Auditjobposting

Configuration

Read .jobops/config.json. If missing, stop with:

JOBOPS NOT CONFIGURED Run /jobops:setup to initialize your workspace.

Use config.directories.<key> for all file paths in this skill. Use config.preferences.cultural_profile if this skill generates resume-style content. Use config.preferences.default_jurisdiction if this skill has jurisdiction-sensitive logic (crisis/legal skills accept --jurisdiction=<ISO-3166-2> to override).

Application Path Resolution

This skill writes to a per-application folder. Before writing any output:

1. Parse {Company}_{Role}_{YYYYMMDD} from the job-posting filename, or honor --app=<slug> if supplied. The slug MUST be canonical: a leading PascalCase {Company} token (matching the Company_Intelligence/{Company}/ folder so OSINT links), a PascalCase {Role} (underscores between words allowed), and a trailing compact 8-digit date (20260519 — no hyphens, no time). Reject leading date/time prefixes such as 2026-04-15_214414_...; if the source filename carries one, recompose it into canonical form ({Company}_{Role}_{YYYYMMDD}) before composing the folder path.
2. Compose the app folder: {config.directories.applications_root}/{app_slug}/.
3. Resolve this skill's sub-folder by category:
   • resume-development (buildresume, provenance-check) → resume/
   • cover-letter (coverletter) → cover-letter/
   • rubric / assessment (createrubric, assessjob, assesscandidate, auditjobposting) → assessment/
   • briefing / interview prep (briefing, interviewprep) → interview/
4. If the app folder does not exist, mkdir -p it, then copy {config.directories.job_postings}/{filename} → {app_slug}/job_posting.md so the pinned JD cannot silently change under completed work. Ensure the pinned copy begins with YAML front matter carrying output_type: job_posting: if the source JD already has a front-matter block, add the key to it; otherwise wrap a new block (--- / output_type: job_posting / source_jd: {filename} / ---) above the JD body.
5. Exact-slug collisions (same Company+Role+Date) are not auto-suffixed. If the folder already contains the same output type, require the user to pass --app=<distinct-slug>.
6. Output filename (fixed; only the sub-folder above is resolved dynamically): write the audit to assessment/job_audit.md.

Your Task

Analyze the job posting at {config.directories.job_postings}/{{ARG1}} (add .md extension if needed) using a rigorous 100-point scoring rubric that identifies red flags, unrealistic expectations, and posting quality issues that job seekers should consider before applying.

Why This Matters

Many job postings contain:

• Impossible requirements: "10 years of Kubernetes experience" when Kubernetes is ~10 years old
• Unicorn hunting: Asking for skills across 4-5 distinct job roles
• Compensation disconnects: Entry-level pay for senior expectations
• Hidden dysfunction: Vague language masking organizational chaos
• Internal contradictions: Title/seniority/responsibility mismatches

This audit helps job seekers make informed decisions about which opportunities are worth pursuing.

JOB POSTING QUALITY AUDIT RUBRIC (100 Points)

Category 1: Internal Consistency (25 Points)

Evaluates whether the posting is internally coherent and free of contradictions.

1.1 Title-Seniority-Responsibility Alignment (8 points)

Evaluation Checklist:

• Does the title reflect actual seniority level?
• Do responsibilities match the level implied by the title?
• Is there consistency between role level and decision-making authority?
• Do reporting relationships align with title hierarchy?

1.2 Experience Requirements Coherence (7 points)

Evaluation Checklist:

• Are experience requirements appropriate for the role level?
• Is there clear distinction between "required" and "preferred"?
• Do experience ranges make sense (not impossibly broad)?
• Are industry-specific experience needs realistic?

1.3 Skills-Duties Alignment (5 points)

Evaluation Checklist:

• Is every required skill actually used in described duties?
• Are listed technologies mentioned in responsibilities?
• Do "preferred" skills relate to actual job functions?

1.4 Reporting Structure Clarity (5 points)

Evaluation Checklist:

• Is the direct manager/reporting line clear?
• Is team size and composition described?
• Are cross-functional relationships defined?
• Is individual contributor vs. management role clear?

Category 2: Market Realism (25 Points)

Evaluates whether the requirements reflect reality in the current job market.

2.1 Technology Timeline Validity (8 points)

Technology Release Reference (verify and calculate fresh age):

• Kubernetes (launched 2014)
• Docker (launched 2013)
• React (launched 2013)
• TypeScript (launched 2012)
• Go/Golang (launched 2009)
• Terraform (launched 2014)
• AWS Lambda (launched 2014)
• ChatGPT/GPT-4 (launched 2022-2023)
• LangChain (launched 2022)
• Azure OpenAI (launched 2023)

Use the release years above (or updated research) to calculate how many years of experience are mathematically possible relative to the current year—never rely on stale "~X years old" notes.

Evaluation Checklist:

• Research age of each mentioned technology
• Calculate if experience requirements are mathematically possible
• Flag any "impossible timeline" requirements
• Note technologies where experience asks are borderline

2.2 Skill Breadth Feasibility (7 points)

Skill Domain Categories for Analysis:

• Frontend: React, Vue, Angular, CSS, UX design
• Backend: APIs, databases, server architecture
• DevOps/Infrastructure: CI/CD, cloud platforms, containers
• Data/ML: Data engineering, ML models, analytics
• Management: Team leadership, project management, stakeholder relations
• Security: Penetration testing, compliance, security architecture
• Mobile: iOS, Android, React Native
• Specialized: Embedded systems, blockchain, game development

Evaluation Checklist:

• How many distinct skill domains are required?
• Are they hiring for 1 job or 3+ jobs combined?
• Would a realistic candidate have this skill breadth?
• Is the combination achievable within one career path?

2.3 Candidate Pool Reality (5 points)

Evaluation Checklist:

• Could you realistically find 10+ candidates who match?
• Is the intersection of required skills commonly found?
• Are they demanding niche expertise + broad generalist skills?

2.4 Geographic Market Alignment (5 points)

Evaluation Checklist:

• Does location have sufficient talent pool?
• Is remote work offered for roles requiring niche skills?
• Are relocation expectations reasonable?
• Does on-site requirement match role complexity?

Category 3: Compensation Assessment (20 Points)

Evaluates whether compensation is realistic and competitive.

3.1 Salary-Role Alignment (7 points)

Research Required:

• Search for similar roles on levels.fyi, Glassdoor, LinkedIn Salary Insights
• Compare to market rates for the specific responsibilities
• Factor in company stage (startup vs. enterprise)

3.2 Salary-Experience Alignment (5 points)

3.3 Salary-Location Alignment (4 points)

3.4 Total Compensation Transparency (4 points)

Unavailable compensation data: When the posting omits explicit pay details, mark 3.4 according to the level of opacity but still score 3.1-3.3 using the best available market proxies (Levels.fyi, historical internal data, similar postings). Note the inference source inside your audit so candidates understand the confidence level.

Category 4: Role Scope & Definition (20 Points)

Evaluates whether this is a well-defined, achievable role.

4.1 Single Role Focus (6 points)

Evaluation Checklist:

• Can the responsibilities be performed by one person?
• Is the role focused or scattered across domains?
• Does it combine incompatible work styles (e.g., deep focus IC + meeting-heavy manager)?

4.2 Responsibility Clarity (5 points)

Red Flag Phrases:

• "Other duties as assigned" (excessive use)
• "Wear many hats"
• "Fast-paced environment" (often means chaos)
• "Self-starter" (often means no support)
• "Rockstar/ninja/guru" (often means unrealistic expectations)

4.3 Success Metrics Clarity (5 points)

4.4 Growth Path Visibility (4 points)

Category 5: Red Flag Assessment (10 Points)

Evaluates organizational health and cultural signals.

5.1 Professional Language Quality (3 points)

Red Flag Language:

• Excessive exclamation points!!!
• "Family" culture (often means boundary violations)
• "Unlimited PTO" (often means no PTO)
• "Work hard, play hard" (often means overwork)
• "Wearing many hats" (often means understaffed)

5.2 Organizational Health Signals (3 points)

Research Required:

• Check Glassdoor reviews for team/department
• Look for turnover patterns in role
• Research company news for layoffs, restructuring

5.3 Process Transparency (2 points)

5.4 Work-Life Balance Signals (2 points)

SCORING INTERPRETATION

EXECUTION PROTOCOL

Step 1: Load and Parse Job Posting

✓ Reading job posting from {config.directories.job_postings}/{{ARG1}}

Read the job posting file and extract:

• Job title and seniority level
• Company name and location
• All required skills and experience
• All preferred/nice-to-have items
• Responsibilities and duties
• Compensation information (if present)
• Team structure and reporting
• Company culture signals

Step 2: Conduct Market Intelligence Research

Use web search to gather:

Access constraints: If the CLI session lacks network access or required sources are paywalled, rely on previously gathered benchmarks, local reference material, or reasonable industry heuristics. Document the missing research explicitly in your audit (e.g., "Glassdoor data unavailable in offline mode") so reviewers know which assumptions require follow-up.

1. Technology Age Verification

   • Research release dates for all mentioned technologies
   • Calculate if experience requirements are possible

2. Salary Benchmarking

   • Search levels.fyi, Glassdoor, LinkedIn for role + location
   • Determine market rate for similar positions

3. Company Intelligence

   • Check Glassdoor reviews (especially recent ones)
   • Search for recent news (layoffs, growth, funding)
   • Look for employee sentiment on LinkedIn/Blind

4. Role Market Analysis

   • How common is this skill combination?
   • What do similar postings require?
   • Is this unicorn hunting or reasonable?

Step 3: Apply Scoring Rubric

For each of the 5 categories:

1. Evaluate each subcategory using the rubric criteria
2. Assign point scores with justification
3. Cite specific evidence from the posting
4. Note any red flags or concerns

Step 4: Generate Comprehensive Audit Report

Create a detailed report with:

4.1 YAML Frontmatter

---
job_file: {config.directories.job_postings}/{{ARG1}}
role: <role title>
company: <company name>
location: <location>
posting_date: <date from job posting, or "Not specified">
generated_by: /auditjob
generated_on: <ISO8601 timestamp>
output_type: job_posting_audit
status: final
version: 1.0
overall_score: <XX/100>
grade: <A/B/C/D/F>
recommendation: <pursue/caution/avoid>
---

4.2 Job Posting Header (REQUIRED - Display Prominently at Top)

Immediately after the YAML frontmatter, display a prominent header block with key job information:

# Job Posting Quality Audit Report

## [JOB TITLE]
**Company:** [COMPANY NAME]
**Posting Date:** [DATE from job posting, e.g., "Nov 24, 2025" or "Not specified"]
**Location:** [LOCATION]

---

This header MUST appear at the very top of the report (after frontmatter) so readers immediately know which job is being audited. Extract the posting date from within the job posting file if available (look for "Date:", "Posted:", "Deadline:", or similar fields).

4.3 Executive Summary

• Overall score and grade
• 2-3 sentence assessment
• Primary recommendation

4.4 Detailed Scoring Breakdown

For each category, provide:

• Category score (X/Y points)
• Subcategory breakdowns with evidence
• Specific findings and concerns

Recommended table template (expand rows as needed):

4.5 Red Flags Identified

• List all red flags found
• Severity assessment
• Impact on candidate decision

4.6 Questions to Ask in Interview

Based on audit findings, generate 5-7 questions the candidate should ask to clarify concerns:

• Address identified inconsistencies
• Probe organizational health signals
• Clarify scope and expectations

4.7 Competitive Intelligence

• How does compensation compare to market?
• Is this role well-positioned vs. similar opportunities?
• Any leverage points for negotiation?

4.8 Final Recommendation

• Clear pursue/caution/avoid recommendation
• Key decision factors
• What would change the assessment

Step 5: Save Audit Report

Resolve {app_slug} per the Application Path Resolution protocol at the top of this skill, and ensure {applications_root}/{app_slug}/assessment/ exists (mkdir -p). Pin the JD to {applications_root}/{app_slug}/job_posting.md if not already present.

Save Location: {applications_root}/{app_slug}/assessment/job_audit.md

This co-locates the audit alongside any rubric/assessment that already lives in the same app folder, and the app folder itself is the self-contained container — no timestamped sub-folder is required.

Example Analysis Application

Given the HONI_Data_Services_Manager.md posting:

Internal Consistency Issues:

• Title says "Data Services Manager" but LinkedIn addendum says "AI Engineer"
• Manager responsibilities listed but technical AI skills demanded
• Potential title-role mismatch

Market Realism Issues:

• LangChain: ~2-3 years old
• Azure OpenAI: ~2 years old
• Any requirement for 5+ years in these is impossible

Scope Issues:

• Official posting: People management focus
• LinkedIn addendum: Deep technical AI focus
• These are two different jobs

This type of analysis should be applied systematically to the target posting.

Error Handling

• Missing job posting: Report if file not found; suggest available alternatives in {config.directories.job_postings}/
• No compensation data: Note as N/A; research market rates for comparison
• Insufficient company info: Document gaps; recommend additional research
• Conflicting information: Flag as major inconsistency; document both versions

Important Notes

• Objectivity: Score based on evidence, not assumptions
• Candidate Perspective: This audit serves job seekers, not employers
• Actionable Output: Provide practical guidance for application decisions
• Evidence-Based: Cite specific passages from the posting for all findings
• Web Research Required: Technology ages and salary data must be verified
• Honesty: Don't soften findings; job seekers deserve accurate assessments