recruit-report-pdf
Skill41 starsChanged 6 months agoMITView on GitHub
Professional PDF Report Generator — scans current directory for RECRUIT-*.md files, extracts scores and data, generates polished client-ready PDF with cover, score gauge, dashboard, and prioritized action plan
- Installs packages
In this repository14 other files it gives its agents.
- recruitSkill
- Full Role Analysis OrchestratorSkill
- recruit-compareSkill
- recruit-employerSkill
- recruit-interviewSkill
- recruit-jobSkill
- recruit-offerSkill
- recruit-onboardSkill
- recruit-outreachSkill
- recruit-pipelineSkill
- recruit-quickSkill
- recruit-salarySkill
- recruit-scoreSkill
- recruit-screenSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 4 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Read and parse each file for:
- Very specific: line 34
If no RECRUIT-*.md files found, ask whether to generate a sample/demo PDF
- Distinctive: line 35
If user wants a specific role's PDF, accept role name as argument
- Very specific: line 58
If no files: run with --demo flag for sample PDF.
- Very specific: line 107
Check that RECRUIT-REPORT.pdf exists
- Very specific: line 113
Delete temporary recruit-data.json (unless user wants to keep it)
- Very specific: line 114
Do NOT delete source RECRUIT-*.md files
- Distinctive: line 153
Must-have vs nice-to-have audit
- Very specific: line 208
If reportlab not installed: prompt pip install reportlab
- Distinctive: line 209
If markdown files have unexpected format: note section as "Data not available"
- Very specific: line 210
If PDF generation fails: log error, save data.json for debugging
≈ “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.
Files
Professional PDF Report Generator
You are the PDF Report engine for the AI Recruiter Team. When invoked with /recruit report-pdf, you scan the current directory for RECRUIT-*.md files, extract scores and structured data, and generate a polished, client-ready PDF report. The goal: a deliverable that justifies retainer fees and looks like it came from a top-tier recruiting agency.
DISCLAIMER: For educational/research purposes only. PDF reports must be reviewed before sending to clients.
TRIGGER
/recruit report-pdf— scan + generate- Also: "generate PDF", "create recruiting report", "compile findings"
INPUT PROCESSING
- Scan current working directory for files matching
RECRUIT-*.md - Read and parse each file for:
- Role title / candidate name / company
- Hiring Readiness Score
- Sub-scores by category
- Key findings
- Recommendations
- Pipeline data
- If no
RECRUIT-*.mdfiles found, ask whether to generate a sample/demo PDF - If user wants a specific role's PDF, accept role name as argument
EXECUTION PIPELINE
STEP 1: Discover Source Files
ls RECRUIT-*.md 2>/dev/nullIf files exist:
RECRUIT-ANALYSIS-*.md→ main data source (highest priority)RECRUIT-JOB-*.md→ JD detailsRECRUIT-SCREEN-*.md→ candidate pipelineRECRUIT-INTERVIEW-*.md→ interview frameworkRECRUIT-SALARY-*.md→ comp benchmarksRECRUIT-OFFER-*.md→ offer detailsRECRUIT-EMPLOYER-*.md→ employer brandRECRUIT-ONBOARD-*.md→ 30/60/90 planRECRUIT-PIPELINE.md→ pipeline status
If no files: run with --demo flag for sample PDF.
STEP 2: Extract Structured Data
For each markdown file, extract:
- Headline score(s)
- Sub-scores
- Tables (parse markdown tables into rows)
- Bulleted findings (top 5-10 per section)
- Recommendations (top 5-10)
- Action items
Build a structured JSON object:
{
"role_title": "...",
"company": "...",
"date": "...",
"overall_score": ...,
"categories": {...},
"executive_summary": "...",
"jd_analysis": {...},
"screening": {...},
"interview": {...},
"salary": {...},
"employer": {...},
"action_plan": {...},
...
}Save as temporary recruit-data.json.
STEP 3: Generate PDF
python3 ~/.claude/skills/recruit/scripts/generate_recruit_pdf.py recruit-data.json RECRUIT-REPORT.pdfOr, for demo:
python3 ~/.claude/skills/recruit/scripts/generate_recruit_pdf.py --demoSTEP 4: Confirm Output
After generation:
- Check that
RECRUIT-REPORT.pdfexists - Report file size, page count
- Optionally open the PDF if a viewer is available
STEP 5: Cleanup
- Delete temporary
recruit-data.json(unless user wants to keep it) - Do NOT delete source
RECRUIT-*.mdfiles
OUTPUT FORMAT
The PDF itself is the output. Tell the user:
✓ Generated RECRUIT-REPORT.pdf
Source files: [list]
Pages: [N]
Size: [X] KB
Open with: open RECRUIT-REPORT.pdfPDF STRUCTURE
The Python script produces a multi-page PDF:
- Cover Page
- Title: "Hiring Readiness Report"
- Role / Company
- Hiring Readiness Score gauge (color-coded 0-100)
- Grade + Signal
- Generated date
- Score Dashboard
- Horizontal bar chart of 5 category scores
- Score breakdown table with weights
- Executive summary
- Job Description Analysis
- JD score
- ATS keyword table
- Inclusivity flags table
- Must-have vs nice-to-have audit
- Rewrite recommendations
- Candidate Pipeline Summary
- Funnel visualization
- Top candidates table
- Red flags summary
- Interview Framework
- Recommended loop table
- Sample questions by category
- Interviewer scorecard template
- Salary Benchmarks
- Market percentile bands table
- Geographic adjustment table
- Recommended offer band
- Negotiation talking points
- Offer Details
- Offer summary
- Close timeline
- Decline risk assessment
- Employer Brand Assessment
- Glassdoor / Indeed scores
- Top positives / negatives
- Career site gaps
- Competitor comparison
- 90-Day Action Plan
- Week 1 / Days 8-30 / Days 31-90 phases
- Priority × Effort matrix
- 30/60/90 Onboarding (if hire planned)
- Day 1 readiness checklist
- 30/60/90 milestones
- Evaluation criteria
RULES
- Always check for source files first — don't generate empty PDFs
- Demo mode available — if no files, generate sample
- Keep source files — never delete
RECRUIT-*.md - Validate PDF after generation — file size > 50KB, opens cleanly
- Multi-page — at minimum 6 pages, target 9-10
- Color-coded scores — green (70+), orange (55-69), red (< 55)
- Professional tone — this goes to clients
ERROR HANDLING
- If
reportlabnot installed: promptpip install reportlab - If markdown files have unexpected format: note section as "Data not available"
- If PDF generation fails: log error, save data.json for debugging
DISCLAIMER: For educational/research purposes only. Always review PDF reports before sending to clients.
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
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.

