agentsclimarketplace

Hire

Skill T4LEL/Claude-Arsenal/skills/hire

25 Claude Code subagents + 14 lifecycle skills + CLAUDE.md templates - build, ship, and monetize products with AI. Clone, run sync, done.

Install
npx -y skills add T4LEL/Claude-Arsenal --skill hire

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

  • 1 stars1 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.

What its author says it does

Copied from the file, not written here

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.

SKILL.md

3.4 KB, as published. Nobody here has run it

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
- [ ] Report

Step 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:

  1. 30-minute screen: motivation for this specific role, walkthrough of relevant past work.
  2. 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.
  3. 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.

Keep looking

Skills are one crate of 328,083. 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.