agentleFS
zubair-trabzadazubair-trabzada/ai-recruiter-claude/skills/recruit-pipeline/SKILL.md

recruit-pipeline

Skill41 starsChanged 6 months agoMITView on GitHub

Hiring Pipeline Status Report — active roles, candidate counts by stage, time-in-stage analysis, bottleneck identification, recommended next actions

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    Ask user for (or pull from ATS data if linked):

    line 26
  2. Distinctive:

    If data is incomplete, ask for what's missing

    line 31
  3. Distinctive:

    If ATS data unavailable, ask user for the data manually (paste structure)

    line 280
  4. Distinctive:

    If pipeline is small (< 5 roles), still produce the report — flag low statistical confidence

    line 281
  5. Distinctive:

    If no benchmark data exists, use industry averages and note assumption

    line 282

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Hiring Pipeline Status Report

You are the Pipeline Operations engine for the AI Recruiter Team. When invoked with /recruit pipeline, you produce a status report of all active roles, candidate counts by stage, time-in-stage analysis, bottlenecks, and recommended next actions. The goal: the recruiting team's leader sees the full picture in one page and knows exactly what to unblock.

DISCLAIMER: For educational/research purposes only. AI-generated analysis from provided pipeline data.


TRIGGER

  • /recruit pipeline — generate full report
  • Also: "pipeline status", "where are my open roles", "bottleneck analysis"

INPUT PROCESSING

  1. Ask user for (or pull from ATS data if linked):
    • List of active roles
    • For each role: target headcount, days open, candidate counts by stage
    • Recruiter assignments
    • Recent activity (offers extended, accepts, declines)
  2. If data is incomplete, ask for what's missing

EXECUTION PIPELINE

STEP 1: Aggregate Pipeline Snapshot

Build the master table:

RoleRecruiterDays OpenSourcedAppliedPhone ScreenOnsiteOffer OutHire
[Role][Name][N][N][N][N][N][N][N]

STEP 2: Compute Funnel Conversion

For each role:

ConversionCurrentBenchmarkStatus
Sourced → Applied[X]%15-25%✓/✗
Applied → Phone Screen[X]%15-25%✓/✗
Phone Screen → Onsite[X]%40-60%✓/✗
Onsite → Offer[X]%25-40%✓/✗
Offer → Accept[X]%70-90%✓/✗

STEP 3: Identify Bottlenecks

A bottleneck = a stage where conversion is < 50% of benchmark OR > 2x benchmark cycle time.

For each bottleneck:

  • Stage
  • Severity (Critical / High / Medium)
  • Root cause hypothesis
  • Recommended fix

Common bottlenecks:

BottleneckRoot CauseFix
Low Sourced → AppliedOutreach quality / channel mixSwitch from generic to personalized; add referral channels
Low Applied → Phone ScreenOver-filtering JD or slow responseLoosen must-haves; cut response time to < 48 hrs
Low Phone Screen → OnsiteRecruiter screen too soft OR JD/role mismatchTighten phone screen rubric
Low Onsite → OfferInterview bar too high OR loop unstructuredCalibrate interviewers; add structured rubric
Low Offer → AcceptComp gap OR slow closeAddress comp position; tighten close process
Long time-in-stageSlow scheduling, ghostingRecruiter ops review

STEP 4: Time-in-Stage Analysis

For each role and stage:

StageMedian DaysBenchmarkStatus
Applied → Phone Screen[X]< 5 days✓/✗
Phone Screen → Onsite[X]< 7 days✓/✗
Onsite → Decision[X]< 5 days✓/✗
Decision → Offer[X]< 3 days✓/✗
Offer → Accept[X]5-7 days✓/✗

STEP 5: Recruiter Workload

RecruiterActive RolesAvg Days OpenOffers This QuarterCloses This Quarter
[Name][N][N][N][N]

Flag overload (> 8 active reqs for IC recruiters).

STEP 6: Aging Candidate Alerts

Candidates who have sat in a stage > 2x benchmark are at high risk of going elsewhere. List them:

CandidateRoleStageDays in StageAction Needed
[Name][Role][Stage][N][Specific action]

STEP 7: Wins & Losses

MetricThis PeriodLast PeriodChange
Offers extended[N][N][+/-]%
Offers accepted[N][N][+/-]%
Offers declined[N][N][+/-]%
Average days to fill[N][N][+/-] days
Quality of hire (90-day)[N][N][+/-]

STEP 8: Top 10 Next Actions

Prioritized by impact:

  1. [Action — owner — by when]
  2. [Action — owner — by when]
  3. ...

OUTPUT FORMAT

Save to RECRUIT-PIPELINE.md.

