agentleFS
MohamedRamadanSalahMohamedRamadanSalah/claude-qa-toolkit/.claude/skills/test-cases/SKILL.md

test-cases

Skill0 starsChanged 17 days agoMITView on GitHub

Generate a complete set of test cases from a requirement, user story, screenshot, or feature description. Covers positive, negative, boundary, and edge cases, and validates its own output with a script. Use when the user asks to write, design, or generate test cases or test scenarios.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use preview, ask and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • kv0906Skill

    preview

    Render vault notes as styled HTML and open in browser. Turn markdown docs, decisions, progress reports into readable previews. Use for "/preview docs/project-a/checkout-flow.md", "/preview progress all", "/preview decide auth-approach", or when user wants to see a doc before sharing.

    Also in 3 projects that use this

  • dubwoahSkill

    ask

    Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.

    Also in 3 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Understand the input: If the requirement is missing key facts (expected behavior, user roles, field limits), ask 1-2 short questions.

    line 12
  2. Very specific:

    If the validator prints any ERROR, fix the file and run it again.

    line 36
  3. Very specific:

    If the user asks for CSV/Excel/TestRail format, first produce and validate the markdown version, then convert.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Test Case Generator

You are helping a QA tester design test cases. Follow this workflow EXACTLY — do not skip steps.

Workflow (mandatory)

  1. Understand the input. If the requirement is missing key facts (expected behavior, user roles, field limits), ask 1-2 short questions. Otherwise proceed.
  2. List the testable behaviors first as a short bullet list (this is your checklist — every behavior must get test cases).
  3. Write the test cases to a file named test-cases/<feature-name>.md using EXACTLY this table format — same columns, same order, nothing added or removed:
| ID | Category | Title | Preconditions | Steps | Test Data | Expected Result | Priority |
|---|---|---|---|---|---|---|---|
| TC-001 | Positive | Login succeeds with valid credentials | User account exists and is active | 1. Open login page<br>2. Enter valid email<br>3. Enter valid password<br>4. Click Login | user1@test.com / Pass123! | User lands on dashboard; welcome message shows the user's name | P1 |

Rules for each cell:

  • ID: TC-001, TC-002, ... sequential, no duplicates.
  • Category: exactly one of Positive, Negative, Boundary, Edge, Non-functional.
  • Steps: numbered 1. 2. 3., separated with <br> inside the cell. Precise enough that a junior tester needs zero questions.
  • Expected Result: the exact observable outcome. NEVER "works", "success", "no error".
  • Priority: P1 (critical) / P2 (major) / P3 (minor).
  • Required coverage: at least one Positive, one Negative, one Boundary case. Add Edge cases (interruption, concurrency, unicode/Arabic text, double-submit) whenever the feature has input or state.
  1. Validate your output (MANDATORY):
python .claude/skills/test-cases/scripts/validate_test_cases.py test-cases/<feature-name>.md

If the validator prints any ERROR, fix the file and run it again. Repeat until it prints OK. Never show the user an unvalidated file.

  1. Finish by showing the user: the coverage counts the validator printed, plus a short "Coverage gaps / questions for the team" section listing anything ambiguous in the requirement.

If the user asks for CSV/Excel/TestRail format, first produce and validate the markdown version, then convert.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.