bleu
当开发者希望在编写任何代码之前,把想法转化为完整、可投入生产、端到端的系统方案时,使用此技能。触发语包括“规划这个系统”“为……设计架构”“帮我做蓝图”“对 X 做深度规划”“把这个想法拆成组件”“展开为行动点”“完整实施计划”,或用户粘贴项目想法并希望梳理出架构、组件、流水线和文件级执行方案时。口语化说法也会触发:“帮我从头到尾想清楚”“先规划再写代码”。还涵盖活工作区模式:自我改进的知识库、带审计智能体的反思循环、四智能体团队、schema 即代码、wiki 健康度评分。**恢复触发语**:“我们上次停在哪里”“继续这个计划”“恢复我的蓝图”——通过 SESSION.md/NEXT.md/decisions/ 从磁盘重新加载状态。每次调用都必须进行网络调研。
机器翻译查看英文原文
Use this skill whenever a developer wants to turn an idea into a complete, production-ready, end-to-end system plan BEFORE writing any code. Trigger on 'plan this system', 'design the architecture for', 'help me blueprint', 'deep plan for X', 'break this idea into components', 'expand into action points', 'full implementation plan', or when the user pastes a project idea wanting architecture, components, pipelines, and file-level execution mapped out. Casual phrasing also triggers: 'help me think this through end-to-end', 'plan before coding'. Also covers living-workspace patterns: self-improving knowledge bases, reflection loops with auditor agents, four-agent teams, schema-as-code, wiki health scoring. **Resume triggers**: 'where did we leave off', 'continue this plan', 'resume my blueprint' - rehydrates state from disk via SESSION.md/NEXT.md/decisions/. Web research is mandatory every invocation.
适用对象:学习与科研。自动收录 · 待核查。
原作者说明节选
从固定版本的 SKILL.md 提取,保留原文语言。以下内容属于作者说明,本站尚未验证安装、兼容或运行结果。
查看英文原文
原文涵盖的主题
- Bleu
- Why this skill exists
- Operating principles
- The workspace
- The phased workflow
- Phase 0 - Intake and framing
- Phase 1 - Initial research pass (web + code, if a codebase exists)
- Phase 2 - Vision, architecture, pipelines
Turn an idea into a fully thought-through, deeply structured system plan - from architecture down to file-level execution - before any code is written. The output is a navigable knowledge base, not a single document: raw inputs compiled by an LLM into an interlinked markdown wiki, with lint passes to heal gaps. No RAG, no vector store, no embeddings - the whole plan fits in a modern context window and every claim is traceable to a file a human can open, edit, or delete. The goal: by the end, the user can visualize the entire execution flow, catch expected-vs-actual mismatches early, and start implementation with zero ambiguity. Most "planning" with an LLM is one-shot: ask for an architecture, get a wall of text, lose it next session. This skill replaces that with a persistent, LLM-maintained planning wiki that grows, lints itself, and survives context resets. It's deliberately heavy on structure because the failure mode of light planning is discovering the architectural hole in week three. The strongest single argument for the skill, worth memorizing: The tedious part of maintaining a knowledge base is not the reading or the thinking - it's the bookkeeping. Updating cross-reference
这里只展示节选,请以完整原文和当前要求为准。
- 来源仓库
- davila7/claude-code-templates
- 源文件
- cli-tool/components/skills/development/bleu/SKILL.md
- 固定版本
- 21be197f100a12b8d0dd9a211cc244c8179f84d3
来源与内容状态
本条为自动发现的元数据,尚未完成人工文档核查;适用性与运行结果待核查。
原作者:davila7/claude-code-templates · 原作者仓库元数据。文档核查:未核查。最近来源检查:2026-11-09T14:01:44.114Z。
分类由名称、说明与路径规则生成,分类不代表已核实适配。
许可与权利归属
MIT。第三方内容及版权归原作者,使用条件以原文为准。
许可原文 ↗本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。
限制与注意事项
- 元数据收录不代表本站已经安装、适配、实测或进行安全审查。