clawd-docs-v2

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Clawd-Docs v2.0 - Smart Documentation Access

Clawd-Docs v2.0 - 智能文档访问工具

This skill provides intelligent access to ClawdBot documentation with:

Local search index - instant keyword lookup (0 tokens)
Cached snippets - pre-fetched common answers (~300-500 tokens)
On-demand fetch - full page when needed (~8-12k tokens)
Freshness tracking - TTL per page type

本Skill为ClawdBot文档提供智能访问功能，包括：

本地搜索索引 - 即时关键词查询（0 Token消耗）
缓存代码片段（Golden Snippets） - 预获取的常见问题答案（约300-500 Token）
按需获取 - 需要时获取完整页面（约8-12k Token）
新鲜度追踪 - 按页面类型设置TTL（过期时间）

Quick Start

快速开始

Step 1: Check Golden Snippets First

步骤1：先检查Golden Snippets

Before fetching anything, check if a Golden Snippet exists:

bash

ls ~/clawd/data/docs-snippets/

Available snippets (check cache first!):

Snippet	Query matches
`telegram-setup.md`	"ako nastaviť telegram", "telegram setup"
`telegram-allowfrom.md`	"allowFrom", "kto mi môže písať", "access control"
`oauth-troubleshoot.md`	"token expired", "oauth error", "credentials"
`update-procedure.md`	"ako updatnuť", "update clawdbot"
`restart-gateway.md`	"restart", "reštart", "stop/start"
`config-basics.md`	"config", "nastavenie", "konfigurácia"
`config-providers.md`	"pridať provider", "discord setup", "nový kanál"
`memory-search.md`	"memory", "vector search", "pamäť", "embeddings"

Read snippet:

bash

cat ~/clawd/data/docs-snippets/telegram-setup.md

在获取任何内容之前，先检查是否存在Golden Snippets：

bash

ls ~/clawd/data/docs-snippets/

可用的代码片段（先检查缓存！）：

代码片段	匹配查询
`telegram-setup.md`	"如何设置Telegram", "telegram setup"
`telegram-allowfrom.md`	"allowFrom", "谁可以给我发消息", "access control"
`oauth-troubleshoot.md`	"token expired", "oauth error", "credentials"
`update-procedure.md`	"如何更新ClawdBot", "update clawdbot"
`restart-gateway.md`	"restart", "重启", "stop/start"
`config-basics.md`	"config", "设置", "konfigurácia"
`config-providers.md`	"添加提供商", "discord setup", "新频道"
`memory-search.md`	"memory", "vector search", "记忆", "embeddings"

读取代码片段：

bash

cat ~/clawd/data/docs-snippets/telegram-setup.md

Step 2: Search Index (if snippet doesn't exist)

步骤2：搜索索引（如果没有对应的代码片段）

Check

~/clawd/data/docs-index.json

for page suggestions.

Keyword matching:

"telegram" → channels/telegram
"oauth" → concepts/oauth, gateway/troubleshooting
"update" → install/updating
"config" → gateway/configuration

查看

~/clawd/data/docs-index.json

获取页面建议。

关键词匹配：

"telegram" → channels/telegram
"oauth" → concepts/oauth, gateway/troubleshooting
"update" → install/updating
"config" → gateway/configuration

Step 3: Check Full Page Cache

步骤3：检查完整页面缓存

BEFORE fetching via brightdata, check if the page is already cached:

bash

undefined

在通过brightdata获取之前，先检查页面是否已缓存：

bash

undefined

Convert path: concepts/memory → concepts_memory.md

转换路径：concepts/memory → concepts_memory.md

ls ~/clawd/data/docs-cache/ | grep "concepts_memory"


**If exists, read locally (0 tokens!):**
```bash
cat ~/clawd/data/docs-cache/concepts_memory.md

ls ~/clawd/data/docs-cache/ | grep "concepts_memory"


**如果存在，本地读取（0 Token消耗！）：**
```bash
cat ~/clawd/data/docs-cache/concepts_memory.md

Step 4: Fetch Page (only if NOT in cache)

步骤4：获取页面（仅当未缓存时）

Use native web_fetch tool (part of Clawdbot core - FREE and fast!):

javascript

web_fetch({ url: "https://docs.clawd.bot/{path}", extractMode: "markdown" })

Example:

javascript

web_fetch({ url: "https://docs.clawd.bot/tools/skills", extractMode: "markdown" })

web_fetch advantages:

	web_fetch	brightdata
Cost	$0 (free!)	~$0.003/call
Speed	~400ms	2-5s
Quality	Markdown ✅	Markdown ✅

使用原生的web_fetch工具（Clawdbot核心组件 - 免费且快速！）：

javascript

web_fetch({ url: "https://docs.clawd.bot/{path}", extractMode: "markdown" })

示例：

javascript

web_fetch({ url: "https://docs.clawd.bot/tools/skills", extractMode: "markdown" })

web_fetch优势：

	web_fetch	brightdata
成本	$0（免费！）	约$0.003/次调用
速度	~400ms	2-5s
质量	Markdown ✅	Markdown ✅

Search Index Structure

搜索索引结构

Location:

~/clawd/data/docs-index.json

json

{
  "pages": [
    {
      "path": "channels/telegram",
      "ttl_days": 7,
      "keywords": ["telegram", "tg", "bot", "allowfrom"]
    }
  ],
  "synonyms": {
    "telegram": ["tg", "telegrambot"],
    "configuration": ["config", "nastavenie", "settings"]
  }
}

Use synonyms for fuzzy matching.

位置：

~/clawd/data/docs-index.json

json

{
  "pages": [
    {
      "path": "channels/telegram",
      "ttl_days": 7,
      "keywords": ["telegram", "tg", "bot", "allowfrom"]
    }
  ],
  "synonyms": {
    "telegram": ["tg", "telegrambot"],
    "configuration": ["config", "nastavenie", "settings"]
  }
}

使用同义词进行模糊匹配。

TTL Strategy (Freshness)

TTL策略（新鲜度）

Page Category	TTL	Why
`install/updating`	1 day	Always current!
`gateway/*`	7 days	Config changes
`channels/*`	7 days	Provider updates
`tools/*`	7 days	Features added
`concepts/*`	14 days	Rarely changes
`reference/*`	30 days	Stable templates

Check snippet expiry:

bash

head -10 ~/clawd/data/docs-snippets/telegram-setup.md | grep expires

页面分类	TTL（天）	原因
`install/updating`	1	内容需保持最新！
`gateway/*`	7	配置可能变更
`channels/*`	7	提供商可能更新
`tools/*`	7	可能新增功能
`concepts/*`	14	很少变更
`reference/*`	30	模板稳定

检查代码片段过期时间：

bash

head -10 ~/clawd/data/docs-snippets/telegram-setup.md | grep expires

Common Scenarios

常见场景

"Ako nastaviť Telegram?"

"如何设置Telegram？"

✅ Read

~/clawd/data/docs-snippets/telegram-setup.md

✅ 读取

~/clawd/data/docs-snippets/telegram-setup.md

"allowFrom nefunguje"

"allowFrom无法正常工作"

✅ Read

~/clawd/data/docs-snippets/telegram-allowfrom.md

✅ 读取

~/clawd/data/docs-snippets/telegram-allowfrom.md

"Token expired / oauth error"

"Token过期 / OAuth错误"

✅ Read

~/clawd/data/docs-snippets/oauth-troubleshoot.md

✅ 读取

~/clawd/data/docs-snippets/oauth-troubleshoot.md

"Ako updatnúť ClawdBot?"

"如何更新ClawdBot？"

✅ Read

~/clawd/data/docs-snippets/update-procedure.md

✅ 读取

~/clawd/data/docs-snippets/update-procedure.md

"Ako pridať nový skill?" (nie je snippet)

"如何添加新Skill？"（无对应代码片段）

Search index → tools/skills

Fetch:

web_fetch({ url: "https://docs.clawd.bot/tools/skills", extractMode: "markdown" })

搜索索引 → tools/skills

获取：

web_fetch({ url: "https://docs.clawd.bot/tools/skills", extractMode: "markdown" })

"Multi-agent routing"

"多Agent路由"

Search index → concepts/multi-agent

Fetch:

web_fetch({ url: "https://docs.clawd.bot/concepts/multi-agent", extractMode: "markdown" })

搜索索引 → concepts/multi-agent

获取：

web_fetch({ url: "https://docs.clawd.bot/concepts/multi-agent", extractMode: "markdown" })

Fallback: Full Index Refresh

备选方案：完整索引刷新

If you can't find what you need:

javascript

web_fetch({ url: "https://docs.clawd.bot/llms.txt", extractMode: "markdown" })

Returns complete list of all documentation pages.

