agentsclimarketplace
Sign in

Interviewing

Skill sandev/engineering-os/skills/leading-people-and-teams/interviewing

Run structured technical interviews that produce reliable hiring signal and a fair candidate experience. Use when designing an interview loop, writing or reviewing an interview question or rubric, conducting an interview, or writing up a hire/no-hire recommendation.From its SKILL.md

Install
npx -y skills add sandev/engineering-os --skill interviewing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 722 tokens by cl100k_base, as published. Nobody here has run it

Interviewing

An interview's job is to gather evidence that predicts on-the-job success, fairly and consistently. Most interviews fail at this: they're unstructured chats that mostly measure how much the candidate resembles the interviewer. Structure is what turns opinion into signal, and it's also what makes interviews fairer.

Structure beats vibes

Decide, before the loop, what you're assessing and how you'll score it. Every candidate for a role gets the same core questions and the same rubric. Structured interviews are dramatically more predictive than unstructured ones and far less biased, because you compare candidates on the same evidence rather than on gut feel.

  • Define the competencies the role needs (e.g. coding, system design, debugging, collaboration).
  • Assign each competency to a specific interview so the loop has coverage, not overlap.
  • Write a rubric with concrete behaviors for each level, agreed in advance.

Ask job-related, open questions

  • Use realistic problems that resemble the actual work, not trivia, puzzles, or gotchas.
  • Behavioral questions for past behavior ("Tell me about a time you disagreed with a technical decision, what did you do?"), then probe for specifics: what they did, not what "we" did.
  • Prefer depth over breadth: one problem explored deeply reveals more than ten shallow ones.
  • Calibrate difficulty to the level you're hiring for.

Run it well

  • Let the candidate talk (aim ~80% them / 20% you); you're gathering evidence, not lecturing.
  • Reduce anxiety: nervous people underperform in ways unrelated to the job. Be warm, set context, share the format up front.
  • Give hints when someone is stuck; how they use a hint is strong signal, and it's more humane and more realistic than watching them flail.
  • Take notes on what they said and did, in the moment, memory distorts fast and favors recency.

Score on evidence, then decide

  • Rate against the rubric, citing specific things the candidate did, not "seemed smart" or "good culture fit" (a phrase that smuggles in bias).
  • Assess for the role, not for similarity to you. "I'd grab a beer with them" is not a competency.
  • Write a clear recommendation (strong hire / hire / no-hire / strong no-hire) with the evidence behind it. Wishy-washy write-ups waste the debrief.
  • Submit before the debrief so you aren't anchored by louder voices (a decision-making failure mode, see the decision-making skill).

Fairness and the candidate experience

Every candidate is also a customer and a broadcaster of your brand. Be on time, prepared, and respectful; the same courtesy you'd want. Consistency in questions and rubric is not just accuracy, it's fairness.

Anti-patterns

  • Unstructured "let's just chat" interviews with no rubric.
  • "Culture fit" used to mean "like us", screen for values and collaboration, not sameness.
  • Trivia, brain-teasers, and gotchas unrelated to the job.
  • The interviewer talking most of the time.
  • Deciding on gut feel, then back-filling justification.
  • Reading other interviewers' scores before writing your own.
  • Treating candidates as disposable, a bad experience costs you future hires.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most hr recruiting skills give in 722 tokens

Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07

  • Quantify achievements with specific metricsin 14 of 356, across 6 files
  • Keep the resume under two pagesin 14 of 356, across 6 files
  • Request the full job description if not providedin 12 of 356, across 4 files
  • Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
  • Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
  • Map candidate experience to job requirementsin 11 of 356, across 3 files
  • Ask if the user wants adjustmentsin 11 of 356, across 3 files
  • Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
  • Request candidate background details if not providedin 10 of 356, across 2 files
  • Format experience bullets as action verb plus resultin 10 of 356, across 2 files
  • Ask for missing inputs before startingin 10 of 356, across 9 files
  • Use exact job description terminologyin 9 of 356, across 1 file

Said here and by no other author read

  • write a rubric with concrete behaviors for each level
  • use realistic problems that resemble the actual work
  • prefer depth over breadth in questions
  • calibrate difficulty to the hiring level
  • reduce candidate anxiety
  • give hints when someone is stuck

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.