Docsbot question history

Skill uglyrobot/docsbot-agent-skills/skills/docsbot-question-history

Search and fetch prior DocsBot bot questions, answers, and conversation history through a per-bot remote MCP server. Activate when a user asks to analyze support history, find past answers, review escalations, inspect unresolved questions, or reuse previous DocsBot conversations.From its SKILL.md

Install

npx -y skills add uglyrobot/docsbot-agent-skills --skill docsbot-question-history

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

2.9 KB, 535 tokens by cl100k_base, as published. Nobody here has run it

DocsBot Question History

Use this skill when working with a specific DocsBot bot's historical question and answer data through the per-bot Question History server:

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

This server gives an authorized agent a focused read-only retrieval surface over prior bot conversations:

search runs semantic search across logged questions, answers, and conversation history.
fetch retrieves a full question or conversation by ID returned from search.

Search results can include operational metadata such as whether the bot could answer, escalation state, resolved state, sentiment, and topic when that data is available.

Setup

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

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

The token can be a DocsBot API key or a DocsBot MCP OAuth token prefixed with mcp-. Question History search requires a bot with at least 5,000 logged questions.

Workflow

Identify the target DocsBot team and bot before searching.
Use search first with the user's natural-language query, support topic, customer issue, escalation phrase, or answer pattern.
Review result metadata such as couldAnswer, escalation, resolved, escalated, sentiment, and topic when present.
Use fetch for question IDs returned by search when the task needs the full conversation or exact answer history.
Summarize patterns, cite relevant prior answers, and call out limits when history is sparse or unavailable.

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, question IDs, conversation history, or support outcomes.
Respect the privacy of logged questions and conversations. Do not expose more customer data than the user needs for the task.
If the bot has fewer than 5,000 logged questions, report that Question History search is not available for that bot yet.
Successful search and fetch calls consume DocsBot AI Credits.

References

MCP client configuration

What ships with it: 2 files

64.1 KB alongside SKILL.md

assets/

icon.png63.4 KB

references/

mcp-client-config.md656 B

Gives 0 of the 12 instructions most mcp tooling skills give in 535 tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07

Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
Test servers using MCP Inspectorin 61 of 638, across 19 files
Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
Define structured output schemas where possiblein 50 of 638, across 8 files
Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
Load framework documentation using WebFetchin 45 of 638, across 3 files
Verify each evaluation answer independentlyin 45 of 638, across 3 files
Implement API client with authentication and paginationin 45 of 638, across 3 files
Define input schemas with validationin 27 of 638, across 9 files

Said here and by no other author read

identify target team and bot before searching
review available result metadata
fetch full conversation by question id when needed
summarize patterns and cite prior answers
report when question history search is unavailable

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.