agentleFS
nishant-Tiwari24nishant-Tiwari24/cracked/skills/profile/resume-blueprint/SKILL.md

resume-blueprint

Skill312 starsChanged 10 days agoMITView on GitHub

Given a target company (and optionally a role), produce a company-specific resume blueprint covering what that company's screen looks for, the sections and order to use, which of the candidate's projects and experiences to lead with, must-have keywords, bullet templates tuned to the company's values, what to cut, and a fill-in-the-blanks resume skeleton built only from the candidate's real experience. Use when the user asks "what should my resume have for Google/Amazon/Microsoft/…", wants to tailor their resume to a company, or asks for a resume reference or template for a specific company.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    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" (level, roles, resume path).

    line 12
  2. Distinctive:

    Call the Skill tool with "company-intel" for the company.

    line 15
  3. Very specific:

    Read their current resume if there is one (same reading rules as roast-my-resume).

    line 16
  4. Distinctive:

    Write 5–8 bullets, each tied to a source in the brief (the company's careers page, published values, or reported experiences), or to its …

    line 20
  5. Distinctive:

    Never fabricate: No invented experience, metrics, or "what <Company> secretly wants".

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Resume blueprint

"What should my resume look like for <Company>?" deserves a better answer than a generic template. This skill combines what the company's screen rewards with the candidate's real material, and produces a resume plan they can fill in today.

0. Inputs

  1. Call the Skill tool with "cracked-profile" (level, roles, resume path).
  2. Company: from the request. If none is given, ask for it in one line. This skill only exists for company targeting; for a general review, point them to /roast-my-resume.
  3. Role: from the request or profile. Default to the profile's first target role.
  4. Call the Skill tool with "company-intel" for the company. You need the Resume screen, Values and DSA focus sections.
  5. Read their current resume if there is one (same reading rules as roast-my-resume). The blueprint is far better with it, but it still works without one.

1. What this company's screen rewards

Write 5–8 bullets, each tied to a source in the brief (the company's careers page, published values, or reported experiences), or to its archetype, labelled as such. For example:

  • "Impact at scale, quantified: bullets with users, latency or throughput numbers (big-tech archetype; consistent with reported screens)."
  • "Ownership and bias for action map to the published Leadership Principles, so frame bullets as you deciding and delivering."
  • "For new-grad SDE roles, DSA proof is a strong signal, given that their OA is reported as 2 medium–hard problems."

Then list what it doesn't care about (cut these): e.g. a long skills dump, an objective statement, non-technical hobbies, certificates without projects.

2. The blueprint

  1. Section order for this company, role and level, with a one-line reason each.
  2. Lead with: which of their projects and experiences go first, and why, mapped to what the company values. Flag any project that hurts more than it helps here.
  3. Must-have keywords for this role at this company, drawn from its JD language and stack. Mark each ✅ you have it / 🟡 true but missing from resume / ❌ gap. Only ✅ and 🟡 go on the resume; ❌ goes to the prep list.
  4. Bullet templates in this company's language: 4–6 templates showing how to frame their real experiences, e.g. Led <project> end-to-end, choosing <tech> over <alt> to <reason>; shipped to [N] users, cutting <metric> by [X]% (ownership and impact).
  5. Proof to add before applying: the 1–3 highest-leverage things they could add in under 2 weeks (a contest rating, deploying an existing project, one metric they can actually measure), each tied to a cracked skill (/make-it-hireable, /github-glowup).

3. Resume skeleton

Write $CRACKED_DIR/resume/<company>-blueprint.md: a full one-page resume skeleton in Markdown, in the recommended order, pre-filled only with facts from their resume or profile, with [placeholders] everywhere else, plus a <!-- why --> comment on each section explaining the choice. Mention that it converts cleanly to a single-column PDF (e.g. pandoc, or paste it into a plain single-column template).

4. Close

  • 3-line summary: the bar, their biggest gap against it, and the first fix.
  • Offer: /roast-my-resume (after they fill it in), /jd-match (once they have a specific JD), /oa-sim <company>.

Rules

  • Never fabricate. No invented experience, metrics, or "what <Company> secretly wants". Everything is sourced, archetype-labelled, or comes from the candidate.
  • Company facts come only from the company-intel brief. If the brief says unverified, say the same here.

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.