Agent skill

Docsgpt Guide

by wentorai in wentorai/research-plugins

Deploy DocsGPT for private document analysis and research knowledge bases

MITAuto-check: notesKnowledge Management

Install Docsgpt Guide

skills CLI
$ npx skills add wentorai/research-plugins --skill docsgpt-guide -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wentorai/research-plugins docsgpt-guide --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tools/document/docsgpt-guide .claude/skills/docsgpt-guide && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
docsgpt-guide
GitHub stars
298
Used in
1 other repo
Token cost
~1.6k tokens
SKILL.md length
586 words
Files
1
Skills in repo
428
Repo updated
First seen
Licence
MIT

At a glance

Deploy DocsGPT for private document analysis and research knowledge bases

  • Tasks that involve Knowledge bases
  • SKILL.md covers Overview, Installation and Setup, Core Features and Research Workflow Integration, plus 2 more sections
  • Calls curl, git and docker; reaches github.com; needs API_KEY and OPENAI_API_KEY

What it does

Docsgpt Guide is an agent skill from wentorai/research-plugins. Deploy DocsGPT for private document analysis and research knowledge bases

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Knowledge bases. The repository describes itself as: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Knowledge bases

Example prompts

  • “/docsgpt-guide”

Requirements

  • Python 3
  • Docker
  • A credential in API_KEY
  • A credential in OPENAI_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • git
    • docker
    • pip
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • docs.docsgpt.cloud

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • API_KEY
    • OPENAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Docsgpt Guide loads about 1.6k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 586 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:32
    cp .env_sample .env
  • NoteMentions a .env fileSKILL.md:35
    Edit the `.env` file to configure your LLM backend:

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 586 words, ~1,594 tokens.

Download SKILL.mdSave it as .claude/skills/docsgpt-guide/SKILL.md (or your agent's skills folder).
name
docsgpt-guide
description
Deploy DocsGPT for private document analysis and research knowledge bases

DocsGPT Guide

Overview

DocsGPT is an open-source platform for building private AI-powered document analysis and question-answering systems. It uses Retrieval Augmented Generation (RAG) to enable natural language queries against your own document collections, making it particularly valuable for researchers who need to quickly extract information from large corpora of papers, technical reports, and institutional documentation.

Unlike general-purpose chatbots, DocsGPT operates on your specific documents, providing grounded answers with source citations. This is critical in academic settings where hallucinated information can derail research. The platform supports a wide range of document formats including PDF, DOCX, Markdown, HTML, and plain text, covering the formats most commonly encountered in research workflows.

With over 18,000 GitHub stars and an active development community, DocsGPT offers both self-hosted deployment for data-sensitive research environments and a cloud-hosted option for quick evaluation. The self-hosted approach ensures that proprietary research data, unpublished manuscripts, and confidential institutional documents never leave your infrastructure.

Installation and Setup

Deploy DocsGPT using Docker Compose for the simplest setup:

bash
git clone https://github.com/arc53/DocsGPT.git
cd DocsGPT

# Copy and configure environment settings
cp .env_sample .env

Edit the .env file to configure your LLM backend:

bash
# Set your LLM provider credentials
LLM_NAME=openai
API_KEY=$OPENAI_API_KEY

# Or use a local model via Ollama
LLM_NAME=ollama
OLLAMA_API_BASE=http://localhost:11434
MODEL_NAME=llama3

Launch the application:

bash
docker compose up -d

The web interface becomes available at http://localhost:5173. For production deployments behind a reverse proxy, configure the appropriate VITE_API_HOST environment variable.

For development or lightweight usage without Docker:

bash
pip install -r requirements.txt
cd application
python app.py

Core Features

Document Ingestion and Indexing: Upload documents through the web interface or API. DocsGPT processes them into vector embeddings for efficient semantic search:

bash
# Upload documents via the API
curl -X POST http://localhost:7091/api/upload \
  -F "file=@research_paper.pdf" \
  -F "name=my-research-collection"

Supported formats include PDF, DOCX, TXT, MD, HTML, EPUB, and RST files. Large documents are automatically chunked with configurable overlap to maintain context across segment boundaries.

