agentleFS
HaroonArshad-53HaroonArshad-53/skills-for-everyone/skills/portfolio-case-study/SKILL.md

portfolio-case-study

Skill1 starsChanged 31 days agoMITView on GitHub

Turn rough notes about a finished project into a portfolio case study and a short LinkedIn or social post that proves skill with the problem, process, and result, without inventing metrics. Use when a user finishes a project and asks to add it to their portfolio, write a case study, a Behance or Dribbble description, or a LinkedIn post about their work.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the short version too: a 100-150 word LinkedIn post - hook line about the problem, 3 lines of process, the result, one lesson, and a …

    line 17
  2. Distinctive:

    Never invent client names, revenue numbers, percentages, or testimonials.

    line 21
  3. Distinctive:

    Do not reveal a client confidential details, unreleased work, or internal data.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Portfolio Case Study Builder

When to use this skill

  • A project is finished and needs to become portfolio proof
  • Updating a portfolio, Behance, Dribbble, or personal website
  • Writing a LinkedIn post about completed work without sounding boastful

Workflow

  1. Collect the raw material: client type (not name unless the user has permission), the problem, what was delivered, tools used, timeline, and any result the user can honestly state.
  2. Structure the case study: The Problem (client situation in 2 lines), My Role, The Process (3-5 steps, decisions and why), The Deliverable, The Result, What I Learned.
  3. For results: use only what the user provided. If there is no number, describe the visible outcome (the new logo stays readable at Instagram profile size) instead of inventing percentages.
  4. Write the short version too: a 100-150 word LinkedIn post - hook line about the problem, 3 lines of process, the result, one lesson, and a soft call to action.
  5. Suggest the visuals to attach: before and after, process sketch, final deliverable - in the order a scroller should see them.

Rules - never break these

  • Never invent client names, revenue numbers, percentages, or testimonials. A true small result beats a fake big one, and clients check.
  • Do not reveal a client confidential details, unreleased work, or internal data. Describe the client by type if unsure.
  • Process is the proof for beginners: clear thinking is what hires juniors, not claimed years of experience.

Output format

  • Case study - full version in the structure above, ready for portfolio or Behance
  • LinkedIn post - short version, ready to paste
  • Visuals to attach - ordered list
  • Missing proof - 1 line: what result or permission to ask the client for, if any

Example

User: Make a case study: I redesigned a bakery logo and menu cards, small local bakery, took 1 week, Illustrator, owner said customers compliment the new menu. No sales numbers.

Good output (excerpt): Result line written honestly: The owner reports customers now compliment the menu cards in-store - the previous design was text-only and hard to read at the counter. No percentage invented. The process section shows the readability decision that actually did the work.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.