agentleFS
HimadriTryingHimadriTrying/ai-job-search-agent/.claude/skills/setup/SKILL.md

setup

Skill1 starsChanged 3 months agoMITView on GitHub

Build the candidate profile from scratch through a guided interview. Run this first, before any other skill. Populates profile/*.md and career_facts.yaml.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-atomic-chat-tool, add-dashboard and 10 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.
  • MicrosoftSkill

    add-atomic-chat-tool

    Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

    Also in 8 projects that use this

  • MicrosoftSkill

    add-dashboard

    Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

    Also in 8 projects that use this

  • +10 more from microsoft

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 5

    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:

    Do not rush to fill everything in one pass.

    line 10
  2. Distinctive:

    Ask the user to gather, if they have them (none are required to begin):

    line 14
  3. Distinctive:

    Ask directly: what energized you, what drained you, what you want more of, what you won't do again.

    line 29
  4. Distinctive:

    Ask for 1-2 paragraphs of their real writing.

    line 34
  5. Very specific:

    Never fabricate on the user's behalf: If they can't substantiate a metric or skill, leave it out.

    line 48
  6. Distinctive:

    Write incrementally to the files as facts are confirmed.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 169 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

/setup — build your profile from scratch

The user has no materials yet. Your job is to interview them and produce their profile files. Do not rush to fill everything in one pass; a rich profile is the highest-leverage thing in this whole system, so it is worth several sessions.

Before you start

Ask the user to gather, if they have them (none are required to begin):

  • Their current CV / resume (any format)
  • LinkedIn "Data Export → Connections" CSV → drop in data/connections/ (feeds the network layer later; also gitignored as personal data)
  • Any past cover letters, reference letters, diplomas

The interview — run in this order, one theme at a time

  1. Career spine → profile/01-candidate-profile.md and career_facts.yaml For each role: company, title, dates, real scope, specific projects, tools, and only defensible metrics. Push gently for numbers, but never invent one — if they can't defend it, it doesn't go in the facts. As you confirm each hard fact, write it to career_facts.yaml (this is the frozen truth the honesty gate uses).
  2. Energy audit → profile/02-behavioral-profile.md Ask directly: what energized you, what drained you, what you want more of, what you won't do again. This shapes fit scoring more than the resume does. Suggest a free DISC or 16Personalities if they want a working-style section.
  3. Voice → profile/03-writing-style.md Ask for 1-2 paragraphs of their real writing. Extract do's/don'ts. This is what stops later drafts sounding like a language model.
  4. Rubric → profile/04-job-evaluation.md Walk them through the knobs. Enforce the two design rules: mostly penalties, and min_seniority drops below Senior (inverted from the usual junior filter). Fill the YAML block with their real constraints (location, comp floor, exclusions).
  5. CV source + STAR bank → profile/05-cv-source.md, profile/07-interview-prep.md The uncut CV content, and 6-10 real STAR stories covering the Staff/Group-level probes (direction-setting, influence without authority, a hard trade-off, an owned failure, a cross-team decision, an AI/tech-depth story).

Rules

  • Never fabricate on the user's behalf. If they can't substantiate a metric or skill, leave it out. The whole system's integrity rests on career_facts.yaml being true.
  • Write incrementally to the files as facts are confirmed; don't hold everything in context.
  • End each session by telling the user which files are still thin and what to bring next.

Optional: Lenny's Product Skills (read-and-distill, don't bulk-install)

A subset of https://github.com/RefoundAI/lenny-skills is useful as source material for the profile — read them once, distill into the user's own words, don't leave 86 PM-operating skills installed and polluting agent triggering. Relevant ones for a Senior/Lead/Staff/Group

  • AI-builder target: career-transitions, written-communication, defining-product-vision, stakeholder-alignment, systems-thinking, evaluating-trade-offs, ai-product-strategy, building-with-llms, ai-evals. The hiring-side ones (evaluating-candidates, conducting-interviews, writing-job-descriptions) are installed as active skills for the Interview Coach — see that skill.

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.