An automated and structural quality assurance skill that scores, optimizes, and reviews functional test cases against system requirements documents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install testcase-reviewer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install testcase-reviewer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TestCase Reviewer?
The testcase-reviewer skill is designed to bring measurable rigor, automation, and structure to software quality assurance workflows. Operating within the Openclaw Skills ecosystem, it systematically assesses functional test cases across six primary dimensions: completeness, accuracy, validity, executability, compliance, and maintainability. By cross-referencing inputted test suites directly with requirement documentation or PRDs, the skill eliminates human oversight and exposes critical gaps early in the development lifecycle.
Beyond basic text analysis, this skill performs deep architectural checks on test designs. It evaluates core structural traits like test case atomicity, logical independence, repeatability, data decoupling, and the appropriate utilization of classic QA methodologies such as boundary value analysis and state transition mapping. Developers and QA engineers receive data-driven scoring, missing scenario mapping, and granular, actionable remediation matrices.
TestCase Reviewer Use Cases
- Quick self-assessment of initial test case drafts for new feature branches.
- Enforcing high-quality test gate checks prior to final code reviews.
- Post-generation alignment and human-in-the-loop validation of AI-generated test cases.
- Conducting periodic audits, maintenance, and optimizations of legacy test repositories.
- Onboarding junior QA engineers by providing automated, mentor-grade corrective feedback.
How TestCase Reviewer Works
- The user supplies both the system requirement documents (PRD, user stories, or functional specs) and the corresponding test cases.
- The skill runs an implicit syntax and structural format linter to ensure all mandatory keys, specific prioritization values, and string variables are fully populated.
- The agent parses the core requirement documentation to build an internal map of feature lists, operational boundaries, and exception-handling feedback loops.
- It executes rule-based linting against the test cases, validating field assertions, logical structural progression, and unique ID mappings.
- The system computes exact weight-based quality scores across the six fundamental evaluation metrics.
- A comprehensive review matrix is compiled, highlighting missing operational flows, deep dependency trees, and individual test flaws.
- The final structured evaluation document is written out locally into markdown files.
TestCase Reviewer Setup
To deploy and configure the testcase-reviewer asset within your runtime directory, configure your workspace environment as follows:
# Navigate to your workspace tool directory
cd default-workspace/skills/
# Clone or download the testcase-reviewer asset configuration
mkdir -p testcase-reviewer
cat << 'EOF' > testcase-reviewer/SKILL.md
# [Insert the raw SKILL.md contents here]
EOF
# Verify your system setup contains the required output directory
mkdir -p report/
TestCase Reviewer Data Schema & Taxonomy
The testcase-reviewer relies on rigorous input specifications and formats its structured outputs inside your local workspace.
Input Document Specifications
- Requirements File (Mandatory): Supports Markdown (
.md), Word (.docx), PDF, raw text, or direct PRD hyperlinks. Used to generate requirement metrics. - Test Case Sheet (Mandatory): Supports Excel (
.xlsx), Markdown tables, JSON arrays, or plain text lists. Requires unique ID, title, preconditions, actions, expected results, classification type, and prioritization level tags. - Business Rules (Optional): Structured logic mapping custom role configurations or field actions.
- Audit Targets (Optional): Specific areas to force strict analysis parameters on (e.g.,
permissions,boundaries).
Output Report Taxonomy
The tool outputs comprehensive reports under the report/ path using the naming convention {Project_or_Module_Name}测试用例评审报告.md.
| Section | Component Content |
|---|---|
| 1. Comprehensive Assessment | Total test counts, PRD match percentage metrics, master grade mapping (A, B, C, D), and dimension scores. |
| 2. Requirement Traceability Matrix | A direct mapping grid linking functional requirement IDs directly to validating test cases. |
| 3. Core Problem Clearinghouses | Categorized lists separating immediate format adjustments from critical structural issues. |
| 4. Structural Strategy & Appendices | Actionable missing test scenario recommendations, cross-case data flow sequencing, and weight criteria rules. |
TestCase Reviewer Advanced Features
- Custom prioritization upgrades that dynamically escalate severity based on explicit keyword emphasis rules.
- Intelligent context-aware reverse verification to validate negative behaviors and empty state assertions.
- Automated data dependency trees that group test execution workflows and deliver decoupling strategies.
- Hard structural validation rules that fail test sets containing ambiguous definitions such as 'success' or 'normal' without clear assertions.
SKILL.md
Loading
Related Openclaw Skills
The Fourth Turning: An American Prophecy
An analytical toolkit based on the Strauss-Howe Generational Theory that maps American history into repeating 80-100 year cyclical turnings driven by generational archetypes.
Eleven Rings: The Soul of Success Skill
An AI-powered leadership and team-building toolkit based on Phil Jackson's championship philosophy, blending Zen mindfulness, ego management, and system-driven success.
Stock and Crypto Analysis
A powerful terminal and agent-driven finance assistant that analyzes stocks and cryptocurrencies, tracks portfolios, and detects market-moving rumors in real time.
The Great Influenza Pandemic Preparedness Agent
An AI-powered historical research and pandemic analysis agent modeled after John M. Barry's authoritative work on the 1918 Spanish flu.
The Forgotten Highlander: WWII Survival & History AI Skill
An interactive AI skill that unpacks Alistair Urquhart's WWII survival memoir, delivering deep historical insights and cognitive resilience frameworks.
What Every Body Is Saying: FBI Body Language Guide
An interactive AI behavior analysis agent based on ex-FBI agent Joe Navarro's definitive body language and nonverbal communication framework.
Featured*
