Просматривайте и устанавливайте тысячи навыков AI Agent в каталоге Killer-Skills. Совместимо с Claude Code, Windsurf, Cursor и другими.
Use when we want to turn a just-finished Formax workflow (e.g. commands, overlays, tools, hooks, permissions, UI parity) into a reusable Codex Skill under .codex/skills, including scaffolding, guardrails, and the minimum test checklist.
Generate and maintain AGENTS.md as a living project context document by scanning the repository, discovering agents/skills, and extracting conventions. Use when initializing Codex context for a repo, refreshing stale AGENTS.md, or after significant project structure changes.
Format high-quality Git commit messages from staged or unstaged changes with stable conventions. Use when Codex is asked to create, polish, or validate commit messages, especially for Conventional Commits, commitlint-compatible repositories, squash/fixup flows, or teams that require consistent subject/body/footer structure.
Manage and guide Hikaze-Model-Manager-2 Codex project work via the .codex governance system. Use when the user says root skill or asks to start development based on the root skill, or when asked to set up or operate .codex constitution/workflows/guidelines/jobs, manage jobs/phases/tasks with Markdown checklists, or migrate project prompts from conductor/ into .codex/.
Maintain the Oris Rust agent runtime with an issue-driven GitHub workflow. Use when Codex is working in the Oris repository and needs to pick up a GitHub issue, turn the issue into scoped code changes, run Rust validation such as cargo fmt and cargo test, publish the oris-runtime crate to crates.io, close the completed issue, and continue to the next iteration.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:acp), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.