Smart ClawdBot documentation access with local search index, cached snippets, and on-demand fetch. Token-efficient and freshness-aware.
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
This skill provides intelligent access to ClawdBot documentation with:
Before fetching anything, check if a Golden Snippet exists:
ls ~/clawd/data/docs-snippets/
Available snippets (check cache first!):
| Snippet | Query matches |
|---|---|
| "ako nastaviť telegram", "telegram setup" |
| "allowFrom", "kto mi môže písať", "access control" |
| "token expired", "oauth error", "credentials" |
| "ako updatnuť", "update clawdbot" |
| "restart", "reštart", "stop/start" |
| "config", "nastavenie", "konfigurácia" |
| "pridať provider", "discord setup", "nový kanál" |
| "memory", "vector search", "pamäť", "embeddings" |
Read snippet:
cat ~/clawd/data/docs-snippets/telegram-setup.md
Check
~/clawd/data/docs-index.jsonKeyword matching:
BEFORE fetching via brightdata, check if the page is already cached:
# Convert path: concepts/memory → concepts_memory.md ls ~/clawd/data/docs-cache/ | grep "concepts_memory"
If exists, read locally (0 tokens!):
cat ~/clawd/data/docs-cache/concepts_memory.md
Use native web_fetch tool (part of Clawdbot core - FREE and fast!):
web_fetch({ url: "https://docs.clawd.bot/{path}", extractMode: "markdown" })
Example:
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 ✅ |
Location:
~/clawd/data/docs-index.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.
| Page Category | TTL | Why |
|---|---|---|
| 1 day | Always current! |
| 7 days | Config changes |
| 7 days | Provider updates |
| 7 days | Features added |
| 14 days | Rarely changes |
| 30 days | Stable templates |
Check snippet expiry:
head -10 ~/clawd/data/docs-snippets/telegram-setup.md | grep expires
~/clawd/data/docs-snippets/telegram-setup.md~/clawd/data/docs-snippets/telegram-allowfrom.md~/clawd/data/docs-snippets/oauth-troubleshoot.md~/clawd/data/docs-snippets/update-procedure.mdweb_fetch({ url: "https://docs.clawd.bot/tools/skills", extractMode: "markdown" })web_fetch({ url: "https://docs.clawd.bot/concepts/multi-agent", extractMode: "markdown" })If you can't find what you need:
web_fetch({ url: "https://docs.clawd.bot/llms.txt", extractMode: "markdown" })
Returns complete list of all documentation pages.
| 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!
~/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)
| 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 |
This skill provides smart documentation access - always cached snippets first, fetch only when necessary.
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.