test-analyze
Analyze test results and create a fix plan with subagents. Use when triaging failing tests, analyzing JUnit XML, planning fixes for accessibility/security, or categorizing flaky/E2E failures.
How do I install this agent skill?
npx skills add https://github.com/laurigates/claude-plugins --skill test-analyzeIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill analyzes test results and creates fix plans. It is susceptible to indirect prompt injection because it reads and processes untrusted test report files without implementing boundary markers or input sanitization, which could allow malicious data to influence the planning logic.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- Runlayerpass
1/1 file flagged
What does this agent skill do?
Test Analysis and Fix Planning
Analyzes test results from any testing framework, uses Zen planner to create a systematic fix strategy, and delegates fixes to appropriate subagents.
When to Use This Skill
| Use this skill when... | Use test-report instead when... |
|---|---|
| Triaging a directory of failing-test results into a fix plan | You only need a quick cached status read |
| Categorizing flaky, performance, accessibility, or security failures | Running the tests in the first place (use test-run) |
| Delegating fixes to specialized subagents | Asking strategic "how should we test X?" questions (use test-consult) |
| Producing a structured plan from JUnit XML or coverage output | Iterating on a single failing spec (use test-focus) |
Usage
/test:analyze <results-path> [--type <test-type>] [--focus <area>]
Parameters
-
<results-path>: Path to test results directory or file (required)- Examples:
./test-results/,./coverage/,pytest-report.xml
- Examples:
-
--type <test-type>: Type of tests (optional, auto-detected if omitted)accessibility- Playwright a11y, axe-coreunit- Jest, pytest, cargo testintegration- API tests, database testse2e- Playwright, Cypress, Seleniumsecurity- OWASP ZAP, Snyk, TruffleHogperformance- Lighthouse, k6, JMeter
-
--focus <area>: Specific area to focus on (optional)- Examples:
authentication,api,ui-components,database
- Examples:
Examples
# Analyze Playwright accessibility test results
/test:analyze ./test-results/ --type accessibility
# Analyze unit test failures with focus on auth
/test:analyze ./coverage/junit.xml --type unit --focus authentication
# Auto-detect test type and analyze all issues
/test:analyze ./test-output/
# Analyze security scan results
/test:analyze ./security-report.json --type security
Command Flow
-
Analyze Test Results
- Parse test result files (XML, JSON, HTML, text)
- Extract failures, errors, warnings
- Categorize issues by type and severity
- Identify patterns and root causes
-
Plan Fixes with PAL Planner
- Use
mcp__pal__plannerfor systematic planning - Break down complex fixes into actionable steps
- Identify dependencies between fixes
- Estimate effort and priority
- Use
-
Delegate to Subagents
- Accessibility issues →
code-reviewagent (WCAG compliance) - Security vulnerabilities →
security-auditagent - Performance problems →
system-debuggingagent - Code quality issues →
code-refactoringagent - Test infrastructure →
test-architectureagent - Integration failures →
system-debuggingagent - Documentation gaps →
documentationagent
- Accessibility issues →
-
Execute Plan
- Sequential execution based on dependencies
- Verification after each fix
- Re-run tests to confirm resolution
Subagent Selection Logic
The command uses this decision tree to delegate:
-
Accessibility violations (WCAG, ARIA, contrast) →
code-reviewagent with accessibility focus -
Security issues (XSS, SQLi, auth bypass) →
security-auditagent with OWASP analysis -
Performance bottlenecks (slow queries, memory leaks) →
system-debuggingagent with profiling -
Code smells (duplicates, complexity, coupling) →
code-refactoringagent with SOLID principles -
Flaky tests (race conditions, timing issues) →
test-architectureagent with stability analysis -
Build/CI failures (pipeline errors, dependency issues) →
cicd-pipelinesagent with workflow optimization
Output
The command produces:
-
Summary Report
- Total issues found
- Breakdown by category/severity
- Top priorities
-
Fix Plan (from PAL planner)
- Step-by-step remediation strategy
- Dependency graph
- Effort estimates
-
Subagent Assignments
- Which agent handles which issues
- Rationale for delegation
- Execution order
-
Actionable Next Steps
- Commands to run
- Files to modify
- Verification steps
Notes
- Works with any test framework that produces structured output
- Auto-detects common test result formats (JUnit XML, JSON, TAP)
- Preserves test evidence for debugging
- Can be chained with
/git:smartcommitfor automated fixes - Respects TDD workflow (RED → GREEN → REFACTOR)
Related Commands
/test:run- Run tests with framework detection/code:review- Manual code review for test files/docs:update- Update test documentation/git:smartcommit- Commit fixes with conventional messages
Prompt:
Analyze test results from {{ARG1}} and create a systematic fix plan.
