Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    portfolio harness

    0

    Generates evidence-based technical portfolios for student developers via structured interviewing and PDF automation.

    Free

    8 usesSecurity scanned
    portfolio harness

    portfolio harness

    Example session with this skill installed

    I want to create a portfolio for a Junior Backend Developer role. I have three projects on GitHub: a chat app, a weather API, and a CLI tool. Help me start the interview and collect facts.

    • Read your context and instructions
    • Compiled the portfolio harness

    Summary

    Reviewed the three projects you listed and found that none of them has a recorded metric yet. Before anything goes into the portfolio, I need facts from you — I won't fill in numbers you haven't measured.

    Fact check

    ProjectWhat's confirmedWhat's missing
    Chat appStack: Node.js, Socket.io (from package.json)Your role, the hardest problem, any measured result
    Weather APIStack: FastAPI, PostgreSQL (from requirements.txt)Why caching was added, before/after numbers
    CLI toolStack: Go (from go.mod)Who used it, what it replaced

    Interview — round 1

    1. Chat app: Was this a team project? Which parts did you build yourself?
    2. Chat app: What broke or got slow, and how did you notice?

    Weather API: Did you measure anything before and after a change (response time, external calls, errors)? If not, can you run a quick test now?
    4. CLI tool: Is it used by anyone besides you?

    If you don't have a number for something, say so — I'll describe it without a metric rather than guess one.

    Next steps

    • Answer the four questions above (rough answers are fine).
    • I'll save confirmed facts to records/ and only then move to layout design.
    Node.js, Socket.io (from package.json

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

    About this skill

    Student portfolios often suffer from vague claims, missing metrics, and poor layout. This skill enforces a rigorous, evidence-based workflow to transform raw project data into a professional A4 PDF portfolio. It prioritizes technical decision-making and verified results over generic descriptions, ensuring every project entry stands up to recruiter scrutiny.

    What it does

    • Evidence-based auditing identifies gaps in existing project records to ensure every claim is backed by facts.
    • Structured interviewing extracts specific technical trade-offs, individual contributions, and measurable outcomes.
    • Visual analysis critiques provided design references or proposes readable, tech-focused layouts.
    • Automated PDF generation builds the final document using internal scripts for layout and image verification.
    • Quality assurance review checks the final PDF for text readability, page overflow, and factual consistency.

    How it works

    1. Assessment: Inspects existing project folders or resumes to determine what can be reused.
    2. Fact Collection: Executes a targeted interview to fill information gaps regarding roles and results.
    3. Design Selection: Analyzes design references or proposes A4-optimized structures.
    4. Build: Runs make_pdf.py and measure.js to generate and validate the document.
    5. Review: Audits the output against professional criteria to fix layout or content issues.

    Frameworks & tools

    Uses Python for PDF generation and image checking, Node.js for layout measurement, and Markdown for intermediate record keeping.

    Why this beats prompting it yourself

    Generic prompts often hallucinate achievements or use flowery language that recruiters ignore. This skill uses a multi-stage verification process and specialized scripts to ensure the output is technically accurate, properly formatted for A4, and free of layout errors.

    Use cases

    • Converting a messy GitHub profile into a structured PDF for internship applications.
    • Improving an existing portfolio by adding technical depth and trade-off analysis.
    • Preparing for technical interviews by documenting project challenges and metrics.

    Known limitations

    Requires a local environment capable of running Python and Node.js scripts. PDF generation depends on specific bundled scripts and local file system access.

    Requires Python and Node.js runtimes to execute bundling scripts. Output is optimized for A4 PDF format. Korean is the default language unless specified.

    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 any payment.

    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

    8 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Requires

    Python 3
    Node.js
    macOS
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Terminal runs the bundled make_pdf.py, check_images.py and measure.js. File read is used to inspect existing project folders and resumes; file write saves interview records and the generated PDF.

    Listed29 days ago

    What's inside

    Frequently Asked Questions

    Generic AI prompts often create "fluff" or hallucinated results; this skill uses a structured interviewing process and specialized layout scripts to ensure every project claim is backed by technical evidence and formatted perfectly for recruiters.

    You will receive the structured interview logic, the Markdown-to-PDF engine, Python/Node.js scripts for layout validation, and A4-optimized design templates specifically tailored for technical roles.

    The skill requires a local environment capable of running Python and Node.js to execute the automated PDF generation and visual measurement scripts included in the package.

    Yes, the skill is designed to audit your existing GitHub repositories or project folders, identifying missing metrics and technical gaps before the writing process begins.

    While the logic is optimized for technical depth, the final PDF generation scripts are set to standard A4 dimensions, ensuring your portfolio is print-ready and compatible with common applicant tracking systems (ATS).