Skill 1
Process evidence intake reviewer
Use when event-log exports, process-mining summaries, task-mining notes, tickets, CRM exports, worker observations, or workflow notes need safety review before AI-assisted process redesign.
Back to Skill Library
Agent governance workflow library
Process evidence packet
Review process evidence, variants, baselines, and intervention choices before assigning AI workflows, Skills, or agents.
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
As-is process mapper
Use when a team needs a step-level map of how a process actually runs from redacted process evidence rather than from assumed diagrams or policy documents.
Skill 3
Variant and rework reviewer
Use when redacted logs or process notes show alternate paths, waits, loops, reopens, handoffs, exceptions, or compliance deviations that may change the AI workflow design.
Skill 4
Baseline metric packet builder
Use when a workflow needs a business baseline and measurement method before AI assistance, Skills, agents, or automation are recommended.
Skill 5
AI intervention router
Use when process evidence needs to be translated into human-only, AI assist, shared review, supervised AI, autonomous AI, no-automation, or process-removal recommendations.
Security fit check
Is the public Process evidence packet 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.
Process evidenceWorkflow OwnerAI OperationsSecurity
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.