Generate a polished slide deck from a rough outline or markdown

    3

    Devs and PMs lose hours hand-building PowerPoint/Google Slides for demos, design reviews, tech talks and stakeholder upd

    Free

    10 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Generate a polished slide deck from a rough outline or markdown

    Example session with this skill installed

    I need an agent context file. Scan my repo, ask me the usual onboarding questions, and generate the PROJECT_CONTEXT.md.

    • Read your context and instructions
    • Compiled the generate a polished

    I've scanned your package.json and directory tree.

    1. One-sentence project goal?
    2. Target users?
    3. Top 3 conventions to maintain?
    4. Any intentional 'weird' architecture?
    5. Areas to avoid?

    [...After answers...]

    Done. PROJECT_CONTEXT.md created with your Tailwind and Vitest rules.

    I've scanned your package.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    AI agents frequently forget your project constraints, leading to repetitive questions about your stack or code changes that violate your specific architectural decisions.

    What it does

    • Scans configuration files and directory structures to map your technical stack.
    • Interviews you about project goals, user types, and intentional technical debt.
    • Document specific "hard rules" and conventions that agents must follow.
    • Generates a standardized PROJECT_CONTEXT.md file designed for agent consumption.
    • Establishes a source of truth for in-flight features and protected directories.

    Frameworks & tools

    Works with any stack including Node.js, Python, Go, Rust, and Ruby. Recognizes tools like Next.js, FastAPI, Vite, Vitest, Ruff, and Prettier.

    Why this beats prompting it yourself

    Manually explaining a codebase in every session is slow and error-prone. This skill automates the extraction of tech specs and forces the agent to acknowledge existing patterns, ensuring consistency across different tools like Cursor, Claude Code, and Windsurf.

    Use cases

    • Bootstrapping context for a new repository to ensure early consistency.
    • Onboarding agents or human teammates to complex legacy codebases.
    • Switching between different AI coding assistants without losing project "memory".
    • Protecting sensitive architectural choices from being refactored by over-eager agents.

    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 local Python with python-pptx installed.
    • Fixed layout: complex custom branding requires manual template reuse in PowerPoint.
    • No support for live web image URLs.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    10 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 4 months ago

    • Free with an Agensi account

    Software
    Python

    Permissions

    No special permissions declared or detected

    Listed4 months ago

    What's inside

    Frequently Asked Questions

    This skill automates the creation of a 'machine-readable' source of truth for your codebase, preventing AI agents from making repetitive mistakes or suggesting architectural changes that violate your project's specific rules and tech stack.

    The generated PROJECT_CONTEXT.md is platform-agnostic, meaning it works seamlessly with popular AI tools like Cursor, Windsurf, Claude Code, GitHub Copilot, and standard LLM chat interfaces.

    This skill is language-agnostic and includes built-in recognition for modern frameworks like Next.js and FastAPI, as well as tooling like Vite, Vitest, Ruff, and Prettier to ensure your linting and testing standards are preserved.

    No coding is required to set this up; the skill performs an automated scan of your configuration files and directory structure, then uses a brief interactive interview to capture your high-level project goals and 'hard rules.'

    You receive the full automation workflow to generate and update your project context files, including lifetime access to updates as new agentic patterns and coding tools emerge.

    While the initial setup builds the foundation, you can re-run the skill whenever you make major architectural changes or add new protected directories to keep your AI agents perfectly synced with your evolving codebase.

    New in Technical Documentation

    Free