Skip to content
Back to search

creative-director-skill

World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning cases.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/smixs--creative-director-skill/badge.svg)](/listings/smixs--creative-director-skill)

HTML

<a href="/listings/smixs--creative-director-skill"><img src="/api/listings/smixs--creative-director-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Via [skills.sh](https://skills.sh/smixs/creative-director-skill) — installs into any of 70+ supported agents:

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:

npx skills add https://skills.sh/p/nuK9jo3sTCZGB2Ul

Or manually (Claude Code):

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.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 335 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="assets/header.webp" alt="Creative Director Skill" width="100%">
  3. </p>
  4. <h1 align="center">There is no creativity in AI.<br>There are the methodologies of winners.</h1>
  5. <p align="center"><sub>Креатива в AI нет. Есть методологии победителей.</sub></p>
  6. <h1 align="center">🎬 Creative Director Skill</h1>
  7. [![Claude Skill](https://img.shields.io/badge/Claude-Skill-blueviolet?style=flat-square)](https://docs.anthropic.com)
  8. [![License: CC BY 4.0](https://img.shields.io/badge/License-CC_BY_4.0-orange?style=flat-square)](LICENSE)
  9. [![Methods 20+](https://img.shields.io/badge/Methods-20%2B-orange?style=flat-square)](#methodologies-20)
  10. [![Case Library](https://img.shields.io/badge/Cases-571-blue?style=flat-square)](#case-library)
  11. [![Version](https://img.shields.io/badge/Version-2.0-red?style=flat-square)](#whats-new-in-v20)
  12. [![Website](https://img.shields.io/badge/Website-cd--skill.com-ff3b47?style=flat-square)](https://cd-skill.com)
  13. **🇷🇺 [Читать на русском](README.ru.md)**
  14. <a href="https://cd-skill.com">
  15. <img src="assets/cd-skill-site.webp" alt="cd-skill.com — full method breakdown, all 20 techniques and the pipeline" width="100%">
  16. </a>
  17. <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>
  18. > Created in collaboration with **Paul Deadcough**.
  19. 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.
  20. 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.
  21. ---
  22. ## What's New in v2.0
  23. - **571-case library** with full Insight / Mechanic / Why-it-worked / Steal structure on every card
  24. - **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
  25. - **6 MOCs** (Maps of Content) for fast lookup by pattern, emotion, format, industry, budget, and chronological index
  26. - **4-point case library integration** in workflow — priming before generation, originality empirical cap, RESTART case-soaking, pattern calibration before exit
  27. - **3 maintenance scripts** (Python via `uv`) — schema validation, MOC generation, graph wikilinks
  28. - **Pollard 7-level idea taxonomy** replacing the previous 3-level system
  29. - **3-tier emotion hierarchy** with 30+ specific emotion values
  30. - **Activation toolkit** with 9 formats and the Non-advertising vs Execution test
  31. - **Pre-Mortem template** before final delivery
  32. 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).
  33. ---
  34. ## What It Does
  35. Feed it a brief in any format — text, voice transcript, PDF, raw notes — and it runs a full creative cycle:
  36. <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%">
  37. 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)
  38. 2. **INSIGHT** — mines consumer insights using 7 proven techniques (Mark Pollard, JTBD, Tension Spotting, HMW, Abstraction Laddering)
  39. 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
  40. 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
  41. 5. **ARTICULATE** — outputs in a presentation-ready format (one-pager, top-3, campaign platform, or quick response)
  42. You can also enter at any phase: jump to insight mining, evaluate an existing idea, or generate concepts from a known insight.
  43. ## Why This Exists
  44. 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.
  45. <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%">
  46. This skill enforces the discipline that separates award-winning work from filler:
  47. - **Insight-first** — no ideation without a validated consumer tension
  48. - **Structural methods** — SIT, TRIZ, SCAMPER, Bisociation, Synectics, not "give me 10 ideas"
