Talent Acquisition

What it does

When your agent uses it

• Writing job descriptions
• Designing interview scorecards
• Analyzing hiring funnels
• Improving offer acceptance rates

Example prompts

• “/talent-acquisition”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Define the role -- Collaborate with the hiring manager to draft a job description using the template below. Confirm level, compensation…
2. 2Build sourcing strategy -- Select channels based on the role profile (see Source Channel Matrix). Set weekly outreach targets and pipeline…
3. 3Screen candidates -- Apply the structured phone screen framework. Score against must-have criteria. Pass or reject within 48 hours.
4. 4Run interviews -- Use competency-based scorecards. Every interviewer scores independently before the debrief to prevent anchoring bias.
5. 5Extend offer -- Follow the offer approval workflow. Present a verbal offer, handle negotiation, and send the written offer within 24 hours…
6. 6Close and onboard -- Confirm start date, initiate background check, and hand off to hiring manager with a 30-60-90 day plan.

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Talent Acquisition loads about 3.8k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,413 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~60

When it runs · the whole SKILL.md, loaded when a task matches

~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 1,413 words, ~3,765 tokens.

name

talent-acquisition

description

Talent acquisition across recruiting strategy, sourcing, interviews, and hiring analytics. Use when writing job descriptions, designing interview scorecards, analyzing hiring funnels, or improving offer acceptance rates.

license

MIT + Commons Clause

metadata.version

1.0.0

metadata.author

borghei

metadata.category

hr-operations

metadata.updated

2026-03-31

metadata.tags

recruiting, hiring, sourcing, interviews, employer-brand

# [Job Title] - [Level]

## About [Company]
[2-3 sentences: mission, stage, team size]

## The Role
[What the person will own and why it matters to the business]

## Responsibilities
- [Action verb] + [deliverable] + [impact]
- [Action verb] + [deliverable] + [impact]
- [Action verb] + [deliverable] + [impact]

## Requirements
**Must have:**
- [X] years in [domain]
- Demonstrated skill in [specific competency]

**Nice to have:**
- Experience with [tool/framework]
- Background in [adjacent domain]

## Compensation
- Base: $[min]-$[max]
- Equity: [details]
- Benefits: [highlights]

## Hiring Process
1. Application review (48 hr)
2. Recruiter screen (30 min)
3. Hiring manager interview (45 min)
4. Skills assessment (1-2 hr)
5. Final panel (2-3 hr)
6. Offer

# Scorecard: [Candidate] for [Role]

**Interviewer:** [Name]
**Date:** [Date]
**Stage:** [Phone Screen / Technical / Final]

## Competency Ratings (1-5 scale)

| Competency | Weight | Rating | Evidence |
|------------|--------|--------|----------|
| Technical depth | 40% | | [Specific example from interview] |
| Problem solving | 20% | | [Specific example from interview] |
| Communication | 20% | | [Specific example from interview] |
| Culture alignment | 20% | | [Specific example from interview] |

**Weighted Score:** [calculated]

## Recommendation
[ ] Strong Hire  [ ] Hire  [ ] No Hire  [ ] Strong No Hire

## Key Strengths
-

## Key Concerns
-

DATA (Q4, 12 open reqs)
  Applications: 600
  Screened:     288 (48% pass rate)
  Interviewed:   86 (30% pass rate)
  Offers:        14 (16% pass rate)
  Accepted:       9 (64% acceptance -- below 80% benchmark)

BOTTLENECK ANALYSIS
  1. Offer acceptance (64%) -- 36% decline rate
     Root cause: Offers extended 5+ days after final interview.
     Candidates accept competing offers in the gap.

  2. Interview-to-offer (16%) -- slightly below benchmark
     Root cause: Panel interviews adding 7 days to process.

ACTIONS
  1. Compress offer timeline: verbal offer within 48 hr of final interview
  2. Replace 4-person panel with 2 focused 1:1s (saves 5 days)
  3. Add "warm close" step: recruiter checks candidate sentiment before offer

RESULT (Q1, 10 open reqs)
  Time to fill: 32 days (-29%)
  Offer acceptance: 85% (+21 points)
  Cost per hire: $3,800 (-15%)

# Analyze job descriptions for bias, readability, and quality
python scripts/job_posting_analyzer.py --file job_description.md
python scripts/job_posting_analyzer.py --file job_description.md --json

# Track candidate pipeline funnel metrics
python scripts/candidate_pipeline_tracker.py --file pipeline.csv
python scripts/candidate_pipeline_tracker.py --file pipeline.csv --json

# Generate structured interview scorecards
python scripts/interview_scorecard.py --role "Senior Engineer" --level IC3
python scripts/interview_scorecard.py --role "Product Manager" --level IC2 --json

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in hr-operations/talent-acquisition of borghei/Claude-Skills.

• SKILL.md
• scripts/candidate_pipeline_tracker.py
• scripts/interview_scorecard.py
• scripts/job_posting_analyzer.py

Open the folder on GitHubat commit 4a698e8