菜单
OpenAgentd TDD workflow — write a failing test before the code that makes it pass, reproduce a bug with a test before fixing it. Use when implementing any logic, fixing any bug, or changing any existing behavior in backend (pytest) or frontend (Bun/RTL) code.
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
OpenAgentd workflow for version bumps, release PRs, GitHub releases, and release notes.
Select and create accurate software architecture, workflow, interaction, data, state, and deployment diagrams.
OpenAgentd workflow for keeping the compact feature catalogue and README aligned with user-visible changes.
Research first, propose a step-by-step implementation plan, and wait for explicit approval before writing any code.
Semantic search over the retained OpenAgentd feature catalogue, ADRs, and repository instructions using the turbovec experiment index.
OpenAgentd testing reference — environment setup, run commands, and fix patterns for backend (pytest) and frontend (Bun/RTL). Load this for running, fixing, or adding coverage to existing tests. For writing a failing test before new code, use oad/test-driven-development instead.
| name | oad/test-driven-development |
| description | OpenAgentd TDD workflow — write a failing test before the code that makes it pass, reproduce a bug with a test before fixing it. Use when implementing any logic, fixing any bug, or changing any existing behavior in backend (pytest) or frontend (Bun/RTL) code. |
Write the test first. It must fail for the right reason before you write the code that makes it pass. Tests are proof — "seems right" is not done.
When NOT to use: pure config, docs, or static content changes with no behavioral impact.
Environment specifics (run commands, placement, fixtures, mock rules) live in oad/testing — load it now.
Before touching implementation code, write the test and confirm it fails for the expected reason, not a typo or import error.
Run it:
# backend — single test
uv run pytest tests/path/to/test_file.py::test_new_behavior -q
# frontend — single file
cd web && bun test src/__tests__/components/Foo.test.tsx
Write the smallest change that makes the test pass. Don't add branches, config, or abstraction the test doesn't require yet.
With the test green, improve naming/structure without changing behavior. Re-run after every refactor step.
uv run pytest -n auto -q
cd web && bun test --parallel
Do not start a bug fix by editing implementation. Start by writing a test that reproduces the bug:
Bug report → write a failing test → confirm it FAILS for the right reason
→ implement the fix → confirm it PASSES → run the full suite (no regressions)
Once the reproduction test is green after the fix, hand off to oad/debug step 6 (verify and report) if this was part of a debug session, or to oad/commit to ship the fix.
oad/testing for placement rules)uv run pytest -n auto -q passes (backend changes)cd web && bun test --parallel passes (frontend changes)tests/manual/*.py scenario script re-run if the touched subsystem has one (see oad/testing)oad/commit