Skill 1
Maintenance record creator
Use when a reusable Skill, prompt, runbook, or workflow instruction needs owner, version, risk, review, eval, and rollback metadata before it is shared or reused.
Back to Skill Library
Agent governance workflow library
Skill maintenance schedule
Keep reusable Skills, prompts, and agent runbooks current with owners, dependency drift maps, review triggers, eval paths, and rollback records.
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
Dependency drift mapper
Use when a Skill, prompt, runbook, or agent workflow may depend on model, provider, tool, schema, retrieval, memory, policy, approval, or output-consumer assumptions that can change.
Skill 3
Review trigger scheduler
Use when a reusable AI instruction needs calendar review cadence plus event-triggered reviews for model, tool, workflow, policy, incident, owner, or risk-tier changes.
Skill 4
Lifecycle decision recorder
Use when a Skill, prompt, runbook, or workflow instruction needs a keep, patch, rewrite, split, merge, retire, block, or revalidate-before-reuse decision after review evidence is collected.
Skill 5
Retirement and rollback planner
Use when a stale, unsafe, duplicated, ownerless, or superseded AI instruction needs a retirement plan, rollback target, replacement route, or revalidation path before reuse.
Security fit check
Is the public Skill maintenance schedule 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 operationsAI OperationsEnablementWorkflow OwnerSecurityPlatform Engineering
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.