Docsbot documentation search

Skill uglyrobot/docsbot-agent-skills/skills/docsbot-documentation-search

Search and fetch a DocsBot bot's indexed documentation, knowledge base, and training sources through a per-bot remote MCP server. Activate when a user asks to use an agent to answer from, inspect, retrieve, or cite content already indexed in a specific DocsBot bot.From its SKILL.md

Install

npx -y skills add uglyrobot/docsbot-agent-skills --skill docsbot-documentation-search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.8 KB, 515 tokens by cl100k_base, as published. Nobody here has run it

DocsBot Documentation Search

Use this skill when working with a specific DocsBot bot's indexed training data through the per-bot Documentation server:

https://api.docsbot.ai/teams/{teamId}/bots/{botId}/mcp/

This server gives an authorized agent a focused read-only retrieval surface over the bot's indexed sources:

search runs hybrid semantic and keyword search across the bot's indexed documentation, website pages, help center articles, files, and other training sources.
fetch retrieves the full source content for an ID returned by search when full-document retrieval is available for that source.

Setup

Configure the MCP server with the DocsBot team ID, bot ID, and a Bearer token:

{
  "mcpServers": {
    "docsbot-docs": {
      "url": "https://api.docsbot.ai/teams/{teamId}/bots/{botId}/mcp/",
      "headers": {
        "Authorization": "Bearer <TOKEN>"
      }
    }
  }
}

The token can be a DocsBot API key or a DocsBot MCP OAuth token prefixed with mcp-. Documentation search is available on Standard plans and above.

Workflow

Identify the target DocsBot team and bot before searching.
Use search first with the user's natural-language query or a concise keyword query.
If the bot uses retriever tags, pass tags and include_untagged only when the user or task clearly calls for a scoped search.
Use fetch for source IDs returned by search when the task needs exact source text, broader context, or citations.
Answer from retrieved content and mention gaps when the indexed sources do not contain enough evidence.

Constraints

Do not use this skill for DocsBot account administration; use DocsBot Administration for teams, bots, sources, settings, members, integrations, or billing.
Do not invent team IDs, bot IDs, source IDs, tags, or source content.
Treat fetch failures on older sources as a data freshness issue; the source may need to be refreshed in DocsBot before full-document retrieval is available.
Do not expose API keys, OAuth tokens, or private indexed content beyond what is necessary for the user's task.
Successful search and fetch calls consume DocsBot AI Credits.