{{#if ARG2}} Test type: {{ARG2}} {{else}} Auto-detect test type from file formats and content. {{/if}}
{{#if ARG3}} Focus area: {{ARG3}} {{/if}}
Step 1: Analyze Test Results
Read the test result files from {{ARG1}} and extract:
- Failed tests with error messages
- Warnings and deprecations
- Performance metrics (if available)
- Coverage gaps (if available)
- Categorize by: severity (critical/high/medium/low), type (functional/security/performance/accessibility)
Step 2: Use PAL Planner
Call mcp__pal__planner with model "gemini-2.5-pro" to create a systematic fix plan:
- Step 1: Summarize findings and identify root causes
- Step 2: Prioritize issues (impact × effort matrix)
- Step 3: Break down fixes into actionable tasks
- Step 4: Identify dependencies between fixes
- Step 5: Assign each fix category to appropriate subagent
- Continue planning steps as needed for complex scenarios
Step 3: Subagent Delegation Strategy
Based on the issue categories, delegate to:
-
Accessibility violations (WCAG, ARIA, color contrast, keyboard nav) → Use
Tasktool withsubagent_type: code-review→ Focus: WCAG 2.1 compliance, semantic HTML, ARIA best practices -
Security vulnerabilities (XSS, SQLi, CSRF, auth issues) → Use
Tasktool withsubagent_type: security-audit→ Focus: OWASP Top 10, input validation, authentication -
Performance issues (slow tests, memory leaks, timeouts) → Use
Tasktool withsubagent_type: system-debugging→ Focus: Profiling, bottleneck identification, optimization -
Code quality (duplicates, complexity, maintainability) → Use
Tasktool withsubagent_type: code-refactoring→ Focus: SOLID principles, DRY, code smells -
Flaky/unreliable tests (race conditions, timing, dependencies) → Use
Tasktool withsubagent_type: test-architecture→ Focus: Test stability, isolation, determinism -
CI/CD failures (build errors, pipeline issues) → Use
Tasktool withsubagent_type: cicd-pipelines→ Focus: GitHub Actions, dependency management, caching -
Documentation gaps (missing docs, outdated examples) → Use
Tasktool withsubagent_type: documentation→ Focus: API docs, test documentation, migration guides
Step 4: Create Execution Plan
For each subagent assignment:
- Context: What files/areas need attention
- Objective: Specific fix goal
- Success Criteria: How to verify the fix
- Dependencies: What must be done first
- Verification: Commands to re-run tests
Step 5: Present Summary
Provide:
- 📊 Issue Breakdown: Count by category and severity
- 🎯 Priorities: Top 3-5 issues to fix first
- 🤖 Subagent Plan: Which agents will handle what
- ✅ Next Steps: Concrete actions to take
- 🔍 Verification: How to confirm fixes worked
{{#if ARG3}} Additional focus on {{ARG3}}: Prioritize issues related to this area and provide extra context for relevant subagents. {{/if}}
Documentation-First Reminder: Before implementing fixes, research relevant documentation using context7 to verify:
- Test framework best practices
- Accessibility standards (WCAG 2.1)
- Security patterns (OWASP)
- Performance optimization techniques
TDD Workflow: Follow RED → GREEN → REFACTOR:
- Verify tests fail (RED) ✓ (already done)
- Implement minimal fix (GREEN)
- Refactor for quality
- Re-run tests to confirm
Do you want me to proceed with the analysis and planning, or would you like to review the plan first?
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/laurigates/claude-plugins/test-analyze">View test-analyze on skillZs</a>