Orchestrator/privat/CV/.kiro/skills/consultant-profile/SKILL.md

---
name: consultant-profile
description: Generates tailored consultant profiles (one-pager) from knowledge base data, matched against a specific RFP or project description.
activation: manual
---

# consultant-profile

Generates consultant/personnel profiles tailored to a specific RFP (Request for Proposal) or project description. Produces an HTML one-pager optimized for A4 landscape PDF export, using the d-hive Corporate Design (white background, black accents, neon green highlights). Outputs to `output/profiles/`.

## Activation

Activated by user request with an RFP or project context. Example triggers:
- "create a consultant profile for this RFP"
- "I need a personnel profile for an offer"
- "generate a Berater-Profil for [project]"
- "write a one-pager for [client]"

## Inputs

- **RFP / Leistungsbeschreibung** (required): The requirements document or project description to match against. Used to select relevant skills, projects, and experience.
- **Person ID** (optional): Which profile to generate for. Defaults to the primary profile.
- **Output filename** (optional): Custom filename. Defaults to `<person-id>-berater-profil`.
- **Role in project** (optional): The specific role the person will fill (e.g., "Projektleitung, KI-Beratung & Entwicklung, Workshop-Moderation").

## Workflow

### 1. Load person profile

- Read the target person profile from `kb/profiles/<person-id>.yaml`
- Read `kb/graph-index.yaml` to discover related entities
- Load all referenced entities: skills, experiences, projects, certifications, organizations

### 2. Analyze RFP requirements

- Extract required competencies from the RFP (fachliche, methodische, sonstige)
- Identify required references/project experience
- Note any specific constraints (availability, location, certifications)

### 3. Match and prioritize

- Map person's skills to RFP requirements — highlight direct matches
- Select the most relevant project experiences (max 5) that demonstrate required competencies
- Prioritize: direct match to RFP context > recent > high-impact
- Flag gaps where the person may not fully match (for user review)

### 4. Generate HTML one-pager

Structure (A4 landscape, 3-column layout):

**Header:**
- Profile photo (circular, from project root)
- Name + Job title ("Mensch-Maschine-Moderator")
- Contact meta (location, website, LinkedIn, email)
- d-hive logo (same height as photo)

**Kurzprofil:**
- 2-3 sentence summary emphasizing relevance to the RFP

**Column 1 — Kompetenzen:**
- Fachliche Kompetenzen (skill tags, highlighted = direct RFP match)
- Methodische Kompetenzen (skill tags)
- Zertifizierungen (checklist)

**Column 2 — Projekterfahrung:**
- Up to 5 reference boxes (most relevant first, "featured" styling for top matches)
- Publikationen section below

**Column 3 — Werdegang & Company:**
- Beruflicher Werdegang & Ausbildung (2-column sub-grid)
- Publikationen (if not in column 2)
- Data Hive Cassel company box (green top-border)

**Stats Bar (footer):**
- Key numbers in neon green on black background

### 5. Apply Corporate Design

- **Background:** White (#ffffff)
- **Text:** Near-black (#1a1a1a)
- **Accent/Highlights:** Neon green (#39ff14 / #2bcc0f)
- **Cards:** Light gray (#f6f6f6) with subtle border
- **Featured elements:** Green left-border (3px)
- **Section titles:** Neon green, uppercase, small
- **Stats bar:** Black background, neon green numbers (only large dark element)
- **Skill tags highlighted:** White background, green border
- **Logo:** `assets/d-Hive_logo_darkText_transparent_crop.png` (for white background)
- **Photo:** `assets/230823_Einfachbahn_Andre-brillenlos-hochformat.png` (circular crop)

### 6. Write outputs

- Write HTML to `output/profiles/<filename>.html`
- Optionally write a Markdown summary to `output/profiles/<filename>.md`
- Present to user for review

## Output

- HTML one-pager: `output/profiles/<filename>.html` — print as PDF via browser (Ctrl+P, landscape, no margins)
- Optional Markdown: `output/profiles/<filename>.md` — quick-reference version

## Corporate Design Reference

The d-hive CD uses:
- **Colors:** Black (#0a0a0a) + Neon Green (#39ff14)
- **On white backgrounds:** Use black for structure, neon green for highlights/accents
- **On dark backgrounds:** Use neon green for text highlights
- **Logo variants:** `assets/d-Hive_logo_darkText_transparent_crop.png` (light bg), `assets/d-Hive_logo_transparent_crop.png` (dark bg)
- **Typography:** Inter (Google Fonts), clean and modern
- **Principle:** Neon green = signal/focus, black = structure/anchor, white = breathing room

## Key Facts (for stats bar)

- 50+ Projekte
- 15+ Kunden
- 13+ Jahre KI-Erfahrung (erste ML-Publikation 2012)
- 60+ wissenschaftliche Veröffentlichungen, 2.000+ Zitationen
- 6 Live Use Cases (Projekt KIQ)
- 100% DSGVO & AI-Act konform

## Shared Modules

- `src/schemas/validate.ts` — Entity validation
- `src/schemas/types.ts` — TypeScript type definitions
- `src/io/yaml-utils.ts` — YAML serialization/deserialization
- `src/io/entity-files.ts` — Entity file read management
- `src/cv/relevance-selection.ts` — Relevance matching logic

## Rules and Constraints

1. **No fabrication** — only include information present in the knowledge base
2. **RFP-driven** — prioritize skills and experience that match the RFP requirements
3. **One page** — HTML must fit on a single A4 landscape page when printed
4. **CD compliance** — follow d-hive Corporate Design (black + neon green on white)
5. **Photo required** — always include the profile photo
6. **Logo required** — always include the d-hive logo at same height as photo
7. **No team stats** — profile is personal; don't include team-level metrics (e.g., "30+ Jahre Erfahrung im Team")
8. **Featured projects** — mark the 1-2 most relevant projects with green left-border
9. **Google Scholar link** — always link to the scholar profile in publications
10. **Print-optimized** — use @page CSS for clean PDF export, no overflow