Test Skill
Guides a maker through debugging a topic they just created or updated — driving it, confirming the reply is real, checking the fix doesn't break the intent the eval cases encode, and localizing a fault to either the flow it calls or the topic's own internal state. Published by microsoft in Employee-Self-Service-Agent-Developer-Kit.
Decision snapshot
Is this a fit?
Testing, Includes SKILL.md, Reusable instructions
Compatibility not yet detected.
Permission behavior not yet detected.
Copy skill directory
2 months ago · MIT license
No specific cautions were detected. Review the source and requested permissions before installing.
What is Test Skill?
Guides a maker through debugging a topic they just created or updated — driving it, confirming the reply is real, checking the fix doesn't break the intent the eval cases encode, and localizing a fault to either the flow it calls or the topic's own internal state. Published by microsoft in Employee-Self-Service-Agent-Developer-Kit. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Testing
- Testing use cases
Declared skill metadata
- Source file: solutions/ess-maker-skills/src/skills/topics/test/SKILL.md
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
When to use Test Skill
- Use it for testing.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/Employee-Self-Service-Agent-Developer-Kit
- Skill file: solutions/ess-maker-skills/src/skills/topics/test/SKILL.md
What it does
Guides a maker through debugging a topic they just created or updated — driving it, confirming the reply is real, checking the fix doesn't break the intent the eval cases encode, and localizing a fault to either the flow it calls or the topic's own internal state.
Skill instructions
Test / Debug Topic Skill Guides a maker through debugging a topic they just created or updated — driving it, confirming the reply is real, checking the fix doesn't break the intent the eval cases encode, and localizing a fault to either the flow it calls or the topic's own internal state. Eval cases are the read-only intent guardrail. A topic's evaluation cases (authored upstream via the evaluations/create skill, stored as EvaluationData under {agent.folder}/evaluations/) encode the intended customer-facing behaviour — especially failure handling (backend down, record missing, connection unauthorized). This skill treats them as a guardrail: a fix must not break the intent they encode. It reads that intent; it does not grade the topic against the cases and it never edits them. If a topic has no eval cases yet, that is a signal to author them with evaluations/create — not work this skill does. Absent evals, drive a representative trigger phrase instead. The debug-and-validate loop Debugg
Verified compatibility and discovery
Frequently asked questions
What is Test?
Test is a open-source AI agent skill with Copy skill directory. Guides a maker through debugging a topic they just created or updated — driving it, confirming the reply is real, checking the fix doesn't break the intent the eval cases encode, and localizing a fault to either.
Who is Test best for?
Test is best for reusing agent instructions, scripts, and references, testing workflows.
How do I install Test?
Install or run Test using Copy skill directory. Check Test for the latest setup command.
Is Test actively maintained?
Test may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
