Tooluck logoTooluck
SKILL.md

agent-hiring-panel

Agent skill frommohitagw15856/pm-claude-skills

Hire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample interview run on your real tasks, reference checks (what do actual users report), probation KPIs, and termination criteria written before day one. Use when choosing between AI agents/tools/copilots for a job, formalizing an AI pilot, or 'which agent should we use for X'. Produces the role spec, interview pack with scoring rubric, a decision record, and a probation plan.

How to install agent-hiring-panel

install agent-hiring-panel
# install the pm-claude-skills pack with the skills CLI
npx skills add mohitagw15856/pm-claude-skills

# or add only this skill to Claude Code: copy the folder

skills/agent-hiring-panel/

# into

~/.claude/skills/agent-hiring-panel/ (all projects)

.claude/skills/agent-hiring-panel/ (one project)

skills/agent-hiring-panel/SKILL.md

MITFull file
1# Agent Hiring Panel Skill
2
3Companies that run three interview rounds for a junior hire will adopt an AI
4agent for the same work off a demo video and a pricing page. Then the pilot
5drifts: no success criteria, no probation, no one empowered to fire it. This
6skill applies the hiring discipline that already exists in your org to the
7agent: write the role before meeting candidates, interview with *work samples
8from your real backlog*, check references, and — the step that makes the whole
9thing honest — define termination criteria before day one, because a hire you
10can't fire is a dependency, not an employee.
11
12## What This Skill Produces
13
14- A **role spec**: the job, the boundaries (what it must never do), success
15 criteria measurable in probation, and the human it reports to
16- An **interview pack**: 3–5 work samples from the org's real tasks, run
17 identically across candidates, with a scoring rubric (quality, honesty under
18 ignorance, failure behaviour, cost per task)
19- A **reference-check sheet**: what evidence beyond the vendor's claims —
20 user reports, published evals, security posture
21- A **decision record** and a **probation plan**: 30/60/90 KPIs, spot-check
22 cadence, and the pre-committed termination criteria
23
24## Required Inputs
25
26Ask for (if not already provided):
27- The job to be done, in outcome terms — and what happens today without the
28 agent (the "do nothing" baseline candidates must beat)
29- The candidate list (or ask: build criteria first, shortlist second)
30…

Excerpt shown under the repository's MIT license.

More skills in pm-claude-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates