先看看示例
作者提供的示例，实际效果取决于你的输入和使用工具。
输入
为聊天机器人项目生成计划：把 LLM 供应商抽取为插件系统，接口设计步骤用最强模型，各供应商实现步骤并行。
输出
预期交付：plans/ 目录下的 Markdown 计划文件，含步骤、依赖顺序、验证命令与退出标准（编辑说明，非实际运行结果）
方法说明
--- name: blueprint description: "Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects: one-PR-sized steps with self-contained context briefs, dependency graph with parallel-step detection, adversarial review gate, and plan mutation protocol. Use when planning a large feature, refactor, or roadmap that spans multiple PRs or sessions; not for single-PR tasks or when the user says \"just do it\"." metadata: origin: community --- # Blueprint — Construction Plan Generator Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold. ## When to Use - Breaking a large feature into multiple PRs with clear dependency order - Planning a refactor or migration that spans multiple sessions - Coordinating parallel workstreams across sub-agents - Any task where context loss between sessions would cause rework **Do not use** for tasks completable in a single PR, fewer than 3 tool calls, or when the user says "just do it." ## How It Works Blueprint runs a 5-phase pipeline: 1. **Research** — Pre-flight checks (git, gh auth, remote, default branch), then reads project structure, existing plans, and memory files to gather context. 2. **Design** — Breaks the objective into one-PR-sized steps (3–12 typical). Assigns dependency edges, parallel/serial ordering, model tier (strongest vs default), and rollback strategy per step. 3. **Draft** — Writes a self-contained Markdown plan file to `plans/`. Every step includes a context brief, task list, verification commands, and exit criteria — so a fresh agent can execute any step without reading prior steps. 4. **Review** — Delegates adversarial review to a strongest-model sub-agent (e.g., Opus) against a checklist and anti-pattern catalog. Fixes all critical findings before finalizing. 5. **Register** — Saves the plan, updates memory index, and presents the step count and parallelism summary to the user. Blueprint detects git/gh availability automatically. With git + GitHub CLI, it generates full branch/PR/CI workflow plans. Without them, it switches to direct mode (edit-in-place, no branches). ## Examples ### Basic usage ``` /blueprint myapp "migrate database to PostgreSQL" ``` Produces `plans/myapp-migrate-database-to-postgresql.md` with steps like: - Step 1: Add PostgreSQL driver and connection config - Step 2: Create migration scripts for each table - Step 3: Update repository layer to use new driver - Step 4: Add integration tests against PostgreSQL - Step 5: Remove old database code and config ### Multi-agent project ``` /blueprint chatbot "extract LLM providers into a plugin system" ``` Produces a plan with parallel steps where possible (e.g., "implement Anthropic plugin" and "implement OpenAI plugin" run in parallel after the plugin interface step is done), model tier assignments (strongest for the interface design step, default for implementation), and invariants verified after every step (e.g., "all existing tests pass", "no provider imports in core"). ## Key Features - **Cold-start execution** — Every step includes a self-contained context brief. No prior context needed. - **Adversarial review gate** — Every plan is reviewed by a strongest-model sub-agent against a checklist covering completeness, dependency correctness, and anti-pattern detection. - **Branch/PR/CI workflow** — Built into every step. Degrades gracefully to direct mode when git/gh is absent. - **Parallel step detection** — Dependency graph identifies steps with no shared files or output dependencies. - **Plan mutation protocol** — Steps can be split, inserted, skipped, reordered, or abandoned with formal protocols and audit trail. - **Zero runtime risk** — Pure Markdown skill. The entire repository contains only `.md` files — no hooks, no shell scripts, no executable code, no `package.json`, no build step. Nothing runs on install or invocation beyond Claude Code's native Markdown skill loader. ## Installation This skill ships with ECC. No separate installation is needed when ECC is installed. ### Full ECC install If you are working from the ECC repository checkout, verify the skill is present with: ```bash test -f skills/blueprint/SKILL.md ``` To update later, review the ECC diff before updating: ```bash cd /path/to/ECC git fetch origin main git log --oneline HEAD..origin/main # review new commits before updating git checkout <reviewed-full-sha> # pin to a specific reviewed commit ``` ### Vendored standalone install If you are vendoring only this skill outside the full ECC install, copy the reviewed file from the ECC repository into `~/.claude/skills/blueprint/SKILL.md`. Vendored copies do not have a git remote, so update them by re-copying the file from a reviewed ECC commit rather than running `git pull`. ## Requirements - Claude Code (for `/blueprint` slash command) - Git + GitHub CLI (optional — enables full branch/PR/CI workflow; Blueprint detects absence and auto-switches to direct mode) ## Source Inspired by antbotlab/blueprint — upstream project and reference design.