Skill 1
Skill intent and boundary capturer
Use when a reusable AI instruction needs its intended task, out-of-scope boundary, users, output contract, allowed inputs, blocked inputs, and approval owner captured before smoke tests are written.
Back to Skill Library
Agent governance workflow library
Skill smoke test runner
Build a five-case smoke-test packet before reusable Skills, prompts, runbooks, or workflow instructions are shared with a team.
This is a complete workflow library with 5 individual skills. Download the full library or pick the specific skill folder your team needs first.
Individual skills in this library
Use one skill at a time, or keep the full workflow together.
Some AI tools expect one skill folder per upload. Download the full library when you want the whole workflow, or download an individual skill when you only need one job done.
Skill 2
Smoke scenario set builder
Use when a Skill, prompt, runbook, or workflow instruction needs a small scenario set covering normal, messy, sensitive, unsupported, and adversarial inputs.
Skill 3
Expected output rubric writer
Use when each smoke scenario needs concrete expected behavior, must-include fields, must-not-include fields, scoring notes, and critical failure conditions before outputs are judged.
Skill 4
Smoke run reviewer
Use when Skill, prompt, runbook, or workflow outputs need to be reviewed against the smoke scenarios and expected-output rubric.
Skill 5
Regression promotion gatekeeper
Use when a changed Skill, prompt, runbook, or workflow instruction needs a release decision after smoke-test results, regression notes, and approval routes are reviewed.
Security fit check
Is the public Skill smoke test runner library enough, or does this need deeper review?
Use the public library when the workflow is low-risk, the inputs are already sanitized, and a team member can review the output before it reaches a buyer or customer.
Do deeper review when this workflow touches real tools, data sources, role ownership, approval paths, or customer-facing output.
Skill evalsAI OperationsEnablementSecurityPlatform EngineeringWorkflow Owner
Good deeper-review trigger signals
- The workflow touches customer, prospect, CRM, proposal, security, pricing, or campaign data.
- Different teams disagree on the approved source of truth.
- The AI output could become customer-facing, revenue-impacting, or compliance-sensitive.
- You need reusable eval checks before asking more people to use the workflow.