メニュー
Use when creating or revising standalone agent profiles, including frontmatter, triggers, prompts, tool limits, examples, and delegation checks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Design OpenAPI component schemas with discriminated variants, constrained primitives, subtype/composition choices, nullability, examples, and invalid-state prevention.
Set up a repository for marketplace-driven AI tooling. Use when onboarding a new repo, refreshing a checked-in marketplace reference, installing core marketplace plugins, or documenting which configured marketplaces should be available by default.
Use when validation, authorization, normalization, or state checks produce facts later code must retain. Replace primitive contracts, flags, sentinel states, string protocols, and call-order conventions with proof-carrying values in any language.
Use when Kotlin work needs type-driven modeling, parse-dont-validate boundaries, semantic package layout, explicit failures, API review, or package cohesion checks.
Pkl engineering for typed configuration contracts, expressions, amendments, evaluation, formatting, tests, projects, dependencies, rendering, and packages. Use when a repository contains `.pkl` modules or `PklProject`, or when configuration behavior should be modeled and enforced with Apple Pkl.
Use when creating or validating referential plugin manifests, marketplace entries, primitive references, or payload-to-reference plugin conversions.
| name | agent-profile-authoring |
| description | Use when creating or revising standalone agent profiles, including frontmatter, triggers, prompts, tool limits, examples, and delegation checks. |
Use this skill to create independent agent profiles. A plugin may refer to an agent profile, but the agent itself must carry its role, trigger, process, tool boundaries, and output contract.
Define the delegation boundary. State what the agent owns, what it must not own, when it should trigger, and what evidence it should return.
Check existing agents.
Search source/agents/ for overlapping names, triggers, or responsibilities.
Draft the profile. Use frontmatter for stable metadata and the body for the operating prompt. Keep provider-specific fields optional unless the target runtime requires them.
Write trigger examples. Cover explicit, implicit, and proactive cases when relevant. Include examples that show when not to delegate if the boundary is easy to over-trigger.
Shape the system prompt. Give the agent a concrete role, responsibilities, process, quality standards, edge cases, and output format.
Validate and promote.
Check name format, trigger clarity, tool scope, and overlap. Add the agent to
source/adaptable.marketplace.json or a referential plugin only after it
exists as an independent primitive.
