Skip to content
Development
Skill

/create-manual-test-instructions

Turn a ticket or requirements document into a concise QA manual-test file a non-author can follow. Invoke manually only.

From plugin
agent-toolkit
4625 skills
Install
$ npx -y skills add eai-org/agent-toolkit --skill create-manual-test-instructions --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/create-manual-test-instructions

Context preview

The summary Claude sees to decide when to auto-load this skill.

Turn a ticket or requirements document into a concise QA manual-test file a non-author can follow. Invoke manually only.

SKILL.md

create-manual-test-instructions.SKILL.md
name: create-manual-test-instructions
description: Turn a ticket or requirements document into a concise QA manual-test file a non-author can follow. Invoke manually only.
context: fork
license: MIT
metadata:
  version: "1.4"

Create manual test instructions

Read the input ticket or requirements document (and, where needed for accurate navigation, the code it cites). Write the manual-test file in the **same directory**, naming it by replacing `.REQUIREMENTS` or `.TICKET` with `.MANUAL-TEST` (e.g. `FOO.REQUIREMENTS.md` → `FOO.MANUAL-TEST.md`); if the input follows neither convention, append `.MANUAL-TEST` before `.md`. If there is no file (pasted text), follow the project's/user's convention for where plans live (default: `.agents/plans/`), derive a kebab-case `<slug>` from the content, and write `<slug>/<slug>.MANUAL-TEST.md` there. Running forked, you can't ask mid-run: flag any guessed location or slug in the final message for the user to verify.

The file must be followable by someone **unfamiliar with the ticket** — short but complete. Four parts:

1. **What changed** — 1–2 sentences: the feature and the user-visible difference. 2. **How to get there** — concrete navigation to the affected area (entry point, page/screen name, any prerequisite state). 3. **Before vs after** — how the area behaved before, how it should behave now. 4. **What to verify** — checklist of behaviors to confirm, including edge cases (empty values, multiple items, boundaries) where relevant.

Do not modify any source files; the only file you write is the manual-test document.

When done, state the manual-test file's **project-relative path**.

Read more
Ships withagent-toolkit

A collection of generic agentic tools for common engineering tasks, designed to work with any AI agent on any kind of software project.

Get the whole plugin

Other skills on agent-toolkit.