claude-mega-brain
OKF knowledge navigation. ALWAYS use this skill the moment a `<mega-brain>` block appears in session context — it means the project has documented concepts and you must consult them before answering questions about data, schemas, metrics, APIs, or systems. Also trigger when the user asks about a table, column, metric definition, service, or API endpoint and there's any chance it's documented in the project. When in doubt, read the file directly.
DeepseekModel
官方收录技能
质量 优秀 · 78
v1.0.0
获取
https://deepseekmodel.com/api/download.php?id=guhcostan-claude-mega-brain-skills-claude-mega-brain-skill-md&format=skill
下载 .skill
标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name claude-mega-brain description OKF knowledge navigation. ALWAYS use this skill the moment a `<mega-brain>` block appears in session context — it means the project has documented concepts and you must consult them before answering questions about data, schemas, metrics, APIs, or systems. Also trigger when the user asks about a table, column, metric definition, service, or API endpoint and there's any chance it's documented in the project. When in doubt, read the file directly. claude-mega-brain — OKF Knowledge Navigator When <mega-brain> context is present, the project has OKF-documented concepts — any Markdown file with type: in its YAML frontmatter. These are the authoritative source for domain knowledge: exact schemas, metric formulas, API contracts, runbooks, business definitions. Answers from the knowledge base beat answers from training data. What OKF files look like Any .md file anywhere in the project with YAML frontmatter containing type: : --- type: BigQuery Table title: Orders description: One row per completed customer order. resource: https://... tags: [ sales , revenue ] timestamp: 2026-06-29T00:00:00Z --- # Schema | Column | Type | Description | ... No dedicated folder required. The file can live in docs/ , wiki/ , project root, anywhere. Navigation Read the file — paths in <mega-brain> are relative to the project root; use the Read tool directly Follow links — [text](rel-path.md) links in the body point to related concepts; read them log.md — chronological changelog; last 3 entries are injected automatically Linked concepts auto-surface — after you read an OKF file, linked concept summaries appear via PostToolUse hook When to proactively read files User asks about a data source, table, column, or metric — check <mega-brain> index first Before writing SQL, queries, or code that touches project data When a business term is ambiguous — OKF has the canonical definition When the user says "check the knowledge base", "what do we know about X", or "olha no okf" If <mega-brain> context is missing No OKF concepts found in the project yet. Suggest: /mega-brain:init — creates index.md and log.md to get started /mega-brain:migrate — scans existing docs and generates OKF files automatically
Agent 识别该技能的关键词,点击任意一个即可复制。
该技能未提供触发词。
下载的 .skill 包内含以下字段。
| 字段 | 说明 |
|---|---|
| format | 格式标识(skill/v1) |
| skill_id | 技能唯一 ID |
| name | 技能名称 |
| version | 版本号 |
| description | 技能描述 |
| category | 所属分类(数组) |
| trigger_words | 触发词列表 |
| tags | 标签列表 |
| source | 来源标识 |
| source_url | 来源链接(本页地址) |
| exported_at | 导出时间(每次下载生成) |
| system_prompt | 系统提示词正文 |
| model_config | 模型参数:provider / model / temperature / max_tokens / top_p |
| examples | 示例 |
| install_guide | 各平台导入说明(Coze / Dify / Claude / 自定义框架) |