<p align="center">
<img src="assets/header.webp" alt="Creative Director Skill" width="100%">
</p>
<h1 align="center">There is no creativity in AI.<br>There are the methodologies of winners.</h1>
<p align="center"><sub>Креатива в AI нет. Есть методологии победителей.</sub></p>
<h1 align="center">🎬 Creative Director Skill</h1>
[](https://docs.anthropic.com)
[](LICENSE)
[](#methodologies-20)
[](#case-library)
[](#whats-new-in-v20)
[](https://cd-skill.com)
**🇷🇺 [Читать на русском](README.ru.md)**
<a href="https://cd-skill.com">
<img src="assets/cd-skill-site.webp" alt="cd-skill.com — full method breakdown, all 20 techniques and the pipeline" width="100%">
</a>
<p align="center"><b>🌐 Full method breakdown, all 20 techniques and the pipeline → <a href="https://cd-skill.com">cd-skill.com</a></b></p>
> Created in collaboration with **Paul Deadcough**.
An AI creative director that generates advertising concepts using world-class methodologies, scores them against Cannes/D&AD-calibrated criteria, recursively refines until the quality threshold is reached, and **calibrates every idea against a library of 571 legendary campaigns** to detect saturation and ensure originality.
Not a brainstorming toy. A structured creative process that mirrors how top agencies (Droga5, Wieden+Kennedy, Mother) actually work — insight before ideas, methodology over free association, honest evaluation over flattery, **calibration against the canon** over invention from zero.
---
## What's New in v2.0
- **571-case library** with full Insight / Mechanic / Why-it-worked / Steal structure on every card
- **17-axis frontmatter schema** — every card tagged across pattern (P01-P18), industry, format, emotion (Tier 1/2/3), budget, idea_type (Pollard 7-level), awards, and more
- **6 MOCs** (Maps of Content) for fast lookup by pattern, emotion, format, industry, budget, and chronological index
- **4-point case library integration** in workflow — priming before generation, originality empirical cap, RESTART case-soaking, pattern calibration before exit
- **3 maintenance scripts** (Python via `uv`) — schema validation, MOC generation, graph wikilinks
- **Pollard 7-level idea taxonomy** replacing the previous 3-level system
- **3-tier emotion hierarchy** with 30+ specific emotion values
- **Activation toolkit** with 9 formats and the Non-advertising vs Execution test
- **Pre-Mortem template** before final delivery
Quality reviewed via [`skill-conductor`](https://github.com/smixs/skill-conductor): **41/50 production-grade** (Discovery 7/10, Clarity 9/10, Efficiency 7/10, Robustness 8/10, Completeness 10/10).
---
## What It Does
Feed it a brief in any format — text, voice transcript, PDF, raw notes — and it runs a full creative cycle:
<img src="assets/pipeline-phases.webp" alt="Pipeline: 5 phases from brief to idea — intake, insight, ideas, evaluate, articulate; phase 04 loops until the idea is strong" width="100%">
1. **INTAKE** — extracts the brief's DNA: product, audience, objectives, constraints + classifies the required idea level using Pollard 7-level taxonomy (business / brand / tagline / advertising / campaign / non_advertising / execution)
2. **INSIGHT** — mines consumer insights using 7 proven techniques (Mark Pollard, JTBD, Tension Spotting, HMW, Abstraction Laddering)
3. **IDEATION** — primes against the canon (scans 5-7 cases from the relevant MOC), then generates 8-12 ideas using 3 methods from different categories (structural × associative × disruptive), rotating between 20+ methodologies, with a Tension test on each
4. **EVALUATE + REFINE** — scores against 6 weighted criteria + HumanKind + Grey Scale, then recursively improves; **Originality is capped empirically** by case-library saturation (3+ canonical cases of the same mechanic → cap at 7); when stuck, RESTARTs through case-soaking (read 8-12 canonical cards, remix allowed); Pattern Calibration + Pre-Mortem before exit
5. **ARTICULATE** — outputs in a presentation-ready format (one-pager, top-3, campaign platform, or quick response)
You can also enter at any phase: jump to insight mining, evaluate an existing idea, or generate concepts from a known insight.
## Why This Exists
Most AI "creative" tools generate ideas by free association — producing volume without structure. The result: hundreds of mediocre concepts that nobody can evaluate, often unknowingly recycling work that already exists.
