원클릭으로
openup-create-test-plan
Generate test cases and test plan from use cases and requirements
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Generate test cases and test plan from use cases and requirements
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
One-command project setup for OpenUP - interactive initialization wizard
Mark a task as complete, update roadmap, commit changes, and prepare traceability logs
Execute an already-claimed lane's Operations boxes with script/judgment classification — script steps run directly with zero self-brief, judgment steps self-brief and execute. Handles only pick/resume; every other resolve path routes to /openup-next.
Run OpenUP Assess Results at iteration end — check evaluation criteria, demo only completed acceptance-tested work, feed discovered work back, and trigger the milestone review at a phase boundary
Run the phase milestone go/no-go — prepare derived evidence, pause for the human decision via an input-request, and record the milestone (never advance the phase itself)
Begin a new OpenUP iteration with proper phase context and task selection
| name | openup-create-test-plan |
| description | Generate test cases and test plan from use cases and requirements |
| model | sonnet |
| arguments | [{"name":"scope","description":"What to test (e.g., specific feature, use case)","required":true}] |
This skill generates test cases and test documentation from the OpenUP templates.
Use this skill when:
Do NOT use this skill when:
After using this skill, verify:
docs/test-cases/docs/test-scripts/If docs/project-config.yaml exists, apply it before drafting (skip if
absent): inject its context: as <project-context> and its rules.test-plan
as <project-rules>, then confirm every injected rule holds before marking
the artifact complete. Rules are additive — they may add but never waive a
framework criterion. Full mechanism + precedence (the single source):
docs-eng-process/project-config.md.
Read relevant documentation:
docs/use-cases/*.md for use casesdocs/requirements/*.md for requirements$ARGUMENTS[scope]Ensure docs/test-cases/ and docs/test-scripts/ directories exist.
Copy templates as needed:
docs-eng-process/templates/test-case.md → docs/test-cases/<name>-test-case.mddocs-eng-process/templates/test-script.md → docs/test-scripts/<name>-test-script.mdFor each test case, document:
Replace each test-case file's template provenance frontmatter (type: Template, source_url) with an instance block declaring the file as a
typed test-case work-product instance. Every test-case must trace from
the requirement or use case it verifies (per the v1 spine: test-case → traces-from → requirement | use-case). The upstream instance ALSO
gains a verified-by: entry pointing at this test-case id — that bidir
link is what check-docs.py --coverage reads when it grades whether a
requirement has a verifying test. Grade against the cross-cutting
Doc Traceability Rubric.
Example block:
---
type: test-case # required — v1 spine
id: TC-031 # stable, project-unique
title: <Test Case Name>
status: implemented
traces-from: [REQ-014] # or a use-case id; both are valid upstream types
owner-role: tester
---
Then add verified-by: [TC-031, …] to the upstream requirement / use-case
instance(s). Doing both halves at the test-plan step keeps the trace
symmetric in one author-time pass instead of leaving it to a later cleanup.
Field reference: docs-eng-process/doc-frontmatter.md.
Validator: python3 scripts/check-docs.py --coverage.
For each test script, document:
Apply the Self-Critique SOP (docs-eng-process/sops/self-critique.md) before
validating coverage: take a hostile-reviewer stance, surface every load-bearing
assumption into the plan, and confirm the suite genuinely exercises error and
edge paths — not happy-path restatements — and that every case is written so it
can actually fail. List every weakness you find — including ones you are uncertain about — then fix or explicitly flag each one. Rank them and record the top one or two with their resolutions.
Re-check every item in Success Criteria (top of this skill) against the document you produced; fix any gap before returning.
Returns:
| Error | Cause | Solution |
|---|---|---|
| Template not found | Template path incorrect | Verify docs-eng-process/templates/test-case.md and test-script.md exist |
| Insufficient coverage | Only happy path tests | Add edge cases and error conditions |
| Missing expected results | Test steps without validation | Define expected results for each test step |
docs-eng-process/templates/test-case.mddocs-eng-process/templates/test-script.mddocs-eng-process/openup-knowledge-base/core/role/roles/tester-5.md