菜单
Use when explicitly asked to map repo instruction boundaries, split AGENTS.md guidance, or document generated/manual edit surfaces.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | repo-instruction-topology |
| description | Use when explicitly asked to map repo instruction boundaries, split AGENTS.md guidance, or document generated/manual edit surfaces. |
Use this skill when repository instructions need to match the actual shape of a codebase. The output is a small hierarchy of scoped instruction files, not a directory-by-directory commentary layer.
AGENTS.md.Inventory the repository. Inspect top-level orchestration files, package/workspace manifests, build configs, codegen configs, CI workflows, docs configs, plugin manifests, hook configs, schema roots, and deployment surfaces.
Map working zones. Identify source roots, generated outputs, docs, tests, infra, plugins, hooks, schemas, templates, and tooling directories. Record the command or policy evidence that makes each zone distinct.
Choose instruction boundaries. Create or update the root instruction file for global rules. Add child files only where local deltas change how an agent should edit, validate, or avoid generated surfaces.
Draft scoped guidance. State scope, work commands, edit rules, source-of-truth inputs, generated boundaries, and verification steps. Keep the file short and actionable.
Verify the topology. Check that major working zones have a nearest applicable instruction file, no child file duplicates its parent, listed commands or manifests exist, and generated/manual boundaries are explicit.