<img src="assets/why-averaged.webp" alt="The model returns averaged and overplayed — without insight and structure, AI runs like a production line stamping the same thing" width="100%">
This skill enforces the discipline that separates award-winning work from filler:
- **Insight-first** — no ideation without a validated consumer tension
- **Structural methods** — SIT, TRIZ, SCAMPER, Bisociation, Synectics, not "give me 10 ideas"
- **Empirical originality** — every idea is checked against 571 real campaigns; if 3+ canonical cases use the same mechanic, originality is capped, not subjectively claimed
- **Honest scoring** — calibrated against real Cannes winners, with anti-inflation rules
- **Recursive refinement** — weak criteria get targeted improvement using different methods each pass
- **Case-soaking on plateau** — when ideas plateau, the skill reads 8-12 canonical cards to re-train its sense for what a strong insight feels like; combining/remixing existing patterns is explicitly allowed (this is how Cannes-grade work is built)
- **Kill Your Darlings** — the skill argues against its own favorite ideas to test their strength
- **Pre-Mortem** — before delivery, simulates failure and surfaces the most likely failure modes
## What's Inside
```
creative-director/
├── SKILL.md # Core skill — phase router + 5-phase workflow
├── assets/
│ └── output-templates.md # 4 presentation formats
├── scripts/ # Python via uv (PEP 723 inline deps)
│ ├── validate_schema.py # Frontmatter validation against tag-schema
│ ├── generate_mocs.py # Builds 6 MOCs from cards
│ └── generate_links.py # Adds Related sections (idempotent)
└── references/
├── tag-schema.md # Single source of truth — 17-axis frontmatter contract
├── idea-taxonomy.md # Pollard 7-level taxonomy
├── emotion-hierarchy.md # Tier 1/2/3 + 30+ specific emotion values
├── activation-toolkit.md # 9 activation formats + Non-ad vs Execution test
├── legendary-patterns.md # P01-P18 mechanics + Pre-Mortem template
├── methods-catalog.md # 20 creative methodologies as executable cards
├── method-selection-matrix.md # Task → method routing + rotation rules
├── insight-mining.md # 7 insight discovery techniques
├── scoring-calibration.md # Detailed rubrics + calibration anchors
├── creative-constitution.md # 3-layer evaluation system + feedback rules
├── storytelling-frameworks.md # 6 narrative frameworks for advertising
└── legendary-campaigns/ # 571-case library
├── README.md # Library guide
├── MOC-index.md # All 571 cards by year DESC
├── MOC-pattern.md # Grouped by P01–P18 (18 mechanics)
├── MOC-emotion.md # Grouped by emotion_tier (3 → 2 → 1)
├── MOC-format.md # Grouped by category (film/integrated/stunt_pr/...)
├── MOC-industry.md # Grouped by industry vertical
├── MOC-budget.md # Grouped by budget (low/medium/high)
└── cards/ # 571 individual cards (flat namespace)
└── {id}.md
```
## Case Library
571 advertising campaigns from 1950–2025, tagged across **17 axes**, with full structural analysis on every card.
<img src="assets/case-library.webp" alt="571 award-winning cases inside — each card breaks down the insight, the execution, why it worked, and what to steal as method" width="100%">
### Card structure
Each card has YAML frontmatter (17 axes — see `references/tag-schema.md`) + 4 sections:
- **Insight** — the human truth the campaign exploits (one sentence)
- **Mechanic** — what was actually executed
- **Why it worked** — psychological / cultural / structural reason
- **Steal** — pattern-level borrow strategy
- **Related** — auto-generated wikilinks (pattern hub + 2 sibling cards + emotion match)
### Tag schema (17 axes)
`id`, `title`, `brand`, `agency`, `year`, `country`, `region`, `industry`, `pattern[]` (P01–P18), `category`, `idea_type` (Pollard 7-level), `involvement`, `channel`, `duration`, `goal[]`, `budget`, `emotion[]`, `emotion_tier` (1/2/3), `insight_domain`, `media_epoch`, `awards[]`, `quality_score` (HumanKind 1–10), `scalability`, `risk`.
### 18 patterns (P01–P18)
Format as Idea · Enemy or Conflict · Behavior Inversion · Brand as Activist · Cultural Hijack · Limitation as Power · Invisible Brand · Craft as Message · User as Co-Author · Serialization & Ritual · Absurd as Carrier · Social Experiment · Truth Telling · Product as Proof · Benefit Hyperbole · Long-form Drama · Design as Idea · Tech as Canvas
### Lookup strategies
```bash
# Browse by axis — open the matching MOC
# Each line has inline-context (brand · year · format · emotion · budget · top_award)
# Filter by combination — ripgrep on frontmatter
rg -l "^budget: low$" cards/ | xargs rg -l "^emotion_tier: 3$"
# All P11 cases since 2020
rg -l "P11" cards/ | xargs rg -l "^year: 202"
# All canonical cases for QSR
rg -l "^industry: qsr$" cards/ | xargs rg -l "^quality: canonical$"
```
### Saturation map (originality pressure)
| Pattern | Saturation | Originality cap |
|---------|-----------|----------------|
| P11 (Absurd as Carrier), P16 (Long-form Drama), P09 (User as Co-Author) | high (>50 cases) | ≤6 unless structurally new variant |
| P02, P10, P12, P14, P18 | medium | ≤7 if 3+ canonical use same mechanic |
| P01, P15 | low | room for novelty |
This is empirical saturation, not subjective novelty.
