test-plan-from-requirements
Skill1 starsChanged 28 days agoMITView on GitHub
Turn a user story, PRD, or ticket into a risk-based test plan with prioritized test cases, test data, and automation candidates.
In this repository16 other files it gives its agents.
- accessibility-auditSkill
- api-test-generatorSkill
- automation-code-reviewSkill
- bug-report-writerSkill
- ci-cd-and-test-dataSkill
- device-cloud-setupSkill
- flaky-test-triageSkill
- framework-scaffolderSkill
- greenbuild-getting-startedSkill
- llm-app-testingSkill
- mobile-automationSkill
- performance-test-starterSkill
- regression-health-digestSkill
- release-readiness-checklistSkill
- tools-and-librariesSkill
- visual-testingSkill
The file
Files
Test plan from requirements
- Collect the input (story text, acceptance criteria, ticket link, mockups). If the acceptance criteria are missing, list the questions they leave open before writing cases.
- Restate the feature in 2 to 3 lines, then list assumptions and out-of-scope items.
- Risk analysis: for each area, rate likelihood x impact (H/M/L). Think about money, data loss, security, auth, and how much of the user journey it touches.
- Derive cases with standard techniques: equivalence partitioning, boundary values, decision tables for rule combinations, state transitions for workflows, and error guessing. Add negative, permission, and accessibility (keyboard, labels) checks where they apply.
- Output a table: ID | Title | Preconditions | Steps | Expected | Priority (P0-P3) | Type (UI/API/unit) | Automate? (Y/N plus reason).
- Apply the test pyramid: push each check to the lowest layer that can catch it (unit < API < UI).
- List test data needs and environment needs.
- End with a coverage summary (criteria → case IDs) and the open questions.
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
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.