zal4dw/career-helper/employer-footprint

Employer Footprint Analysis

See yourself through an employer's eyes. A deep-research swarm audit of your digital footprint, synthesised into a credit-report style dashboard with actionable recommendations.

Capabilities

Quick Start

"Check my digital footprint before I apply to the NHS"
"What would a recruiter find if they searched for me online?"
"Audit my LinkedIn and Twitter for red flags"
"Generate interview questions based on what's publicly visible about me"

Accessibility

At skill start, check for career-helper-preferences.md in the current working directory using the Glob tool. If found, read the YAML frontmatter and apply:

• dyslexia_friendly: true → Use short sentences. Number all lists and options (never unnumbered). One decision per message. No idioms or metaphors; use plain replacements. Explicit signposting at every transition ("Step 2 of 4. Next: employer impression report."). Refer to saved files by description, not filename. Repeat key details (company names, role titles, dates); do not assume the user remembers from earlier messages.
• colour_blind: true → Never use colour alone to convey meaning. Use labels, text, or icons for all status indicators. Dashboard scores must use text labels, not colour coding.

If no preferences file exists and this skill was invoked directly (not dispatched by Tim): ask once, "Do you have any accessibility preferences I should know about? For example, if you're dyslexic, I can adjust how I format things." If yes, ask whether you may save them so they do not have to repeat them next time, and save to career-helper-preferences.md using the format in @../tim/references/tim-preferences-format.md only if they agree. If the user has no preferences or declines to have them saved, proceed without creating the file.

These rules apply to all communication with the user and to the formatting of output documents.

How It Works

This skill uses an agentic deep-research swarm approach:

1. You provide your name, CV, social media handles, and target company/role
2. Parallel research agents scan publicly available data across multiple channels simultaneously
3. Employer lens analysis interprets findings through the target company's values and culture
4. Dashboard synthesis produces a credit-report style output with positive/negative indicators
5. Recommendations suggest next actions across career-helper skills

Input Gathering

Before starting any analysis, collect the following via AskUserQuestion:

Required Information

Question 1: Basic Details "To analyse your digital footprint, I need some details. Let's start with the basics - what is your full name (as it appears professionally)?"

Question 2: Social Media Handles "Which social media platforms do you use? Please share your usernames/URLs for any that apply:"

• LinkedIn profile URL
• GitHub username
• Twitter/X handle
• Personal website or blog URL
• Any other professional platforms (Medium, Stack Overflow, Behance, Dribbble, YouTube, etc.)

Question 3: Target Context "Are you targeting a specific company and role? If so, please share:"

• Company name
• Role title
• Job description (if available)

Question 4: CV "Please share your CV - either paste the text, provide a file path, or upload it."

Question 5: Concerns "Is there anything specific you're worried an employer might find? (This helps me focus the analysis - everything stays private.)"

1. Full Footprint Analysis

What you need: Name + social handles + CV + target company/role (optional) Load: @references/digital-footprint-audit.md Template: @references/footprint-dashboard-template.md

Agentic parallel research covering:

Research Swarm Architecture

Launch parallel research agents for each channel simultaneously:

┌─────────────────────────────────────────────────────────────┐
│              EMPLOYER FOOTPRINT RESEARCH SWARM              │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│   ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐  │
│   │ Agent 1  │  │ Agent 2  │  │ Agent 3  │  │ Agent 4  │  │
│   │ Google   │  │ LinkedIn │  │ Twitter/ │  │ GitHub   │  │
│   │ Presence │  │ Analysis │  │ X Audit  │  │ Profile  │  │
│   └────┬─────┘  └────┬─────┘  └────┬─────┘  └────┬─────┘  │
│        │             │             │             │          │
│   ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐  │
│   │ Agent 5  │  │ Agent 6  │  │ Agent 7  │  │ Agent 8  │  │
│   │ Other    │  │ News &   │  │ Company  │  │ Red Flag │  │
│   │ Socials  │  │ Media    │  │ Culture  │  │ Scanner  │  │
│   └────┬─────┘  └────┬─────┘  └────┬─────┘  └────┬─────┘  │
│        │             │             │             │          │
│        └──────┬──────┴──────┬──────┴──────┬──────┘          │
│               │             │             │                 │
│         ┌─────▼─────────────▼─────────────▼─────┐          │
│         │       SYNTHESIS & DASHBOARD ENGINE      │          │
│         │                                         │          │
│         │  • Score each dimension (1-10)           │          │
│         │  • Flag positives and negatives          │          │
│         │  • Map to employer values                │          │
│         │  • Generate recommendations              │          │
│         └─────────────────────────────────────────┘          │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Channels Audited

Scoring Dimensions

Each dimension scored 1-10 with text-label rating (GREEN/AMBER/RED):

Output: {name-slug}-footprint-dashboard.md

2. Social Media Audit

What you need: Social media handles for specific platforms Load: @references/social-media-audit.md

Focused deep-dive into specific social channels:

• Platform-by-platform analysis
• Content tone assessment
• Privacy settings check (what's publicly visible)
• Recruiter-eye-view of each profile
• Specific recommendations per platform

Output: {name-slug}-social-media-audit.md

3. Employer Impression Report

What you need: Name + CV + target company name + role Load: @references/employer-impression-analysis.md Template: @references/footprint-dashboard-template.md Also Load: @references/digital-footprint-audit.md

The full footprint analysis interpreted specifically through the lens of the target employer:

• Company values and culture research (parallel with footprint analysis)
• Map your digital presence against their stated values
• Identify aspects of your experience to prioritise based on company needs
• Flag any misalignments between your online presence and their culture
• Generate talking points that leverage your digital presence positively

Output: applications/{role-slug}/{name-slug}-{company-slug}-employer-impression.md if an application folder exists for this company; otherwise {name-slug}-{company-slug}-employer-impression.md in the workspace root

4. Interview Questions from Footprint

What you need: Completed footprint analysis or employer impression report Load: @references/interview-questions-from-footprint.md

Generate likely interview questions based on what's publicly visible:

• Questions about specific projects or roles mentioned online
• Questions probing gaps or inconsistencies found
• Questions about controversial or interesting content discovered
• Questions that leverage your strongest public signals
• Preparation strategies for each question category

Output: {name-slug}-footprint-interview-questions.md

Deep Research Validation

All research uses a rigorous multi-cycle validation workflow: Load: @references/deep-research-reflection.md

• Gap Analysis - After initial search, identify what's missing
• Counter-Evidence Search - Actively search for contradicting information
• Source Credibility Scoring - Primary sources weighted over secondary
• Red Flag Hunting - Proactively search for negative/controversial content
• Citation Requirements - All findings include source URLs and access dates

Research Approach

The audit covers several independent sources (search-engine presence, LinkedIn, X/Twitter, GitHub, and the target company's culture and values), so run that research in parallel with Task sub-agents and parallel WebSearch calls rather than one source at a time. Use Sonnet for these research sub-agents; it searches and extracts well at a lower cost, and the scoring and recommendations stay with the main model.

Once the first pass is back, look for what is missing: flagged content that needs a closer look, claims on the CV that the online presence does not support, and counter-evidence or red flags the first searches did not surface. Search for those next. Then score every dimension, generate the dashboard, map the findings to the employer's values, and write the recommendations.

Persona Adaptation

When the user's context matches a specific persona, adapt the analysis focus: