據 AlphaMoat 統計,截至 2026-10,Clawd Docs V2 累計下載 9,408 次、獲 16 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 2,929 位,在「知識管理」分類(745 個)中排名第 200 位。
列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。
| 平台 | 累計下載 | 星標 | 評論 |
|---|---|---|---|
| ClawHub ↗ | 6555 | 16 | - |
| SkillHub ↗ | 9408 | 16 | — |
各平台的計數口徑不同,統計時間不一致。
三層架構為搜尋索引(0 token)→ 快取片段(約 300-500 token)→ 按需抓取整頁(約 8-12k token),並按頁面型別設定 TTL(install/updating 1 天,gateway/channels/tools 7 天,concepts 14 天,reference 30 天)。查詢時先檢查 ~/clawd/data/docs-snippets/ 的黃金片段(覆蓋 Telegram 配置、allowFrom、OAuth 排錯、更新流程、重啟閘道器、配置基礎、Provider 配置與記憶搜尋等主題;主文不同位置給出的片段數量不一致,譯文不固定為單一數字),再查 ~/clawd/data/docs-index.json 搜尋索引(含關鍵詞與同義詞模糊匹配),再看 ~/clawd/data/docs-cache/ 整頁快取,最後才用 Clawdbot 內建 web_fetch 抓取(免費且約 400ms,替代約 $0.003/次、耗時 2-5 秒的 brightdata)。找不到內容時可用 llms.txt 兜底獲取全部文件頁清單。主文宣稱 80-90% 的查詢應能由片段回答;批次抓取約 20-30k token。索引約覆蓋 50 個核心頁面。版本為 2.2.0(frontmatter 與 changelog;主文 Version Info 表中的 2.1.0 為陳舊記錄)。
資料釋出於 2026-10-29
以下是根據技能文件生成的示例,不代表實際執行結果。
2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。
| 月份 | 累計下載 | 環比 | 星標 |
|---|---|---|---|
| 2026-10 | 9408 | — | 16 |
| 2026-09 | 6367 | — | 16 |
| 2026-08 | 6649 | +3.0% | 16 |
| 2026-07 | 6454 | +4.6% | 16 |
| 2026-06 | 6173 | +3.2% | 16 |
| 2026-05 | 5979 | — | 16 |
| 2026-03 | 5558 | — | 16 |
以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。
---
name: clawd-docs-v2
description: Smart ClawdBot documentation access with local search index, cached snippets, and on-demand fetch. Token-efficient and freshness-aware.
homepage: https://docs.clawd.bot/
metadata: {"clawdbot":{"emoji":"📚"}}
version: 2.2.0
---
# Clawd-Docs v2.0 - Smart Documentation Access
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
---
## Quick Start
### Step 1: Check Golden Snippets First
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
```
### Step 2: Search Index (if snippet doesn't exist)
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
### Step 3: Check Full Page Cache
**BEFORE fetching via brightdata**, check if the page is already cached:
```bash
# Convert path: 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
```
### Step 4: Fetch Page (only if NOT in cache)
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 ✅ |
---
## Search Index Structure
**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.
---
## TTL Strategy (Freshness)
| 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
```
---
## Common Scenarios
### "Ako nastaviť Telegram?"
1. ✅ Read `~/clawd/data/docs-snippets/telegram-setup.md`
### "allowFrom nefunguje"
1. ✅ Read `~/clawd/data/docs-snippets/telegram-allowfrom.md`
### "Token expired / oauth error"
1. ✅ Read `~/clawd/data/docs-snippets/oauth-troubleshoot.md`
### "Ako updatnúť ClawdBot?"
1. ✅ Read `~/clawd/data/docs-snippets/update-procedure.md`
### "Ako pridať nový skill?" (nie je snippet)
1. Search index → tools/skills
2. Fetch: `web_fetch({ url: "https://docs.clawd.bot/tools/skills", extractMode: "markdown" })`
### "Multi-agent routing"
1. Search index → concepts/multi-agent
2. Fetch: `web_fetch({ url: "https://docs.clawd.bot/concepts/multi-agent", extractMode: "markdown" })`
---
## Fallback: Full Index Refresh
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.
---
## Token Efficiency Guide
| 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!
---
## Data Locations
```
~/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)
```
---
## Version Info
| 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 |
---
## Changelog
### 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
### v2.1.3 (2026-01-25) - ClawdHub
- Documentation fix: check vs refresh clarification
### 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
### 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.*
透過公開搜尋URL在16個搜尋引擎(7個國內直連+9個國際)中做跨引擎檢索、結果去重與多源交叉驗證,無需API Key,內建零依賴Python指令碼。Use when 使用者要求“搜一下/查資料/多找幾個來源/核實訊息/找公眾號文章/排查報錯/找論文或開源專案”時。輸入自然語言查詢詞,輸出帶來源連結與可信度標註的結構化結果。不適用於私有資料檢索、批次抓取、需要登入後可見的內容。
透過 IMA OpenAPI 管理筆記與知識庫內容。
把長文字、文件與網頁內容壓縮成要點和關鍵詞的摘要工具。
透過“查一下、搜一下、搜尋、找一下”等自然語言檢索公開網頁,整理來源並交付橫版 PDF、Markdown 與標題連結表。支援使用者主動開啟、檢視和取消技能收藏,保留原報告取回。
規定如何為網頁請求選擇合適工具的必讀指引。
AI HOT(aihot.virxact.com)中文 AI 資訊查詢 Skill,幫助使用者獲取今日 AI 圈動態、AI 日報、AI 熱點、最新 AI 資訊以及 OpenAI、Anthropic、Google 等公司的最新發布資訊。
全球12億文獻知識庫(8千萬中文期刊可下載)——透過 SmartLib 開放平台 API 提供中外文學術文獻檢索與下載能力,覆蓋 8000 萬篇授權中文期刊全文 + 12.28 億條全球文獻後設資料(期刊 7.19 億 / 專利 2.15 億 / 會議 7155 萬 / 學位論文 2473 萬 / 標準 268 萬)。 能力:中英文關鍵詞檢索、文獻詳情、中文期刊 PDF 全文下載、外文 OA 文獻十級渠道免費下載(不消耗配額)、智慧關鍵詞擴充套件、核心期刊優先排序、相關性重排、引文追溯、分類號檢索。 配額:首次使用自動註冊,免費 100 次檢索 + 10 次下載 / 月;耗盡自動彈出方案(體驗卡 / 個人版月 / 專業版月 / 單篇下載 / 下載包),可說「升級 / 充值」喚起;企業 / 機構定製聯絡 [email protected]。 觸發:使用者表達"查論文""找文獻""檢索學術""搜期刊""查專利""找標準""下論文""寫文獻綜述""找參考文獻""查 SCI/EI"等意圖時啟用;也適用"幫我找關於 XX 的論文""寫文獻綜述""找幾篇引用支撐論點"。英文:"find papers" "search literature" "write literature review" "find supporting citations"。 呼叫前必須先用 /consume 獲取 consume_token,再憑 token 調 /search(每次計費介面呼叫都需一次 /consume)。
用 uvx 直接呼叫 markitdown,把各類檔案轉成 Markdown。
資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。