hire
Skill1 starsChanged 4 months agoMITView on GitHub
Use when bringing on human help - a contractor, freelancer, or first employee - or when the user says hire, job description, find a developer, outsource, delegate to a person.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- fainir/agent-harnesstheir own version, first seen Nov 1, 2026
- ARCASSystems/FounderOStheir own version, first seen Oct 24, 2026
- menkesu/awesome-pm-skillstheir own version, first seen Oct 13, 2026
- jamillazarev/multica-opstheir own version, first seen Sep 25, 2026
- markfulton/ai-employeestheir own version, first seen Sep 2, 2026
- danielgefen/soustheir own version, first seen Aug 25, 2026
Used with
Projects with it also use ship.
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.
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- markfulton/ai-employees★ 822same name
- menkesu/awesome-pm-skills★ 441same name
- jamillazarev/multica-ops★ 11same name
- ARCASSystems/FounderOS★ 7same name
- freskhu/genesis★ 5same name
- jamillazarev/opsinist★ 1same name
- danielgefen/sous★ 0same name
- fainir/agent-harness★ 0same 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 repository13 other files it gives its agents.
- add-aiSkill
- add-authSkill
- growSkill
- hardenSkill
- launchSkill
- maintainSkill
- monetizeSkill
- new-projectSkill
- optimizeSkill
- pitchSkill
- product-specSkill
- ship-itSkill
- validate-ideaSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
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 42
Never cut the paid work sample to save time.
“Common” is measured: kept by at least 6 in 10 of the 5 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.
Files
Hire
Scorecard before job description, job description before interviews — skip the scorecard and you hire whoever interviews best, not whoever does the job.
Copy this checklist and check off items as you complete them:
Hire Progress:
- [ ] Step 1: Scorecard
- [ ] Step 2: JD draft
- [ ] Step 3: Sourcing plan
- [ ] Step 4: Interview loop
- [ ] Step 5: Contract checklist
- [ ] ReportStep 1 — Scorecard before JD
Define the outcome, not the resume. Write 3-5 measurable outcomes for what great looks like at the 90-day mark (shipped what, moved which metric by how much), plus two skill lists: required and nice-to-have. If the role's scope is fuzzy — generalist or specialist, contract or full-time, needed now or in three months — delegate to the biz-strategist agent with the business problem this hire is meant to solve.
Step 2 — JD draft
Delegate to the copywriter agent with the scorecard as input, not a blank prompt. The JD leads with the 90-day outcomes, states the stack plainly (the actual tools, not a wishlist of 15 technologies nobody uses together), and states a real compensation range — one you'd defend out loud in the interview, not a placeholder. Publishing the JD anywhere public is outward-facing: confirm with the user before posting it.
Step 3 — Sourcing plan
Rank channels for this specific role type — relevant communities, job boards, freelance platforms (Upwork/Toptal for contract work, LinkedIn for full-time), personal network — and commit to the top 2-3 rather than spraying across all of them. Name the first 3 concrete actions (post in which community, DM which 5 people, apply which platform filter) with who does each and by when.
Step 4 — Interview loop
Identical loop for every candidate — that's what makes them comparable:
- 30-minute screen: motivation for this specific role, walkthrough of relevant past work.
- PAID, timeboxed work sample pulled from the real backlog — an actual ticket or task, not a synthetic puzzle. Pay it whether or not the candidate advances.
- Score against the Step 1 scorecard with a rubric — required skills as line items, not gut feel.
Never cut the paid work sample to save time; unpaid "sample work" is a legal and trust liability, not a shortcut.
Step 5 — Contract
Delegate to the legal-advisor agent with the role type and jurisdiction for a checklist covering: IP assignment (non-negotiable — anything built for the business belongs to the business), contractor-vs-employee classification (misclassification is a real liability, not paperwork), payment terms (rate, schedule, currency), and a trial period with an explicit exit clause.
Report
- Scorecard: the 90-day outcomes and required/nice-to-have skills.
- JD draft: full text, ready to post.
- Sourcing plan: ranked channels and the first 3 concrete actions.
- Interview loop: the screen/work-sample/rubric structure for this role.
- Contract checklist: IP, classification, payment terms, trial period — flag anything needing the user's own legal review before use.
Any compensation figure or market-rate number not supplied by the user is a training-data estimate, not current data — label it an unverified assumption in the report rather than stating it as fact.
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.

