基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/archibate/dotfiles-opencode --skill tdd-workflow命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Best practices for AI-driven English-to-Chinese translation. This skill should be used when the user asks to "translate to Chinese", "update the Chinese translation", "improve Chinese translation", "fix translation quality", "review Chinese translation", or when translating any English text into Chinese. Also applies when polishing an existing Chinese translation of English content.
This skill should be used when sending images, files, or notifications back to the user via messaging platforms (Discord, Feishu, Telegram, etc.) through cc-connect. TRIGGER when agent generates a plot/chart/screenshot and wants to show the user; agent creates a report/PDF/file the user should receive; agent needs to proactively notify the user (e.g. task completed, alert, reminder); user asks to "send image", "show me the chart", "notify me", "send the file", "send to Telegram", "show plot in Discord".
Browser automation CLI for AI agents. Use when needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. TRIGGER when user requests to "open a website", "fill out a form", "click a button", "take a screenshot", "debug this in browser", "scrape data from a page", "test this web app", "login to a site", "frontend UI/UX aesthetics", "automate browser actions", or any task requiring programmatic web interaction.
| name | tdd-workflow |
| description | Use this skill for developing software in TDD (Test-Driven Design). |
A strict 7-step TDD cycle that produces high-quality, well-tested code. Each step must be verified and confirmed before proceeding. Status is only updated after real verification
Core principle: RED (failing test) -> GREEN (minimal implementation) -> REFACTOR.
At the start of each session, before doing anything else:
tdd-summary/ to check for existing step reports (e.g. step-1.md, step-2.md).step-1.md under
an "Assumptions" section rather than asking for clarification.Write tdd-summary/step-1.md:
# Step 1 - Understand Intent
## Functional Requirements
### FR-1: <title>
<description>
### FR-2: <title>
<description>
## Assumptions
- <any ambiguous point and the assumption made>
For each functional requirement, create a scenario document at docs/scenario/<name>.md:
# Scenario: <Title>
- Given: <precondition>
- When: <action>
- Then: <expected outcome>
## Test Steps
- Case 1 (happy path): <brief description>
- Case 2 (edge case): <brief description>
- Case N: ...
## Status
- [x] Write scenario document
- [ ] Write solid test according to document
- [ ] Run test and watch it failing
- [ ] Implement to make test pass
- [ ] Run test and confirm it passed
- [ ] Refactor implementation without breaking test
- [ ] Run test and confirm still passing after refactor
**IMPORTANT**: Only update above status when a step is confirmed complete. Do not hallucinate.
Invariant: Count of FR = count of scenario documents. Verify before continuing.
Write tdd-summary/step-2.md:
# Step 2 - Write Scenario Docs
## Scenario Documents Created
- FR-1: <title> - `docs/scenario/<name>.md`
- ...
For each scenario document:
tests/scenario/test_<name>.py (or equivalent).- [x] Write solid test according to document.After writing, run each test and verify it fails:
- [x] Run test and watch it failing.Invariant: Count of scenario documents = count of test files. Verify before continuing.
Write tdd-summary/step-3.md:
# Step 3 - Write Failing Test
## Failing Tests Created
- FR-1: <title> - `docs/scenario/<name>.md` - `tests/scenario/test_<name>.py`
- ...
For each failing test:
- [x] Implement to make test pass.- [x] Run test and confirm it passed.Write tdd-summary/step-4.md:
# Step 4 - Implement to Make Tests Pass
## Implementations Completed
- FR-1: <title> - `docs/scenario/<name>.md` - Implementation in `<module>`
- ...
All tests now pass. Scenario documents updated.
For each scenario where tests now pass:
- [x] Refactor implementation without breaking test.- [x] Run test and confirm still passing after refactor.Write tdd-summary/step-5.md:
# Step 5 - Refactor for Maintainability
## Refactorings Completed
- FR-1: <title> - `docs/scenario/<name>.md` - <what was improved>
- ...
All tests still pass after refactoring. Scenario documents updated.
Run the complete test suite (all tests, not just those added in this session):
NEVER modify existing tests that are unrelated to the current functional requirements.
Write tdd-summary/step-6.md:
# Step 6 - Regression Test
## Regression Test Results
- Complete test suite executed: `<command>`
- All tests pass: Yes / No
- If regression found: <brief description of fix applied>
Verify that every scenario document has all status checkboxes checked.
Review:
Write tdd-summary/step-7.md:
# Step 7 - Final Review
## Summary
- Functional requirements addressed:
- FR-1: ...
- Scenario documents: `docs/scenario/...`
- Test files: `tests/scenario/...`
- Implementation complete and all tests passing after refactoring.
## How to Test
Run: `<test command>`
Finally, archive the summary folder:
mv tdd-summary/ completed-tdd-archives/tdd-$(date +%Y%m%d-%H%M%S)
TDD workflow complete.