hiring-kit
Skill0 starsChanged 4 months agoMITView on GitHub
Build a complete hiring kit for an early startup hire, including an outcomes-based job description, interview loop, scorecard, and reference questions. Use when the user wants to write a job description, plan interviews, hire their first employees, or evaluate candidates.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- GTMify/aigtmtheir own version, first seen May 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- GTMify/aigtm★ 25same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- cold-outreachSkill
- competitor-scanSkill
- customer-discoverySkill
- investor-updateSkill
- landing-copySkill
- launch-planSkill
- metrics-reviewSkill
- mvp-cutSkill
- pitch-deck-reviewSkill
- pricing-strategySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Every stage kills or advances.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Hiring Kit
Early hires are existential: hire number 3 shapes the next 30. This skill produces the four artifacts of a disciplined hire, in order, because the JD cannot be written before the outcomes are known.
1. Outcome definition
Before any JD, get the user to answer: "What must this person have accomplished in 12 months for the hire to be a clear win?" Force 3-4 concrete outcomes ("shipped the mobile app to both stores," "took support ticket resolution from 3 days to same-day"). If the user lists activities instead of outcomes, convert them or push back.
2. Job description
Structure:
- Mission: one paragraph on what the company does and why this role exists now
- Outcomes: the 3-4 from step 1, verbatim; this is the spine of the JD
- What you bring: 4-6 requirements that trace to the outcomes. Cut every credential that does not ("BSc required" rarely survives this test). Mark at most 2 as hard requirements; long must-have lists filter out exactly the scrappy people startups need.
- How we work, compensation range, and how to apply (a range in the posting widens and speeds the funnel)
Banned: laundry lists of 15 technologies, "rockstar/ninja/wizard," "work hard play hard," unpaid "test projects" longer than 2 hours, and any criterion touching age, gender, family status, or other protected characteristics.
3. Interview loop
Four stages, each with a distinct question and owner:
- Screen (30 min): motivation and trajectory. Are they running toward this or away from something?
- Deep dive (60-90 min): walk backward through their 2 most relevant accomplishments. What did they do, decisions they made, real numbers. Generic answers to specific questions are the signal.
- Work sample (max 2 hours, paid or lightweight): a scoped exercise resembling the actual job. For engineers: real-ish code review or small feature, not puzzles.
- Values and cofounder chat (45 min): mutual selling, working-style honesty, answering their questions.
Every stage kills or advances; no "let's see them again to be sure" limbo.
4. Scorecard and references
Scorecard: for each outcome and each of 3-4 competencies, a 1-4 rating with a written evidence line. Filled in within an hour of each interview, before interviewers talk to each other. Verdicts: strong hire, hire, no hire, strong no hire. A committee of "weak hire" votes is a no.
Reference questions (talk to 2-3, at least one manager):
- "In what situations does [name] do their best work? Their worst?"
- "Rank them in the top X% of people you have worked with in this role?"
- "Would you hire them again?" Anything but an immediate yes is a no.
Rules
- Hire for slope over pedigree at early stage, but verify slope with evidence, not vibes.
- The bar does not lower because the search is long; the search widens instead.
- Close fast: startups win offers on speed and conviction, not compensation.
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
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.