agentleFS
Tdeniz1Tdeniz1/resume-engine-starter/.claude/skills/intake/SKILL.md

intake

Skill0 starsChanged 3 months agoMITView on GitHub

Load the user's career history into master data. Use on first setup, when the user has filled in intake/PASTE_YOUR_INFO.md, when they paste a resume or LinkedIn profile, or when they want to add a new job, skill, project, or metric to their master data.

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan, triage and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read AGENTS.md in the repo root first if you have not already.

    line 8
  2. Very specific:

    If PASTE_YOUR_INFO.md is still the untouched template and the user pasted nothing, ask them to fill it in or to paste their resume and …

    line 20
  3. Distinctive:

    Never quietly upgrade a CLAIMED number to VERIFIED.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “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

Load career history into master data

Read AGENTS.md in the repo root first if you have not already.

This skill fills data/*.yaml, the single source of truth every resume is built from. Everything downstream depends on this being rich and honest.

Steps

  1. Find the input. In order of preference:

    • intake/PASTE_YOUR_INFO.md, if the user has filled it in
    • a resume, LinkedIn dump, or CV the user pasted into the conversation
    • a file they pointed you at

    If PASTE_YOUR_INFO.md is still the untouched template and the user pasted nothing, ask them to fill it in or to paste their resume and LinkedIn directly, and work from that.

  2. Write data/profile.yaml first. Replace every FILL_ME. Leave a field as "" to omit it from the header. Never add date of birth, home address, photo, or nationality.
  3. Fill the rest of data/: experience, education, projects, skills, honors, certifications, publications. Match the shape of the shipped sample entries exactly. Ids are stable kebab-case and are what tailored resumes reference, so pick them once and do not rename them later.
  4. Delete every sample-* entry you replaced. If the user genuinely has nothing for a section, leave that file as an empty list ([]) rather than leaving samples behind. Validation blocks any resume that still references a sample id.
  5. Write bullets LONG. Master data is not a resume and is never trimmed for length. Keep every number, scope detail, tool, and stakeholder. One master entry might hold 8 bullets that no single resume ever shows in full.
  6. Interrogate the numbers. This is the step that decides whether the whole system is honest, because the validator can stop you from inventing facts but cannot stop the user.
    • Vague claims get a question: "improved efficiency" becomes "by how much, measured how?"
    • Suspiciously round or convenient numbers get a question about how they know it. A number recalled from a dashboard is different from a number that "sounds about right".
    • Record the answer as a provenance flag in the entry's details: VERIFIED (an artifact exists), CLAIMED (true to memory, no document), CONFLICT (two sources disagree, unusable until resolved).
    • Never quietly upgrade a CLAIMED number to VERIFIED.
  7. Capture standing rules from section 9 of the intake file, or anything the user says in passing, into the relevant entry's details field. Examples: which GPA to state and never round, which venture to leave off by default, which framing of a degree to use. These notes never render, and they are what makes the engine behave consistently months later.
  8. Smoke-test. Build a throwaway application against the new data, confirm scripts/validate.py passes and scripts/render.sh produces one page, then delete the throwaway folder.
  9. Report back: what you loaded, what you flagged CLAIMED or CONFLICT, and what you still need from them.

Incremental updates

This skill also handles "I just got promoted", "here is a metric I forgot", and "I finished that project". Append and enrich; never delete history. Old jobs stay in master data forever, and the tailoring step decides what to omit.

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.