Skill 1
Mismatch envelope recorder
Use when a failed or questionable AI output needs a structured record before prompt, Skill, evaluator, or parser changes are proposed.
Back to Skill Library
Agent governance workflow library
Prompt Mismatch Log Review
Turn failed AI outputs into mismatch records, failure labels, route decisions, regression cases, and owner-reviewed prompt-change packets before rewriting prompts.
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
Failure label splitter
Use when a mismatch record needs a failure label that separates intent mismatch, missing constraint, stale context, output-schema mismatch, unsafe action, evaluator mismatch, and downstream integration failure.
Skill 3
Clarification route chooser
Use when a mismatch may require a clarifying question, tighter input contract, example, schema validation, retrieval change, tool boundary change, evaluator change, or human checkpoint instead of a prompt rewrite.
Skill 4
Regression case promoter
Use when a mismatch pattern should become an eval case, smoke test, regression example, or Skill acceptance criterion.
Skill 5
Prompt change decision recorder
Use when reviewers need to decide and document whether to rewrite a prompt, edit a Skill, add an example, change schema, change retrieval, change evaluator, add approval, or leave unchanged.
Security fit check
Is the public Prompt Mismatch Log 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.
Prompt maintenanceAI OperationsProductEnablementSupportWorkflow OwnerSecurity
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.