- Home
- Skills
- Technical Documentation
- research report
More screenshots
Works with the AI Agents you already use
research report
Turn code analysis and session research into professionally typeset PDF reports and technical design documents.
$35
research report
Example session with this skill installed
Document this repository for my manager. Focus on the high-level design and dependencies. Make it a standard 3 to 5 page report.
- Read your context and instructions
- Compiled the research report
- Generated the document
I have completed the repository scan and drafted the High-Level Design report. I analyzed the core service architecture, dependency tree, and entry points. The report includes a KPI section for code coverage and a visual representation of the module hierarchy.
Technical Report: Architecture Overview
File Path: report/architecture-overview.pdf
| Component | Responsibility | Primary Dependencies |
|---|---|---|
| API Gateway | Request routing and auth | FastAPI, JWT |
| Order Service | Transaction logic | SQLAlchemy, PostgreSQL |
| Worker Node | Async task processing | Celery, Redis |
| Fact Sheet | Raw data extraction | repo_scan.py |
Executive Summary preview:
The system is built on a microservices architecture using Python 3.10. The core logic is decoupled from the transport layer, allowing for independent scaling of the Order Service. Current test coverage stands at 84%, with identified gaps in the asynchronous worker error handling.
Next steps
- Review the generated PDF at
report/architecture-overview.pdfto verify the module diagram layout. - If you need to adjust the text, edit
report/architecture-overview.mdand I can rebuild the PDF. - I can now proceed to generate the Low-Level Design for the
Order Servicemodule if required.
architecture-overview.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
When technical investigations or repository audits stay trapped in a chat history, knowledge is lost and stakeholders stay out of the loop. This skill converts session research and codebase analysis into professional, typeset PDF reports. It eliminates the friction of manual documentation by scanning repositories, organizing research flows, and rendering structured documents with cover pages, tables of contents, and data visualizations.
What it does
- Repository Scanning scans codebases to extract facts on languages, dependencies, and architecture.
- Research Reconstruction tracks questions, sources, and dead ends from the current session.
- PDF Rendering builds styled documents with cover pages, numbered sections, and KPI callouts.
- Visual Data Integration generates charts and Markdown tables to illustrate technical findings.
- Reference Management automatically logs and cites external sources and documentation.
How it works
- Settle the Brief by defining report length, target audience, and subject scope.
- Gather Evidence using the repository scanner and logging session research steps.
- Plan the Storyline to draft a sequence of headings and visual assets based on the evidence.
- Build and Preview the PDF using the ReportLab renderer and page preview tools to ensure layout quality.
Frameworks & tools
The skill requires Python 3.9+ and uses reportlab for PDF generation, matplotlib for charts, pygments for code highlighting, and pymupdf for page previews.
Why this beats prompting it yourself
Generic prompts often produce unstructured, conversational text that fails as a formal document. This skill uses dedicated scripts for repo scanning and professional typesetting, ensuring reports follow strict structural templates for HLDs, LLDs, and audits.
Use cases
- Codebase Handover documenting architecture and dependencies for new developers.
- Research Summary compiling session investigations into a shareable stakeholder report.
- Technical Audits identifying performance bottlenecks or security gaps with supporting data.
- Design Documentation creating high-level or low-level design PDFs directly from the source.
Known limitations
The PDF renderer does not support SVG images. Users must have Python and required libraries installed in the environment to build the final document.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.
Requires Python 3.9+ and reportlab. SVG images not supported; use PNG. Reports are strictly one-pagers or 3 to 5 page documents.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Software
Node.js
Python