Agent Skill
An Agent Skill teaches one repeatable kind of work. It contains focused rules and may include scripts or resources.
Another example
A PDF skill explains form checks, the required renderer, visual checks, and when missing authority must stop work.
Main parts
- 01User intent and context
- 02Model or tool decision
- 03Grounded result and fallback
Use it when
Use it when repeated work needs the same rules, tools, checks, and safe stop points.
Do not use it when
Avoid vague universal skills, hidden side effects, credentials, stale rules, and skills unrelated to the goal.
Name used in code
instructions + resources/scripts + trigger + validation Before you ship
Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback.
Outcome: Use or evaluate Agent Skill to make AI behavior measurable and tied to evidence. User context: A PDF skill explains form checks, the required renderer, visual checks, and when missing authority must stop work. AI method or concept: Agent Skill. Why it fits: Use it when repeated work needs the same rules, tools, checks, and safe stop points. Do not use it when: Avoid vague universal skills, hidden side effects, credentials, stale rules, and skills unrelated to the goal. AI requirements: Define the input and source evidence. Set model and tool permissions. Use versioned evaluation data and measures. Define failure, decline-to-answer, privacy, speed, and cost limits. Operational safeguards: Keep a clear trace and hide sensitive log data. Show users a safe fallback. Mark steps that need human review. Define how to roll back the model or prompt. Acceptance criteria: Record baseline and target measures on a versioned evaluation set. Test edge cases and hostile inputs. Verify fallback, monitoring, permissions, and rollback. Evidence and limits (evidence boundary): This is not a normative standard. Its name, limits, and expected behavior can change from one source to another. Unknowns to confirm: Target task, model and version, evaluation owner, source data, risk limit, tool permissions, and production fallback.
Check this request
Review the current use of Agent Skill. Definition: An Agent Skill teaches one repeatable kind of work. It contains focused rules and may include scripts or resources. Release checks: Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback. Before changing code, report the evidence you found, gaps, severity, and the smallest safe fix.