Conversational Querying: Ask natural language questions about your documents and receive answers grounded in the source material:

bash
# Query your document collection via API
curl -X POST http://localhost:7091/api/answer \
  -H "Content-Type: application/json" \
  -d '{
    "question": "What statistical methods were used for sample size estimation?",
    "active_docs": "my-research-collection"
  }'

Each response includes source references pointing to the specific document sections used to generate the answer, enabling verification.

Multiple Knowledge Bases: Create separate document collections for different research projects, courses, or literature review topics. Switch between collections seamlessly during querying.

API Integration: The REST API enables programmatic access for building custom research tools, automated analysis pipelines, or integration with existing laboratory information management systems.

Show full SKILL.md (252 more words)Show less

Research Workflow Integration

DocsGPT serves several important functions in academic research:

Literature Synthesis: Upload all papers related to a research question and use conversational queries to identify consensus findings, methodological variations, and contradictions across the literature. This accelerates the synthesis phase of literature reviews.

Thesis and Dissertation Support: Index your entire reference collection and use DocsGPT to quickly locate specific claims, find supporting evidence for arguments, and verify that your citations accurately represent source material.

Lab Notebook Analysis: Upload experimental protocols, lab notebooks, and equipment manuals to create a searchable knowledge base. New lab members can quickly find procedures and troubleshooting information without interrupting senior researchers.

Grant Proposal Preparation: Build a collection from relevant prior work, agency guidelines, and successful proposal examples. Query this collection to identify framing strategies, required elements, and alignment between your proposed work and funder priorities.

Course Material Management: Instructors can index textbooks, lecture notes, and supplementary readings. Students can then query the collection for study assistance, with all answers grounded in approved course materials.

Configuration and Customization

Tune retrieval and generation parameters for your use case:

bash
# Environment variables for fine-tuning
CHUNKS_PER_QUERY=5          # Number of document chunks retrieved per query
CHUNK_SIZE=512              # Size of text chunks during ingestion
CHUNK_OVERLAP=64            # Overlap between adjacent chunks
MAX_TOKENS=2048             # Maximum response length
TEMPERATURE=0.1             # Lower values for more factual responses

For academic use, keep temperature low (0.1-0.3) to prioritize factual accuracy over creative responses. Increase CHUNKS_PER_QUERY when questions require synthesizing information from multiple sections of a document.

Custom embeddings models can be configured for domain-specific terminology. If your research involves highly specialized vocabulary (medical terminology, chemical nomenclature), consider using domain-adapted embedding models for improved retrieval accuracy.

References

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tools/document/docsgpt-guide of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Docsgpt Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Docsgpt Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Docsgpt Guide this skillwentorai/research-plugins2981 repos~1.6kAutomated safety check: NotesMIT
Solidworks Designhashgraph-online/awesome-codex-plugins1.2k—~1.1kAutomated safety check: PassApache-2.0
Learn From Materialsdmoshehun-prog/learn-from-materials902—~7.9kAutomated safety check: PassMIT
Youtube FetcherJimmySadek/youtube-fetcher-to-markdown485—~1.8kAutomated safety check: PassMIT
Incident Alert Ticketslangfuse/langfuse35k—~1.6kAutomated safety check: PassCustom licence
Playbook Lookuppapadopouloskyriakos/agentic-chatops107—~363Automated safety check: NotesNone

Similar skills

  • Solidworks Design

    hashgraph-online/awesome-codex-plugins

    Plan, create, modify, inspect, repair, validate, save, and export SolidWorks parts, assemblies, and drawings.

    1.2k GitHub stars~1.1k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Learn From Materials

    dmoshehun-prog/learn-from-materials

    Turns books, PDFs, slides and web pages into a source-grounded knowledge base and an interactive learning page in English or Chinese, with quizzes, relationship maps and reusable methodology notes.

