菜单
Post-cargo-generate setup for a new {{project-name}} project. Walks through first-run configuration, domain replacement, and tooling bootstrap.
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
| name | template-init |
| description | Post-cargo-generate setup for a new {{project-name}} project. Walks through first-run configuration, domain replacement, and tooling bootstrap. |
| disable-model-invocation | false |
Run /template-init immediately after cargo generate completes in a new project.
Ask the user which surfaces were selected during generation (CLI / API / MCP / web). Note any surfaces that were excluded — those directories won't exist and references to them should be skipped.
The generated project contains a demo example domain. Ask the user for their first real domain name (snake_case).
Then:
crates/core/src/example.rs → crates/core/src/{domain}.rscrates/core/src/example/ → crates/core/src/{domain}/crates/app/src/cli/example.rs → crates/app/src/cli/{domain}.rs (if CLI surface)crates/app/src/api/services/example.rs → crates/app/src/api/services/{domain}.rs (if API surface)mod example / use example references in lib.rs, main.rs, and surface filescrates/app/src/mcp/ (if MCP surface)If the user doesn't have a domain name yet, skip this step and remind them to use /add-domain later.
Replace the template placeholder content with:
just bootstrap # installs cargo-nextest, lefthook, taplo, etc.
just install-hooks # wires lefthook git hooks
Invoke the sync-stack-llms subagent to analyze the actual Cargo.toml and package.json dependencies and generate any missing llms.txt reference files.
just lint # should pass on the fresh scaffold
just test # should pass
If either fails, surface the errors before proceeding.
git add -A
git commit -m "chore: initialize {{project-name}} from rust-bin template"
{{project-name}} substitution, surface file inclusion/add-domain for subsequent domainsScaffold a new domain module following the {{project-name}} spec layout. Creates all required files with correct structure and wires CLI, API, and MCP surfaces.
Specialized configuration help for Claude Code, Codex CLI, and Gemini CLI — skills, subagents, hooks, MCP servers, plugins, slash commands, permissions, settings, memory. Use whenever the user asks to add, modify, troubleshoot, or audit any agentic-CLI configuration. Trigger this skill aggressively for anything touching .claude/, .codex/, .gemini/, settings.json, config.toml, hooks.json, .mcp.json, AGENTS.md, GEMINI.md, or whenever the user mentions "Claude config", "Codex config", "Gemini config", "agent config", or any feature listed in the routing table — even if they don't explicitly ask to "configure" something.
Authoritative checklist for reviewing apps/web/ changes — fully aligned with docs/design-docs/design-system-contract.md. Covers Aurora tokens, typography ramp, elevation, radius, scrollbar, import rules, shadcn bans, TanStack Query v5, logging, and auth. Preloaded by aurora-reviewer.
Authoritative checklist for auditing parity between Claude Code, Codex CLI, and Gemini CLI configurations across skills, subagents, hooks, and MCP servers. Encodes the cross-platform mapping rules including the hook-event capability gap. Preloaded by agent-parity.
Audit the docs/references llms.txt cache for drift — stale files, orphaned entries, and (optionally) version-bumped upstream releases. Each *-llms.txt is self-describing via YAML frontmatter; this skill reads that frontmatter and cross-references it against Cargo.lock / package.json. Used by sync-stack-llms before generating new entries.
Five drift checks for detecting where the codebase has outpaced documentation — knowledge map integrity, spec.md vs xtask parity, exec-plan lifecycle drift, stale active plans, ADR coverage gaps. Preloaded by drift-detector.