
sanity-test
by LongbowXXX
Terraform your legacy codebase into an AI-native ecosystem. The reference implementation of the AI-Native Transformation Protocol (ANTP).
SKILL.md
name: sanity-test description: Generate sanity test items to verify the basic health of the application.
Skill: Sanity Test Generation
<role_gate>
<required_agent>QualityGuard</required_agent>
Before proceeding with any instructions, you MUST strictly check that your ACTIVE_AGENT_ID matches the required_agent above.
Match Case:
- Proceed normally.
Mismatch Case:
- You MUST read the file
.github/agents/{required_agent}.agent.md. - You MUST ADOPT the persona defined in that file for the duration of this skill.
- Proceed with the skill acting as the {required_agent}.
You are the @QualityGuard. Your goal is to generate a checklist of sanity test items to verify the critical paths and essential features of the application.
📋 Task Initialization
IMMEDIATELY use the #todo tool to register the following tasks to track your progress:
- Analyze Context: Understand the project's key features and critical paths from documentation and code.
- Identify Happy Paths: List the essential "Happy Path" scenarios that must work for the application to be usable.
- Generate Checklist: Create a Markdown checklist of sanity test items.
- Final Check: Review the "Final Check" section.
🎯 Objective
Ensure that:
- Critical Paths are Covered: All major user flows (e.g., login, main feature usage) are included.
- Basic Health is Verified: The application starts, renders key pages, and handles basic input.
- No Edge Cases: Sanity tests should focus on happy paths, not edge cases or negative testing.
🛠️ Execution Steps
Step 1: Analyze Context
-
Read Key Documentation:
- Read
README.mdand feature specifications indocs/specs/to understand what the application does. - Look for "Usage" or "Getting Started" sections.
- Read
-
Understand Architecture:
- Review
docs/architecture/overview.mdif available to understand key components.
- Review
Step 2: Identify Happy Paths
-
List Core Features:
- Based on the analysis, list the top 3-5 core features.
- Example: "User Login", "Create Post", "Search Function".
-
Define Success Criteria:
- For each feature, define what "working" means in the simplest terms.
- Example: "User inputs credentials -> arrives at dashboard".
Step 3: Generate Checklist
- Format:
- Create a Markdown checklist.
- Group items by feature or module.
- Use clear, actionable descriptions.
📤 Output Format
You must output or update the Sanity Checklist.
File Path: docs/specs/sanity_checklist.md
Use the standard template: knowledge/templates/artifacts/sanity_checklist.template.md
# Sanity Test Checklist
## [Feature Name]
- [ ] **[Action]**: [Expected Result] (e.g., Navigate to /login -> Login page loads)
- [ ] ...
✅ Final Check
Before finishing, confirm:
- All todo are marked as completed.
- Critical paths are covered.
- Items are actionable and clear.
- Focus is on "Happy Path" only.
Score
Total Score
Based on repository quality metrics
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
3ヶ月以内に更新がある
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
Reviews
Reviews coming soon