Requirement-to-Testpoint Extraction
Paste the following prompt into your AI chat to install this skill:
Please follow the guide at https://skillhub.cn/install/skillhub.md to install @user_827d1ddb/requirement-to-testpoints into your AI assistant.
About this skill
Problem
When reviewing long PRDs, user stories, or specs, manual test-point extraction is serial and uneven. Happy paths are often covered, while boundary values, exception paths, performance, security, and compatibility checks scatter across individuals’ experience, producing inconsistent coverage.
How It Works
The skill decomposes requirement documents into a module tree, then extracts business rules, interface dependencies, state transitions, and feature points. It then applies five dimensions to each module: functional validation, business-rule combinations, boundary conditions, exception scenarios, and non-functional inference. For example, file upload triggers checks for large files, unsafe file types, concurrent uploads, and interrupted recovery; payment or login triggers idempotency, privilege escalation, expired tokens, and brute-force protection. Finally, it deduplicates semantically, labels priorities as P0/P1/P2, and outputs a reviewable checklist.
Boundaries
It produces test points, not executable test scripts, and does not replace requirement review. Ambiguous or contradictory requirements reduce output quality, and domain-specific rules for finance, healthcare, or other regulated areas still need team input. Review P0 items first, then P1/P2, and remove scenarios that do not apply to the current project.
Use Cases
- After receiving a 50-page order PRD, draft functional, boundary, exception, and non-functional test points quickly so the QA team can review P0 coverage before planning.
- Before reviewing user stories, list P0 test points and rule conflicts for payment, login, and export modules for the design discussion.
- For a file upload requirement, derive checks for large files, unsafe types, concurrency, recovery, and formats before implementation starts to reduce late QA surprises.
- Cross-check multiple API specs and functional docs, then generate a prioritized test checklist labeled by dimension for the QA review meeting.
Best For
- Test lead owning requirement review: needs a quick, discussable test-coverage framework from PRDs.
- Test engineer inheriting an old module: needs boundary, exception, and compatibility checks beyond happy paths.
- QA analyst writing acceptance criteria: needs user stories converted into P0/P1/P2 test-point lists.
- Technical owner running pre-release smoke checks: needs core paths and high-risk test points marked.
Related Skills
Automatically indexes Gradle-cached AAR/JAR dependency classes and returns library coordinates, versions, and public APIs by fully qualified name, using only the Python standard library.
Codifies AMT and YourMT3 training conventions, script patterns, hyperparameters, precision, checkpoints, and NaN safeguards.
Retrieve relevant chunks from a customer-managed PKM dataset by dataset_id and return concise, source-annotated answers.
Scan frontend repos and monorepos to generate executable Python or Node.js CLIs with API, type, enum, and auth support.