Skill Creator

Create Skills that give the current Agent useful, non-obvious guidance without constraining unrelated work.

For searching SkillHub, uploading a local Skill, or updating an already-published Skill, read references/skillhub-publishing.md and follow the relevant workflow. Searching, local editing and cloud publication are separate actions; publish when the user requests it. An explicit upload/update request is authorization for that publication; ask only for missing choices such as the target Skill or first-publication visibility.

Core Principles

Assume the Agent is already capable. Include only information that changes its decisions or improves its work. Remove generic advice, repeated instructions, speculative edge cases, and examples that do not materially clarify the task.

Preserve user intent and scope. A skill should support the requested task, not replace the user's chosen product, expand the assignment, modify unrelated configuration, or imply permission for additional external actions. Do not turn a particular example, past failure, or personal preference into a universal requirement.

Approval to complete a task does not expand its scope or execution permissions. For retrying or externally mutating workflows, define a stopping condition proportional to the risk.

Match specificity to the risk. Give the model room to choose an appropriate approach when multiple approaches are reasonable. Use detailed steps, deterministic scripts, or absolute language only when correctness, safety, permissions, or a genuinely fragile workflow requires them.