菜单
Use when planning a substantial change before coding — new wire fields, new persisted things, new endpoints, new persistent UI surfaces, cross-package refactors. Produces a structured plan, not code.
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
Use when working on the Hecate native desktop app in `tauri/`. Covers the Tauri 2.x Rust layer, sidecar lifecycle, platform bundling, and the gateway↔webview integration.
Use when working on the Hecate Go backend — gateway, agent runtime, providers, sandbox, storage. Keeps backend work aligned with Hecate's "operator-grade control plane, runtime-aware" thesis.
Use when working on the Hecate operator UI in `ui/`. Keeps frontend work aligned with Hecate's operator-console workflows, runtime-debugging focus, and React/Vite stack.
Use when reviewing delivery safety — env-var changes, schema migrations, deploy risk, rollback paths, observability surfaces, release notes.
Use when working in `internal/providers/` — outbound HTTP adapters to LLM upstreams (OpenAI-compat, Anthropic). Owns the api↔providers parallel-struct boundary and the seven-step "add a wire field" chain.
Use when choosing test layers, designing regression coverage, auditing test gaps, or reporting verification results. Pushes for evidence, not assumptions.
| name | hecate-architect |
| description | Use when planning a substantial change before coding — new wire fields, new persisted things, new endpoints, new persistent UI surfaces, cross-package refactors. Produces a structured plan, not code. |
Plan-shaped responses for substantial changes. The skill produces a plan, not code. Use it when "I am about to make a substantial change; I need to think before I type."
Any change that triggers a planning event in ../../core/workflow.md:
../providers/SKILL.md)./v1/... or Hecate-native /hecate/v1/...).When in doubt, default to using this skill. The cost of a brief plan is far less than the cost of an unplanned change that hits the wrong seam.
Plan first. Do not write code in this skill's response. Unless the task is trivial (typo fix, single-line dependency bump, comment touch-up), produce a plan first.
Use the canonical plan structure and anti-patterns in ../../tasks/planning.md. That doc owns the format; this skill owns when to invoke it.
The plan is the brief for a hecate-backend, hecate-ui, or hecate-providers skill turn. It should give the implementer everything they need to proceed without further context — including the verification ladder they'll run and the docs they'll update.
None for the plan itself. The plan must enumerate the verification ladder for the implementer.