mcorbett51090/ravenclaude/recruiter-capacity-model
Claude Code and agent skill by mcorbett51090/ravenclaude
- community
Checking that the SKILL.md file is still in the repository.
Right-size a recruiting desk by modeling fillable-order supply against the reqs a recruiter can carry at target conversion, distinguishing nominal from fillable orders and under-fed from under-staffed. Reach for this when the question is whether to hire more recruiters or whether the team is the right size.
Install
npx vskill@latest install mcorbett51090/ravenclaude/recruiter-capacity-modelSKILL.md
The same SKILL.md was published earlier as mcorbett51090/ravenclaude/recruiter-capacity-model.
Skill: Recruiter capacity model
"Should we hire more recruiters?" is usually the wrong first question — the right one is "are the recruiters we have being fed fillable orders, and are they unblocked?" This skill models capacity honestly.
Step 1 — Separate nominal orders from fillable orders
Strip dead, on-hold, and structurally-uncompetitive orders. A desk buried in unfillable orders looks understaffed and isn't — adding recruiters to dead demand burns money. Fillable-order count is the only denominator that matters.
Step 2 — Establish per-recruiter throughput
From the client's own data: reqs a recruiter carries and placements/quarter at the current conversion. Context anchors ([ESTIMATE], Recruiterflow): hires/recruiter/quarter bottomed ~4.5 (early 2023), recovered to ~7.3 (Q1 2026). Use the client's actuals; the benchmark is a sanity rail only.
Step 3 — Model the gap
Required recruiters = fillable-order supply ÷ (reqs a recruiter can carry at target conversion). Compare to current headcount. The output is over-staffed / right-sized / under-staffed — for the fillable demand, not nominal.
Step 4 — Check the "unblock vs. hire" lever first
Before recommending headcount, check whether existing recruiters are blocked: AI/automation can return up to ~17 hrs/recruiter/week against the ~14.6 hrs/week spent sourcing (Bullhorn GRID 2026, [ESTIMATE]). If recruiters are spending capacity on admin a tool could absorb, the cheaper fix is unblocking, not hiring.
Step 5 — Factor segment difficulty
Credentialing-heavy (healthcare) and academic-calendar-bound (education) desks have lower effective throughput per req — a recruiter on rural school-therapy roles can't carry the same load as one on light-industrial. Adjust the carry assumption by segment, don't average.
Step 6 — Account for seasonality in the supply curve
Education demand front-loads to spring/summer; healthcare has surge windows. A capacity model on an annual-average order supply will under-staff the peak and over-staff the trough. Model the curve, or at least name the peak the desk must cover.
Step 7 — State the assumptions to validate
Capacity models are assumption-stacked (carry rate, conversion, fillable %, seasonality). List each assumption and the client data that would confirm it. A model whose assumptions aren't surfaced is a guess with a spreadsheet.
Reference
Funnel definitions: `../../knowledge/staffing-kpi-glossary.md` §A, §D. Decision tree for under-fed vs. under-performing: `../../knowledge/staffing-decision-trees.md`.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/staffing-operations/skills/recruiter-capacity-model/SKILL.md
Popularity
- Repository stars
- 8
- Repository forks
- 1
- 7-day trend score
- 16
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mcorbett51090/ravenclaude/recruiter-capacity-model)