agentleFS
qbekaqbeka/jev-job-search/.claude/skills/expand/SKILL.md

expand

Skill368 starsChanged 5 days agoMITView on GitHub

Enrich the user's profile from the public sources they already link to (GitHub repositories, a portfolio site, published projects). Use when the user says /expand, "add my GitHub projects to my profile", or after /setup when the profile is thin. Proposes each discovered fact with its source; nothing is added without the user's yes.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review.

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.
  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Read data/profile.json: links (GitHub, portfolio, LinkedIn), the projects, the experience bullets, the skills and the facts.

    line 16
  2. Distinctive:

    Leave out anything vague, anything older than the profile's own timeline, and anything the user did not build themselves.

    line 25
  3. Very specific:

    Ask the user which rows to add.

    line 27
  4. Distinctive:

    Never invent a number, a date or a credential.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 6 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

/expand: what the public web says you have done

The writer may use only what data/profile.json holds. This skill finds what is missing from it, from places the user already points to, and asks before adding anything.

Steps

  1. Read data/profile.json: links (GitHub, portfolio, LinkedIn), the projects, the experience bullets, the skills and the facts.
  2. For each public link, fetch what is there. For GitHub, the user's public repositories: name, description, languages, README highlights, stars, last activity. For a portfolio site, the project pages. LinkedIn is not fetched; the user can export it as a PDF into documents/ instead.
  3. Compare with the profile. List, as a table, each candidate addition: a project not in projects, a language or framework not in skills, a concrete, checkable fact not in facts. Each row names its source. Leave out anything vague, anything older than the profile's own timeline, and anything the user did not build themselves.
  4. Ask the user which rows to add. Then write them with /profile's rules: projects as {name, role, start, end, link, bullets}, skills into the right list, facts as one sentence each. Every added bullet is plain, has one fact, and uses only what the source said.
  5. Say that the answer memory starts over, because the profile changed, and offer npx jev apply --dry --count 2 to see the effect.

Never invent a number, a date or a credential. If a source and the profile disagree, ask; do not pick.

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.