## Methodologies (20+)
<img src="assets/methods-20.webp" alt="20 methods to ideate in 6 groups — structural, association, inversion, perturbation, volume, bonus; every brief pulls one technique from different groups" width="100%">
| Category | Methods |
|----------|---------|
| **Structural** | SIT/Goldenberg Templates, SCAMPER, TRIZ (10 principles), Morphological Analysis |
| **Association** | Bisociation, Random Entry, Forced Connections, Synectics |
| **Inversion** | Reverse Brainstorming, Worst Possible Idea, Provocation PO |
| **Perturbation** | Oblique Strategies, Six Thinking Hats, Disney Creative Strategy |
| **Volume** | Crazy 8s, Brainwriting 6-3-5, Starbursting |
| **Bonus** | First Principles Thinking, Lateral Thinking Toolkit, Design Sprint Sketch |
## Evaluation System
<img src="assets/scoring-loop.webp" alt="6 weighted criteria — originality 0.25, strategic fit 0.20, emotion 0.20, craftability 0.15, scalability 0.10, simplicity 0.10; score 9 of 10 and human impact 7+ to advance" width="100%">
Three parallel scoring systems calibrated against real campaigns:
- **6 Weighted Criteria** — Originality (0.25, empirically capped by case library), Strategic Fit (0.20), Emotional Response (0.20, Tier 1/2/3 hierarchy), Feasibility (0.15), Scalability (0.10), Simplicity (0.10)
- **HumanKind Scale** (Leo Burnett) — 1-10, from "Destructive" to "Changes the World"
- **Grey Scale** (Grey Group) — 1-10, from "Toxic" to "Best in the World"
Anti-inflation rules: batch control, normal distribution enforcement, real analogues test, specificity test, time test, **empirical saturation cap from case library**.
## Idea Taxonomy (Pollard 7-level)
| Level | When required | Lifespan |
|-------|---------------|----------|
| `business` | new venture, repositioning the entire company | years |
| `brand` | rebranding, brand platform — "what does the brand stand for?" | 5–10+ years |
| `tagline` | short phrase that crystallizes brand idea | 5–10+ years |
| `advertising` | central thought across all comms — recognizable without logo | 3–5 years |
| `campaign` | seasonal campaign, product launch, promo | 3–12 months |
| `non_advertising` | activation/utility/cultural object that lives without ads | varies |
| `execution` | one-off channel/format/mechanic | days–weeks |
**Activation diagnostic:** if brief mentions activation/stunt/utility — apply the test "remove the campaign, does it still have meaning?" → Yes = `non_advertising` / No = `execution`.
## Emotion Hierarchy (Tier 1/2/3)
- **Tier 1 (forgettable):** happy, sad, angry, afraid → score ≤ 6
- **Tier 2 (memorable):** nostalgic, defiant, proud, ironic, etc. → score 6–8
- **Tier 3 (greatness):** bittersweet pride, ironic sincerity, vulnerable defiance, etc. → score 8–10
- **Score 9+ requires Tier 3.**
## How Recursion Works
```
Generate ideas (3 methods, 8-12 ideas, primed against canon)
↓
Tension test on each idea
↓
Score top 3 (6 criteria + HumanKind + Grey, originality capped by saturation)
↓
Score ≥ 9? ──→ YES → Pattern Calibration + Pre-Mortem → Output
↓ NO
Identify weak criteria → Apply different method → Rescore
↓
Plateau? ──→ YES → RESTART via case-soaking
↓ (read 8-12 canonical cards, remix allowed)
↓ NO
Continue refinement
↓
5 passes? ──→ YES → Output best + honest assessment
```
## Storytelling Frameworks
Story Spine (Pixar) · Sparkline (Nancy Duarte) · Freytag's Pyramid · Monroe's Motivated Sequence · Pixar Rules · Hero's Journey (StoryBrand)
## Installation
Via [skills.sh](https://skills.sh/smixs/creative-director-skill) — installs into any of 70+ supported agents:
```bash
npx skills add smixs/creative-director-skill # asks where to install
npx skills add smixs/creative-director-skill -g # globally, for all projects
npx skills update creative-director # update to latest
```
**The full Creative Agency pack** — `creative-director`, `image` and `video` in one command:
```bash
npx skills add https://skills.sh/p/nuK9jo3sTCZGB2Ul
```
Or manually (Claude Code):
```bash
git clone https://github.com/smixs/creative-director-skill.git
cp -r creative-director-skill/creative-director ~/.claude/skills/
```
After installation, restart Claude Code session (`/clear` or new session) to pick up the skill.
