·
Last changedVersion:
This version passed the hardening gate. Hardening applied 4 targeted changes and preserved all other text. Classified findings before hardening: 0. Classified findings closed: 0. Classified findings remaining: 0. Unclassified scanner findings remaining: 0. Review findings closed: 2. Review findings remaining: 12.
None
None
Expand | File | Group | Subtype | Severity | Status |
|---|
No findings available
0 findings
An AI-powered skill that generates comprehensive, workable unit tests for any programming language using a coordinated multi-agent pipeline.
Use this skill when you need to:
This skill coordinates multiple specialized agents in a Research → Plan → Implement pipeline:
Make sure you understand what user is asking and for what scope. When the user does not express strong requirements for test style, coverage goals, or conventions, source the guidelines from unit-test-generation.prompt.md. This prompt provides best practices for discovering conventions, parameterization strategies, coverage goals (aim for 80%), and language-specific patterns.
Start by calling the polyglot-test-generator agent with your test generation request:
The Test Generator will manage the entire pipeline automatically.
The polyglot-test-researcher agent analyzes your codebase to understand:
Output: .testagent/research.md
The polyglot-test-planner agent creates a structured implementation plan:
Output: .testagent/plan.md
The polyglot-test-implementer agent executes each phase sequentially:
polyglot-test-builder subagent to verify compilationpolyglot-test-tester subagent to verify tests passpolyglot-test-fixer subagent if errors occurpolyglot-test-linter subagent for code formattingEach phase completes before the next begins, ensuring incremental progress.
All pipeline state is stored in .testagent/ folder:
| File | Purpose |
|---|---|
| Codebase analysis results |
| Phased implementation plan |
| Progress tracking (optional) |
| Agent | Purpose | Tools |
|---|---|---|
| Coordinates pipeline | runCommands, codebase, editFiles, search, runSubagent |
| Analyzes codebase | runCommands, codebase, editFiles, search |
| Creates test plan | codebase, editFiles, search |
| Writes test files | runCommands, codebase, editFiles, search, runSubagent |
| Compiles code | runCommands, codebase, search |
| Runs tests | runCommands, codebase, search |
| Fixes errors | runCommands, codebase, editFiles, search |
| Formats code | runCommands, codebase, search |
The polyglot-test-fixer agent will attempt to resolve compilation errors. Check .testagent/plan.md for the expected test structure.
Review the test output and adjust test expectations. Some tests may require mocking dependencies.
Specify your preferred framework in the initial request: "Generate Jest tests for..."
Get started with chainctlchainctl skill install public/github/polyglot-test-agent:latest
Bring Chainguard's hardening pipeline to your first-party skills — custom rulesets, automated remediation, full audit trail.
skills.cgr.dev/public/github.com/github/skills/polyglot-test-agent:latest
MIT
HARDENING.md
LICENSE
SKILL.md
unit-test-generation.prompt.md