Instructions file CodexOpenCode
Instructions for idaibin/rustzen-admin, covering repository rules, source of truth, reading order, boundaries and working rules.
Instructions file CodexOpenCode
Instructions for idaibin/rustzen-admin, covering repository rules, source of truth, reading order, boundaries and working rules.
Instructions file CodexOpenCode
Instructions for idaibin/skills, covering agent instructions, task routing, repository work rules, project structure and skill validation.
Instructions file
Instructions for idaibin/skills, a project described as: Independent Agent Skills for repository analysis, planning, implementation, review, delivery, design, and runtime verification.
Skill Claude CodeCodex
Use when the user requests a package or named external-AI result for review, research, cross-review/互审, final-result retention, image work, or an exact saved user instruction such as 进行三方会审; also handles legacy ask-chatgpt wording, but do not use when Codex or an available host tool can complete the result directly.
Skill Claude CodeCodex
Use when a known frontend surface needs a scoped, read-only audit of selected architecture, reuse, data/UI contract, build/tooling, accessibility, performance, selected-source visual fidelity, or desktop-boundary profiles; use repo-review when a Worktree or immutable change basis needs coordination.
Skill Claude CodeCodex
Use when a known Java source surface or Java-owned Spring/build configuration needs a scoped, read-only audit of selected architecture, API/security, transaction, persistence, concurrency, integration, performance, or migration risks; not for non-Java JVM semantics, and use repo-review when a Worktree or immutable…
Skill Claude CodeCodex
Use when a Rust workspace or known Rust surface needs a scoped, read-only audit of selected architecture, ownership, error, concurrency, performance, persistence, or unsafe-boundary risks; use repo-review when a Worktree or immutable change basis needs coordination.
Skill Claude CodeCodex
Use when an authorized frontend change must be implemented or refactored; owns frontend source edits and risk-matched validation, not audit-only work, UI specification, browser/client operation, or Git delivery.
Skill Claude CodeCodex
Use when Java source or Java-owned Maven/Gradle configuration must be implemented, migrated, or refactored across Spring services, HTTP/security boundaries, explicit code-first or contract-first OpenAPI, persistence, transactions, messaging, scheduling, caches, tests, or configuration; owns source edits and…
Skill Claude CodeCodex
Use when a Rust source change must be implemented, ported, or refactored across APIs, crates, services, CLIs, async, persistence, unsafe or FFI boundaries, tests, or docs; owns source edits and validation, not audit-only, review-only, or Git-delivery work.
Skill Claude CodeCodex
Use when an authorized non-browser TypeScript or JavaScript source change must be implemented or refactored in a Node.js, Bun, or Deno service, API, CLI, MCP server, worker, library, or engineering script; owns source edits and validation, not browser UI, audit-only, review-only, or Git-delivery work.
Skill Claude CodeCodex
Use when shared business terms, meanings, rules, lifecycle conflicts, or domain boundaries are ambiguous across product work and must be resolved before specification or implementation; route feature-local behavior and acceptance to product-spec.
Skill Claude CodeCodex
Use when drafting, rewriting, proofreading, diagnosing, or adapting source-grounded prose, especially technical articles, essays, tutorials, product notes, and social posts, while preserving facts, attribution, uncertainty, voice, and meaning. Supports private English-first reasoning for Chinese finals; not…
Skill Claude CodeCodex
Use when directly operating or verifying a specified page, capturing same-state visual/computed evidence, or gathering isolated browser-layer evidence, especially when existing login state, tabs, downloads, or non-interrupting background operation matter; require a verified target and proven capability, not…
Skill Claude CodeCodex
Use when directly operating or verifying a specified real desktop client, or gathering evidence for an isolated client-layer failure; require a verified target, window, and capability, not browser-page verification, source changes, or cross-system diagnosis.
Skill Claude CodeCodex
Use when an ambiguous product feature, new product boundary, named product fact source, or authorized product-document rebuild must become the smallest current implementation-ready specification; owns product decisions and terminal product artifacts, not shared domain-language/lifecycle conflicts, selected-source UI…
Skill Claude CodeCodex
Use when reviewed repository changes are explicitly authorized for staging, commit, push, branch integration, synchronization, cleanup, or ref proof; owns Git mutation and stops before pull-request creation.
Skill Claude CodeCodex
Use when a Git or non-Git workspace needs a machine-queryable repository asset scan, impact/relationship query, coverage or drift check, or an optional derived navigation view; not for task-local discovery, source changes, repository-guidance authoring, or change review.
Skill Claude CodeCodex
Use when Worktree changes or a fixed snapshot/range need coordinated read-only Standards and Spec findings, documentation-authority review, completed provider-evidence integration, or selected-source visual-completion review; use audit- for bounded domain audits and a host security workflow for security-only review.
Skill Claude CodeCodex
Use when a source-grounded candidate visual direction needs a local review spec and complete generation prompt, or a selected visual source or accepted UI surface must become a traceable Feature Spec or adopted Google DESIGN.md contract; route external-AI sending to ask-ai, visual generation to the host design…