agentleFS
nishant-Tiwari24nishant-Tiwari24/cracked/skills/profile/make-it-hireable/SKILL.md

make-it-hireable

Skill5 starsChanged 8 days agoMITView on GitHub

Upgrade a student or college project into something that impresses interviewers by adding what real engineering teams expect (README, tests, CI, env config, error handling, linting, deployment, a fixed security flaw) in small, reviewed steps on a separate branch. Use when the user wants to improve a project for their resume, make a project production-ready or interview-ready, clean up a college project, or "make my project look professional".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call the Skill tool with "cracked-profile" (target role shapes priorities: a backend role cares about APIs, tests and DB.

    line 12
  2. Distinctive:

    Check git status. If there are uncommitted changes, stop and ask them to commit or stash first.

    line 14
  3. Very specific:

    Read the project: manifests, entry points, structure, config, tests, CI, deploy files, README.

    line 18
  4. Very specific:

    Create a branch: git checkout -b hireable/<short-name>.

    line 26
  5. Distinctive:

    Verify it actually works: run the tests, build, lint, and start the app if feasible.

    line 29
  6. Very specific:

    Commit with a clear conventional message (test: add integration tests for cart API).

    line 30

≈ “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

Make it hireable

The gap between a "college project" and "someone who can work on our codebase" is usually the same 8–10 things. This skill closes that gap in the candidate's real project, with them in the loop, so they can explain every change in an interview.

0. Setup

  1. Call the Skill tool with "cracked-profile" (target role shapes priorities: a backend role cares about APIs, tests and DB; frontend about performance, accessibility and UX).
  2. Confirm the project is the current directory and is a git repo. If it isn't a git repo, offer git init plus an initial commit first, so every change is reversible.
  3. Check git status. If there are uncommitted changes, stop and ask them to commit or stash first.

1. Audit

Read the project: manifests, entry points, structure, config, tests, CI, deploy files, README. Score it against the checklist in CHECKLIST.md and show it as a table: Item | Status (✅/🟡/❌) | Evidence (file:line).

Then propose an upgrade plan: the 5–8 highest-impact items, ordered by interview value per hour of work. Each item gets: what changes, the files touched, the estimated size (S/M/L), and the interview talking point it creates ("Now you can say: 'I added integration tests for the payment flow and a CI pipeline that blocks merges on failure.'").

Wait for approval. They can pick a subset.

2. Execute, one item at a time

  1. Create a branch: git checkout -b hireable/<short-name>.
  2. For each approved item:
    • Make the change in the project's existing style, language and framework. Don't rewrite the stack.
    • Verify it actually works: run the tests, build, lint, and start the app if feasible. Never claim it works without running it.
    • Commit with a clear conventional message (test: add integration tests for cart API).
    • Explain the change in 2–3 sentences so they can explain it in an interview: what, why, and the trade-off. If they can't explain it, the change is worth nothing on a resume.
  3. Things you must not do: invent features, fake data or metrics, add dependencies without saying why, delete their code without asking, or push to a remote or deploy without explicit permission.

3. Wrap up

  1. Summary table of what changed, with commit hashes.
  2. Resume bullets reflecting the upgrades, using [N] placeholders for unknown metrics.
  3. Interview talking points: 5 likely questions about these changes, with answers.
  4. Next steps that need them (e.g. "Add your real Postgres URL to Vercel env and deploy").
  5. Re-score the checklist and log a scorecard via the Skill tool with "cracked-profile". Dimensions: Docs, Testing, Code Quality, Security, Deployability. Show the before → after.

Skill calls: if your agent has no Skill tool, open the named skill's SKILL.md in the cracked skills folder (core/, interview/, profile/, strategy/) and follow it instead.

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.