    902 GitHub stars~7.9k tokensUpdated 6 days ago
    Knowledge ManagementAuto-check passed
  • Youtube Fetcher

    JimmySadek/youtube-fetcher-to-markdown

    Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source…

    485 GitHub stars~1.8k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Incident Alert Tickets

    langfuse/langfuse

    Read and record root causes in the Linear incident-alert knowledge base.

    35k GitHub stars~1.6k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Playbook Lookup

    papadopouloskyriakos/agentic-chatops

    Query past incident resolutions from the knowledge base. An agent skill from papadopouloskyriakos/agentic-chatops.

    107 GitHub stars~363 tokensUpdated yesterday
    Knowledge ManagementAuto-check: notes
  • Knowledge Base Design

    revfactory/harness-100

    Knowledge base design guide. An agent skill from revfactory/harness-100.

    1.3k GitHub stars~897 tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check passed

More from wentorai/research-plugins

All 428 skills in this repo
  • Abstract Writing Guide

    wentorai/research-plugins

    Craft structured research abstracts that maximize clarity and journal acceptance

    298 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Academic Citation Manager

    wentorai/research-plugins

    Manage academic citations across BibTeX, APA, MLA, and Chicago formats

    298 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed
  • Academic Paper Summarizer

    wentorai/research-plugins

    Summarize academic papers with structured extraction of key elements

    298 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Academic Study Methods

    wentorai/research-plugins

    Evidence-based study techniques for academic learning and retention

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Academic Tone Guide

    wentorai/research-plugins

    Adjust writing tone and register for academic audiences and venues

    298 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Academic Translation Guide

    wentorai/research-plugins

    Academic translation, post-editing, and Chinglish correction guide

    298 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Questions about Docsgpt Guide

What does Docsgpt Guide do?

Deploy DocsGPT for private document analysis and research knowledge bases. Docsgpt Guide is an agent skill from wentorai/research-plugins.

When should I use Docsgpt Guide?

Docsgpt Guide fits situations like: tasks that involve Knowledge bases.

How do I install Docsgpt Guide in Claude Code?

Run `npx skills add wentorai/research-plugins --skill docsgpt-guide -a claude-code`. Or copy the skill folder (skills/tools/document/docsgpt-guide in wentorai/research-plugins) into .claude/skills/docsgpt-guide in your project. Claude Code loads it when a task matches its description.

How do I install Docsgpt Guide in Codex?

Run `npx skills add wentorai/research-plugins --skill docsgpt-guide -a codex`. Or copy the skill folder (skills/tools/document/docsgpt-guide in wentorai/research-plugins) into .agents/skills/docsgpt-guide in your project. Codex loads it when a task matches its description.

Can I use Docsgpt Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wentorai/research-plugins --skill docsgpt-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docsgpt-guide, .gemini/skills/docsgpt-guide, .github/skills/docsgpt-guide and .opencode/skills/docsgpt-guide in your project.

What does Docsgpt Guide need to run?

Going by SKILL.md and its folder, Docsgpt Guide needs the command-line tools its instructions call (curl, git, docker, pip and python) and credentials named API_KEY and OPENAI_API_KEY. Our summary lists: Python 3; Docker; A credential in API_KEY; A credential in OPENAI_API_KEY.

Does Docsgpt Guide access the network?

SKILL.md names 2 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: docs.docsgpt.cloud. This is read from the text; nothing was executed.

Is Docsgpt Guide safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Docsgpt Guide use?

Docsgpt Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Docsgpt Guide use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Docsgpt Guide?

Skills that share tags, products or a category with Docsgpt Guide: Solidworks Design (hashgraph-online/awesome-codex-plugins, 1.2k stars), Learn From Materials (dmoshehun-prog/learn-from-materials, 902 stars), Youtube Fetcher (JimmySadek/youtube-fetcher-to-markdown, 485 stars) and Incident Alert Tickets (langfuse/langfuse, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Docsgpt Guide?

wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 428 skills in this directory. The repository was last updated on June 19, 2026.

Source: wentorai/research-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.