tc-review
Compares test documentation with codebase knowledge to find missing scenarios and improve coverage.
Install
mkdir -p .claude/skills/tc-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13168" && unzip -o skill.zip -d .claude/skills/tc-review && rm skill.zipInstalls to .claude/skills/tc-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review QA test case documents (Markdown) against source code to find coverage gaps. Use when reviewing test cases, analyzing test coverage, suggesting missing scenarios, or learning codebase to extract testable scenarios. Supports project-based learning from multiple GitHub repos with dual memory (local + Dify RAG).Key capabilities
- →Review QA test case documents against source code
- →Identify test coverage gaps
- →Suggest missing test scenarios
- →Learn codebase from GitHub repositories
- →Search project knowledge base
- →Batch review multiple test case files
How it works
The skill reviews Markdown test case documents by comparing them against knowledge learned from GitHub source code, identifying coverage gaps and suggesting new test cases.
Inputs & outputs
When to use tc-review
- →Identify test coverage gaps
- →Validate test case documentation
- →Learn codebase for testing
- →Generate new test scenarios
About this skill
Test Case Review
Review test case documents against source code knowledge. Learn codebases, identify coverage gaps, suggest missing test cases.
Quick Start
# 1. Create project and add repos
python scripts/setup_project.py myproject https://github.com/org/repo.git
# 2. Review test cases
python scripts/review.py tests/checkout.md --project myproject
Decision Tree
User task → What do they need?
│
├─ Review test cases → Is project set up?
│ ├─ No → Run: python scripts/setup_project.py <name> <repo-url>
│ └─ Yes → Run: python scripts/review.py <testcase.md> --project <name>
│
├─ Learn new codebase → Run: python scripts/learn.py <project>
│
├─ Get suggestions → Run: python scripts/suggest.py <project>
│
└─ Search knowledge → Run: python scripts/search.py <project> "<query>"
Available Scripts
Always run with --help first to see usage. Scripts handle complex workflows reliably.
| Script | Purpose |
|---|---|
scripts/setup_project.py | Create project + add repo + learn (all-in-one) |
scripts/review.py | Review test case file against knowledge |
scripts/learn.py | Learn/re-learn source code from repos |
scripts/suggest.py | Generate test case suggestions |
scripts/search.py | Search project knowledge |
scripts/batch_review.py | Review multiple files at once |
Test Case Format
Test cases must be Markdown. See references/testcase-format.md for complete guide.
# Test Suite: Payment Flow
## TC-001: Successful Payment
**Preconditions:**
- User logged in
- Cart has items
**Steps:**
1. Navigate to checkout
2. Enter valid card
3. Click Pay
**Expected Result:**
Payment success, order created
Example Workflows
Review Single File
python scripts/review.py tests/login.md --project auth-service
Output:
📊 Score: 65/100 Coverage: 65%
✅ Covered: Successful login, Invalid password
⚠️ Missing: Account locked, Rate limiting, Session timeout
💡 Suggested: TC-005 Account Lockout, TC-006 Rate Limit
Batch Review
python scripts/batch_review.py "tests/**/*.md" --project myapp --min-score 70
Quick Review (No Project Setup)
python scripts/setup_project.py temp-project https://github.com/org/repo.git
python scripts/review.py tests/feature.md --project temp-project
Environment Variables
| Variable | Required | Description |
|---|---|---|
ANTHROPIC_API_KEY | Yes* | For Claude LLM |
OPENAI_API_KEY | Yes* | For OpenAI/Codex |
LLM_PROVIDER | No | anthropic or openai (default: anthropic) |
LLM_MODEL | No | Model name |
DIFY_API_KEY | No | Enable Dify RAG |
DIFY_DATASET_ID | No | Dify dataset ID |
*One of ANTHROPIC_API_KEY or OPENAI_API_KEY required.
Reference Files
- testcase-format.md - Complete test case writing guide
- scenarios.md - Test scenario types and examples
- troubleshooting.md - Common issues and solutions
When not to use it
- →When test cases are not in Markdown format
- →When the codebase is not available in a GitHub repository
- →When a quick review without project setup is not desired
Prerequisites
Limitations
- →Test cases must be in Markdown format
- →Requires GitHub repositories for codebase learning
- →Requires an LLM API key (Anthropic or OpenAI)
How it compares
This skill automates the process of cross-referencing test case documentation with actual source code, providing a quantitative score and specific suggestions for improvement, which is more efficient than manual review.
Compared to similar skills
tc-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| tc-review (this skill) | 0 | 5mo | Review | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| pr-review | 6 | 2mo | Review | Intermediate |
| pytest | 8 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by diegosouzapw
View all by diegosouzapw →You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
pytest
prowler-cloud
Pytest testing patterns for Python. Trigger: When writing or refactoring pytest tests (fixtures, mocking, parametrize, markers). For Prowler-specific API/SDK testing conventions, also use prowler-test-api or prowler-test-sdk.
code-change-verification
openai
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
python
alinaqi
Python development with ruff, mypy, pytest - TDD and type safety