### Claude Projects
Add the files to your Claude Project's knowledge base. Upload all files from `creative-director/` — `SKILL.md` is the entry point, it references other files via `[[wikilinks]]`.
### Other AI Agents (Cursor, Windsurf, GPT, Gemini)
The skill works with any AI agent that supports structured instructions — the core logic is in markdown files, no platform lock-in. Copy the `creative-director/` folder to your project or skills directory.
## Maintenance Scripts
Three Python scripts (run via `uv run`, PEP 723 inline deps — no manual setup):
```bash
cd creative-director
uv run scripts/validate_schema.py # Validate all card frontmatter
uv run scripts/generate_mocs.py # Rebuild 6 MOCs from cards
uv run scripts/generate_links.py # Rebuild Related sections (idempotent)
```
Run pipeline: edit/add cards → validate → regenerate MOCs → regenerate links.
## Usage Examples
**Full creative cycle:**
> "Come up with a campaign for [brand]. Target audience: [who]. Budget: [range]. Channels: [where]."
**Insight mining:**
> "Find a consumer insight for [category]. The brief says [context]."
**Evaluate an existing idea:**
> "Evaluate this concept: [description]. The brief objective was [goal]."
**Activation / non-advertising:**
> "Need a PR-stunt for [brand]. Low budget, must drive earned media in a week. Not a campaign — a one-shot activation."
**Quick ideation:**
> "Need 5 concepts for [brand] social media posts about [topic]."
## Next in the Pipeline
This skill delivers the idea and the script. To turn them into frames and footage, use the sibling repo **[visual-skills](https://github.com/smixs/visual-skills)** — two skills that pick up where this one stops: `image` writes art-director-grade prompts for keyframes, character sheets and storyboards (Nano Banana, GPT Image 2), `video` turns them into director-grade prompts for Seedance, Kling and Veo. Full chain: **idea & script (this skill) → keyframes (`image`) → motion (`video`)**.
## What It's Not For
- Media planning or budget allocation
- Production management
- Brand identity / logo design
- Final copywriting (it generates concepts, not polished copy)
- Market research data collection
- Brand positioning warmaps (use a dedicated positioning skill)
## Limitations & Honest Notes
- **Auto-trigger in `claude -p` mode is unreliable.** This is an advisory skill — when invoked through one-shot CLI, the model often answers creative briefs directly without consulting it. For consistent behavior in interactive sessions, invoke explicitly or share a detailed brief (>500 chars with structure).
- **571 source URLs are unverified.** Library was built from public award-show indexes; verify links manually before citing in client work.
- **12 cards have `confidence: low`** with `verification_required: true` — these should be cross-checked against external sources. The skill prefers `quality: canonical` cards for calibration.
- **Library is static.** New campaigns from 2026+ are not auto-added; periodic manual extension required.
## Credits
Created in collaboration with **Paul Deadcough**.
Built on methodologies from: Jacob Goldenberg (SIT), Genrich Altshuller (TRIZ), Edward de Bono (Lateral Thinking, Six Hats, PO), Arthur Koestler (Bisociation), William Gordon (Synectics), Brian Eno (Oblique Strategies), Nancy Duarte (Sparkline), Joseph Campbell / Donald Miller (Hero's Journey / StoryBrand), Leo Burnett (HumanKind), Mark Pollard (Strategy + 7-level Taxonomy), Clayton Christensen (JTBD).
Creative Constitution based on the Voskresensky/IKRA approach.
Case library curated from D&AD, Cannes Lions, One Show, Webby, and Effie shortlists 1950–2025.
## Author
**Serge Shima** — [t.me/aimastersme](https://t.me/aimastersme) · [sergeshima.com](https://sergeshima.com) · [aimasters.me](https://aimasters.me)
## License
**CC BY 4.0** — use it, fork it, make better ads, commercially too. One hard rule: **credit the author**. Any copy or derivative — including skills assembled by AI agents from these files or the 571-case library — must keep the attribution line: *Serge Shima — [github.com/smixs/creative-director-skill](https://github.com/smixs/creative-director-skill)*. See [LICENSE](LICENSE) and [NOTICE](NOTICE).