如果无法找到所需内容：

javascript

web_fetch({ url: "https://docs.clawd.bot/llms.txt", extractMode: "markdown" })

返回所有文档页面的完整列表。

Token Efficiency Guide

Token效率指南

Method	Tokens	When to use
Golden Snippet	~300-500	✅ Always first!
Search Index	0	Keyword lookup
Full Page Fetch	~8-12k	Last resort
Batch Fetch	~20-30k	Multiple related topics

80-90% of queries should be answered from snippets!

方法	Token消耗	使用场景
Golden Snippet	~300-500	✅ 优先使用！
搜索索引	0	关键词查询
完整页面获取	~8-12k	最后手段
批量获取	~20-30k	多个相关主题

80-90%的查询应该通过代码片段就能回答！

Data Locations

数据存储位置

~/clawd/data/
├── docs-index.json       # Search index
├── docs-stats.json       # Usage tracking
├── docs-snippets/        # Cached Golden Snippets
│   ├── telegram-setup.md
│   ├── telegram-allowfrom.md
│   ├── oauth-troubleshoot.md
│   ├── update-procedure.md
│   ├── restart-gateway.md
│   └── config-basics.md
└── docs-cache/           # Full page cache (future)

~/clawd/data/
├── docs-index.json       # 搜索索引
├── docs-stats.json       # 使用情况追踪
├── docs-snippets/        # 缓存的Golden Snippets
│   ├── telegram-setup.md
│   ├── telegram-allowfrom.md
│   ├── oauth-troubleshoot.md
│   ├── update-procedure.md
│   ├── restart-gateway.md
│   └── config-basics.md
└── docs-cache/           # 完整页面缓存（未来规划）

Version Info

版本信息

Item	Value
Skill version	2.1.0
Created	2026-01-14
Updated	2026-01-26
Authors	Claude Code + Clawd (collaborative)
Source	https://docs.clawd.bot/
Dependencies	web_fetch (Clawdbot core tool)
Index pages	~50 core pages
Golden snippets	7 pre-cached

项目	数值
Skill版本	2.1.0
创建时间	2026-01-14
更新时间	2026-01-26
作者	Claude Code + Clawd（协作开发）
来源	https://docs.clawd.bot/
依赖	web_fetch（Clawdbot核心工具）
索引页面数	~50个核心页面
Golden Snippets数量	7个预缓存

Changelog

更新日志

v2.2.0 (2026-01-26)

v2.2.0（2026-01-26）

Migration to web_fetch - replaced brightdata MCP with native Clawdbot tool
Benefits: FREE ($0), faster (~400ms vs 2-5s)
No external dependencies (mcporter no longer required)
Collaborative work: Claude Code 🦞 implementation, Clawd 🐾 review

迁移至web_fetch - 替换brightdata MCP为原生Clawdbot工具
优势：免费（$0）、速度更快（~400ms vs 2-5s）
无外部依赖（不再需要mcporter）
协作开发：Claude Code 🦞 实现，Clawd 🐾 审核

v2.1.3 (2026-01-25) - ClawdHub

v2.1.3（2026-01-25）- ClawdHub

Documentation fix: check vs refresh clarification

文档修复：明确检查与刷新的区别

v2.0.0 (2026-01-14)

v2.0.0（2026-01-14）

3-layer architecture: Search Index → Snippets → On-demand Fetch
Golden Snippets pre-cached for common queries
TTL-based freshness tracking
Synonym support for fuzzy matching
80-90% token reduction for common queries

三层架构：搜索索引 → 代码片段 → 按需获取
为常见查询预缓存Golden Snippets
基于TTL的新鲜度追踪
支持同义词模糊匹配
常见查询的Token消耗减少80-90%

v1.0.0 (2026-01-08)

v1.0.0（2026-01-08）

Initial release with brightdata fetch only

This skill provides smart documentation access - always cached snippets first, fetch only when necessary.

初始版本，仅支持brightdata获取

本Skill提供智能文档访问功能 - 优先使用缓存代码片段，仅在必要时才进行获取。