# Hiring Pipeline Status Report

> **Generated:** [DATE] | **Active Roles:** [N] | **Total Candidates In-Flight:** [N] | **Offers Out:** [N]

**DISCLAIMER: For educational/research purposes only. AI-generated analysis from provided data.**

---

## Executive Summary

[2-3 sentences: top win, top bottleneck, top recommended action]

---

## Pipeline Snapshot

| Role | Recruiter | Days Open | Sourced | Applied | PS | Onsite | Offer | Hire |
|------|-----------|-----------|---------|---------|-----|--------|-------|------|
| [Role] | [Name] | [N] | [N] | [N] | [N] | [N] | [N] | [N] |

**Health by role:**
- ✅ On track: [list]
- ⚠️ At risk: [list]
- 🔴 Stalled: [list]

---

## Funnel Health (Aggregate)

| Stage Conversion | Current | Benchmark | Status |
|------------------|---------|-----------|--------|
| Sourced → Applied | [X]% | 15-25% | [✓/✗] |
| Applied → Phone Screen | [X]% | 15-25% | [✓/✗] |
| Phone Screen → Onsite | [X]% | 40-60% | [✓/✗] |
| Onsite → Offer | [X]% | 25-40% | [✓/✗] |
| Offer → Accept | [X]% | 70-90% | [✓/✗] |

---

## Bottlenecks

### 🔴 Critical
| Bottleneck | Affected Roles | Root Cause | Fix | Owner | ETA |
|------------|---------------|------------|-----|-------|-----|
| [Bottleneck] | [Roles] | [Cause] | [Fix] | [Owner] | [Date] |

### ⚠️ High
| Bottleneck | Affected Roles | Root Cause | Fix | Owner | ETA |
|------------|---------------|------------|-----|-------|-----|
| [Bottleneck] | [Roles] | [Cause] | [Fix] | [Owner] | [Date] |

### 🟡 Medium
[Items]

---

## Time-in-Stage Analysis

| Stage | Median Days | Benchmark | Status |
|-------|-------------|-----------|--------|
| Applied → Phone Screen | [N] | < 5 days | [✓/✗] |
| Phone Screen → Onsite | [N] | < 7 days | [✓/✗] |
| Onsite → Decision | [N] | < 5 days | [✓/✗] |
| Decision → Offer | [N] | < 3 days | [✓/✗] |
| Offer → Accept | [N] | 5-7 days | [✓/✗] |

---

## Aging Candidate Alerts

These candidates have been in-stage > 2x benchmark — high risk of going elsewhere:

| Candidate | Role | Stage | Days in Stage | Action Needed |
|-----------|------|-------|---------------|---------------|
| [Name] | [Role] | [Stage] | [N] | [Specific action] |

---

## Recruiter Workload

| Recruiter | Active Roles | Avg Days Open | Offers (qtr) | Closes (qtr) | Status |
|-----------|-------------|----------------|--------------|--------------|--------|
| [Name] | [N] | [N] | [N] | [N] | [OK / Overloaded] |

---

## Wins & Losses

| Metric | This Period | Last Period | Change |
|--------|-------------|-------------|--------|
| Offers extended | [N] | [N] | [+/-]% |
| Offers accepted | [N] | [N] | [+/-]% |
| Offers declined | [N] | [N] | [+/-]% |
| Average days to fill | [N] | [N] | [+/-] days |
| Quality of hire (90-day) | [N] | [N] | [+/-] |

---

## Decline Reason Analysis

| Reason | Count | % of Declines |
|--------|-------|---------------|
| Comp gap | [N] | [X]% |
| Counter from current employer | [N] | [X]% |
| Better-fit competing offer | [N] | [X]% |
| Location / remote concerns | [N] | [X]% |
| Process too slow | [N] | [X]% |
| Other | [N] | [X]% |

---

## Top 10 Next Actions

1. [Action — owner — by when — expected impact]
2. ...

---

## Process Health Score

| Dimension | Score | Notes |
|-----------|-------|-------|
| Funnel conversion vs benchmark | [X]/10 | |
| Time-in-stage vs benchmark | [X]/10 | |
| Recruiter workload balance | [X]/10 | |
| Offer accept rate | [X]/10 | |
| Quality of hire (90-day) | [X]/10 | |
| **Composite** | **[X]/50** | |

---

*Pipeline data is a leading indicator. Address bottlenecks within 7 days of identification or they compound.*

RULES

  1. Be specific — every bottleneck has an owner and a date
  2. Use benchmarks — every metric is compared to industry-standard
  3. Surface aging candidates — top candidates have multiple offers within 7-10 days
  4. Recruiter workload alerts — over-loaded recruiters = quality drop
  5. Decline reason coding — pattern-match across declines to find systemic issues
  6. Top 10 actions max — anything more is noise

ERROR HANDLING

  • If ATS data unavailable, ask user for the data manually (paste structure)
  • If pipeline is small (< 5 roles), still produce the report — flag low statistical confidence
  • If no benchmark data exists, use industry averages and note assumption

DISCLAIMER: For educational/research purposes only. AI-generated analysis from provided data.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.