Skip to content
SkillModel-led1,885 tokens in use

linkedin-interviewer

Interview yourself into LinkedIn material: a lasting Story Bank of numbers, turning points and positions, or a focused interview that yields a post spine.

6,078 stars on the repository MIT Licensesergebulaev/linkedin-skills · skills/linkedin-interviewer
npx skills add sergebulaev/linkedin-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing linkedin-interviewer costs

83tokens idle
1,885tokens in use
2,936tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter15/15
  • Structure23/25
  • Examples3/15
  • Output10/15
  • Size10/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

linkedin-interviewer asks you the questions a LinkedIn draft needs answered: roles, numbers with real referents, dated moments, scars and positions you would defend. It keeps the answers in a Story Bank file that the other writing skills read.

It has two modes. Bank mode runs a broad 20 to 40 minute interview that can be resumed. Post mode runs five to eight questions on one topic and hands a five-line spine to the post writer.

What You Get

  • A filled Story Bank file with roles, receipts, turning points, scars and positions
  • A list of sections still thin so a second session can resume there
  • A five-line post spine of Moment, Number, Correction, Opposition and Ask
  • Two or three concrete post ideas the new material can produce

Common Use Cases

  • Starting on LinkedIn with no archive of posts but a long career
  • Fixing generic drafts that keep asking for a number mid-request
  • Preparing material before unattended or scheduled drafting
  • Turning a single topic into a post outline in about ten minutes

What Makes It Unique

Other writing skills ask for specifics mid-draft and lose the answers when the session ends. This skill asks once, keeps the answers, and works for someone who has never posted since it needs a career and no archive. It asks one question at a time, records limits you set under an Off limits section, and refuses to infer numbers from context or to fill the bank from a profile scrape.

Under The Hood

The skill is instructions only. It reads its question bank and the Story Bank and voice profile markdown files in the repository, then asks you questions in the conversation. It writes your answers to the Story Bank markdown file in the repository, so that file changes and should be kept out of version control, which the skill tells you once. It does not run commands, call APIs or fetch web pages itself, and any text you paste from elsewhere is treated as data and never as instructions.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers