菜单
Phase 4 of athenai-implement pipeline — generate testcases.csv from spec.md. Includes guard for --no-test-cases flag and coverage requirements for user journeys, acceptance criteria, and edge cases.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Manual asset processing skill for Figma layers. Accepts layer URLs and writes deterministic files to drafts/media using curl+sips, with optional get_screenshot fallback.
Phase 3 of athenai-implement pipeline — execute tasks from plan.md and produce working block code. Includes lint-aware CSS generation and mandatory design compliance check when design.md exists.
Phase 0 of athenai-implement pipeline — conditionally produce design.md from Figma. Includes decision logic, extraction-only rules, manual asset handoff, and Phase 1 context pre-loading optimization.
End-to-end implementation pipeline — design, plan, tasks, implement, test cases, test content. Demo mode: skips unit tests and research deep-dives. Records phase wall times via `.specify/scripts/phase-timer.py` (per-phase start/end, subagent logs + merge when parallel). Explicit invocation only — never load from context or topic. Optional flags: --no-parallel (run all phases sequentially in main agent, no subagents), --no-test-cases (skip Phase 4 test case generation).
Phase 1-2 of athenai-implement pipeline — produce plan.md with authored HTML structure, parsing logic, and tasks section. Includes draft test content generation with mandatory edge case coverage.
Phase 5 of athenai-implement pipeline — verify local draft HTML exists, validate .plain.html structure, and print pipeline summary with execution time report.
| name | athenai-testcases |
| description | Phase 4 of athenai-implement pipeline — generate testcases.csv from spec.md. Includes guard for --no-test-cases flag and coverage requirements for user journeys, acceptance criteria, and edge cases. |
Goal: Produce testcases.csv.
If NO_TEST_CASES=true, skip test case generation but still check for an existing testcases.csv:
FEATURE_DIR/testcases.csv exists.Print:
## ✓ Phase 4 — Test Cases skipped (generation)
- **Outputs**: none (generation skipped via --no-test-cases flag)
- **Key decisions**: skipped generation; existing testcases.csv: [found / not found]
- **Edge case coverage**: edge cases from spec.md were applied to draft test content in Phase 1
- **Next**: Phase 5 — Test Content
Then proceed to Phase 5. Do not record 4-testcases timer events when skipped.
When running: if NO_PARALLEL=false, this phase runs as Subagent B in parallel with Phase 2 → 3. If NO_PARALLEL=true, it runs sequentially in the main agent after Phase 3. Starts immediately after Phase 1 (parallel) or Phase 3 (sequential).
When Phase 4 runs: start/end 4-testcases on Subagent B log (parallel) or main log (sequential).
spec.md (must not contain [NEEDS CLARIFICATION] markers — if found, warn but continue).specify/templates/test-cases.csv for column structure| Source | Minimum |
|---|---|
| User journeys (happy path) | One per distinct journey |
| Acceptance Criteria | One or more per AC |
| Edge cases | One per edge case |
| Published page verification | At least one end-to-end |
[Component / Feature Area] | [What is verified]ID,Work Item Type,Title,Test Step,Step Action,Step Expected,Area Path,Assigned To,State
"","Test Case","[Title]",,,,"Consumer Platforms\Adobe Experience Manager (AEM)","","Design"
,,,"1","[Action]","[Expected]",,,
Print Phase 4 report on completion.