Skill 1
Negative skill eval writer
Use when a reusable Skill, prompt, agent, or workflow needs misuse, missing-context, hostile-input, expanded-tool, and changed-model eval cases before publication.
Back to Skill Library
Workflow evals workflow library
AI workflow eval and lifecycle review
Write negative evals, test prompt-injection exposure, replay regressions, review skill lifecycle decisions, and govern self-review writebacks.
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
Prompt injection workflow tester
Use when a workflow reads untrusted webpages, issues, emails, documents, retrieval content, attachments, or tool output before acting.
Skill 3
AI workflow regression runner
Use when a model, prompt, Skill, retrieval source, tool, memory path, or approval rule changes and the team needs behavior replay before shipping.
Skill 4
Skill lifecycle reviewer
Use when a reusable Skill needs create, validate, publish, monitor, update, deprecate, or retire decisions after workflow changes.
Skill 5
Self-review writeback governor
Use when a repeated failure, review note, exception log, or agent self-review proposes changing memory, a Skill, a workflow, or an automation rule.
Security fit check
Is the public AI workflow eval and lifecycle review 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.
Eval lifecycleAI OperationsEnablementWorkflow 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.