detect active profiles.** Run the `shared-profile-detection.md` procedure against the changed files. 2. **Load profile content.** For each active profile that contributes a `test/` subdirectory, load `${TOOLBOX_PLUGIN_ROOT}/profiles/<name>/test/index.md` and read its always-load + any matching conditional content. Honor the binary-presence protocols named there BEFORE any validator invocation — a missing pre-check step can crash on a tool that isn't installed. 3. **Apply the test guidelines below.** With instructions loaded, inspect the affected behavior, select proportionate checks and execute applicable profile validators.

Guidelines

1. Cover intended behavior, affected contracts and consequential boundaries. Reuse existing coverage; add a regression test when it would meaningfully detect recurrence. 2. Investigate failing tests against the requirement and implementation. Correct a flawed test explicitly; never relax a valid assertion just to obtain a pass. 3. Start with relevant checks and honor explicit repository/release requirements. Broaden or repeat only when changed shared behavior, failures or unresolved risks justify it; apply the loaded verification policy to agent evaluations. 4. **Profile-aware validators.** Apply the validators and check categories the active profile's `test/index.md` specifies (loaded in Step 2 of the Workflow); honor the binary-presence protocol documented there — missing binaries should surface install hints, not shell errors.

**Capy search:** Before applying test guidelines, search `kk:test-patterns` for project-specific testing approaches and known edge cases.

Choose techniques that answer the actual verification question; this is not a required checklist:

  • Use table-/data-driven tests and test generation
  • Benchmark tests and performance regression detection
  • Integration testing with test containers
  • Mock generation with %LANGUAGE% best practices and well-establised %LANGUAGE% mocking tools
  • Property-based testing with %LANGUAGE% best practices and well-establised %LANGUAGE% testing tools
  • Propose end-to-end testing strategies if automated e2e testing is not feasible
  • Code coverage analysis and reporting

**Capy index:** If a novel testing approach or tricky edge case was discovered during this session, index it as `kk:test-patterns`.

Read more
@serpro69
Ships withclaude-toolbox

<div align="center" claude-toolbox is a collection of "tools" for all your agentic workflows — pre-configured MCP servers, skills, sub-agents, commands, hooks, statuslines with themes, and more - everything you need for AI-powered development workflows, used

15525 skills9 agents1 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
155
Star history of serpro69/claude-toolbox on GitHub, a chart by star-history.com

Other skills on claude-toolbox.

alpha

alpha

Alpha links a shared instruction directly, delegates to a peer skill, and spawns a review agent. Together these exercise the…

beta

beta

Beta reaches shared resources through the plugin-root variable, which exercises the template-ref (concrete suffix) and…

brainstorm

brainstorm

TRIGGER when: asked to brainstorm, think through, explore, or pressure-test a technical idea or decision through conversation.…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills11d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about test.

Which coding agents can use test?
test installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.