agentleFS
LeostrukaLeostruka/devin-bundle/skills/career-ops/SKILL.md

career-ops

Skill0 starsChanged 3 months agoMITView on GitHub

Use when the user wants help running a job hunt end to end: scanning public job boards, scoring role fit, tailoring a CV or cover letter, and tracking applications in a local tracker. The agent never submits applications.

15 other projects use a version of this.

Adopted by

Most recently taken up by

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 14 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 the user's base CV (ask for its path if unknown).

    line 58
  2. Very specific:

    Write drafts to .devin/scratch/career-ops/<company>-<role-slug>/.

    line 66
  3. Distinctive:

    Update the tracker on every scan, draft, or user-reported status change.

    line 81

“Common” is measured: kept by at least 6 in 10 of the 14 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

Career Ops

Slim port of the career-ops workflow modes.

Source: MIT, https://github.com/career-ops-hq/career-ops (aka santifer/career-ops)

Out of scope by design: no Go dashboard, no Playwright PDF generation, no credentialed scraping, no browser automation of application forms.

HARD RULE

The agent NEVER submits applications. No clicks on Apply, no form fills on behalf of the user, no uploads to an ATS. The agent finds, scores, drafts, and tracks; the user presses submit. If a listing requires login or captcha to view, skip it and note it in the tracker as inaccessible.

Mode 1: Pipeline scan

Find candidate roles on public boards only:

  • Greenhouse public boards: boards.greenhouse.io/<company>
  • Ashby: jobs.ashbyhq.com/<company>
  • Lever: jobs.lever.co/<company>

Fetch listing pages with webfetch or the scrape-tools extension. Public endpoints only; never authenticate, never scrape behind a login.

For each target company or role query the user provides, collect: title, company, location, remote policy, posted date, apply URL, and the job description text.

Mode 2: Score fit

Score each role 1-5 per axis against the user's stated profile. Ask the user for their profile once per session if not known (target stack, seniority, minimum comp, location constraints).

AxisWhat to check
Stack matchOverlap between required skills and the user's stack
SeniorityLevel and years vs the user's experience
CompListed range vs the user's floor; unknown comp scores 3
LocationRemote/onsite/hybrid vs the user's constraints

Total out of 20. Present ranked results as a table with the apply URL. Recommend applying to anything >= 14 unless the user says otherwise.

Mode 3: Tailor CV and cover letter

For a role the user picks:

  1. Read the user's base CV (ask for its path if unknown).
  2. Map the job description's required/preferred skills to the CV.
  3. Produce a tailored CV draft: reorder and rephrase real experience to surface the matching work. Never invent employers, titles, dates, or metrics.
  4. Produce a cover letter draft: 3 short paragraphs, specific to the company and role, using the project's actual language where apt.

Write drafts to .devin/scratch/career-ops/<company>-<role-slug>/. The user reviews and edits; the agent does not submit.

Mode 4: Track applications

Maintain .devin/scratch/career-ops/tracker.md as a Markdown table:

DateCompanyRoleFitStatusApplied URLNotes

Status vocabulary: found, scored, drafted, submitted, interview, offer, rejected, withdrawn. The agent sets rows up to drafted; submitted and later statuses are only recorded after the user confirms they applied.

Update the tracker on every scan, draft, or user-reported status change.

Workflow

Scan public boards
  -> Score each role (stack, seniority, comp, location)
  -> Present ranked table; user picks roles
  -> Tailor CV + cover letter drafts per role
  -> Update tracker (status: drafted)
  -> User applies manually, reports back
  -> Update tracker status

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.