  49. - **Empirical originality** — every idea is checked against 571 real campaigns; if 3+ canonical cases use the same mechanic, originality is capped, not subjectively claimed
  50. - **Honest scoring** — calibrated against real Cannes winners, with anti-inflation rules
  51. - **Recursive refinement** — weak criteria get targeted improvement using different methods each pass
  52. - **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)
  53. - **Kill Your Darlings** — the skill argues against its own favorite ideas to test their strength
  54. - **Pre-Mortem** — before delivery, simulates failure and surfaces the most likely failure modes
  55. ## What's Inside
  56. ```
  57. creative-director/
  58. ├── SKILL.md # Core skill — phase router + 5-phase workflow
  59. ├── assets/
  60. │ └── output-templates.md # 4 presentation formats
  61. ├── scripts/ # Python via uv (PEP 723 inline deps)
  62. │ ├── validate_schema.py # Frontmatter validation against tag-schema
  63. │ ├── generate_mocs.py # Builds 6 MOCs from cards
  64. │ └── generate_links.py # Adds Related sections (idempotent)
  65. └── references/
  66. ├── tag-schema.md # Single source of truth — 17-axis frontmatter contract
  67. ├── idea-taxonomy.md # Pollard 7-level taxonomy
  68. ├── emotion-hierarchy.md # Tier 1/2/3 + 30+ specific emotion values
  69. ├── activation-toolkit.md # 9 activation formats + Non-ad vs Execution test
  70. ├── legendary-patterns.md # P01-P18 mechanics + Pre-Mortem template
  71. ├── methods-catalog.md # 20 creative methodologies as executable cards
  72. ├── method-selection-matrix.md # Task → method routing + rotation rules
  73. ├── insight-mining.md # 7 insight discovery techniques
  74. ├── scoring-calibration.md # Detailed rubrics + calibration anchors
  75. ├── creative-constitution.md # 3-layer evaluation system + feedback rules
  76. ├── storytelling-frameworks.md # 6 narrative frameworks for advertising
  77. └── legendary-campaigns/ # 571-case library
  78. ├── README.md # Library guide
  79. ├── MOC-index.md # All 571 cards by year DESC
  80. ├── MOC-pattern.md # Grouped by P01–P18 (18 mechanics)
  81. ├── MOC-emotion.md # Grouped by emotion_tier (3 → 2 → 1)
  82. ├── MOC-format.md # Grouped by category (film/integrated/stunt_pr/...)
  83. ├── MOC-industry.md # Grouped by industry vertical
  84. ├── MOC-budget.md # Grouped by budget (low/medium/high)
  85. └── cards/ # 571 individual cards (flat namespace)
  86. └── {id}.md
  87. ```
  88. ## Case Library
  89. 571 advertising campaigns from 1950–2025, tagged across **17 axes**, with full structural analysis on every card.
  90. <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%">
  91. ### Card structure
  92. Each card has YAML frontmatter (17 axes — see `references/tag-schema.md`) + 4 sections:
  93. - **Insight** — the human truth the campaign exploits (one sentence)
  94. - **Mechanic** — what was actually executed
  95. - **Why it worked** — psychological / cultural / structural reason
  96. - **Steal** — pattern-level borrow strategy
  97. - **Related** — auto-generated wikilinks (pattern hub + 2 sibling cards + emotion match)
  98. ### Tag schema (17 axes)
  99. `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`.
  100. ### 18 patterns (P01–P18)
  101. 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
  102. ### Lookup strategies
  103. ```bash
  104. # Browse by axis — open the matching MOC
  105. # Each line has inline-context (brand · year · format · emotion · budget · top_award)
  106. # Filter by combination — ripgrep on frontmatter
  107. rg -l "^budget: low$" cards/ | xargs rg -l "^emotion_tier: 3$"
  108. # All P11 cases since 2020
  109. rg -l "P11" cards/ | xargs rg -l "^year: 202"
  110. # All canonical cases for QSR
  111. rg -l "^industry: qsr$" cards/ | xargs rg -l "^quality: canonical$"
  112. ```
  113. ### Saturation map (originality pressure)
  114. | Pattern | Saturation | Originality cap |
  115. |---------|-----------|----------------|
  116. | P11 (Absurd as Carrier), P16 (Long-form Drama), P09 (User as Co-Author) | high (>50 cases) | ≤6 unless structurally new variant |
  117. | P02, P10, P12, P14, P18 | medium | ≤7 if 3+ canonical use same mechanic |
  118. | P01, P15 | low | room for novelty |
  119. This is empirical saturation, not subjective novelty.
  120. ## Methodologies (20+)
  121. <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%">
  122. | Category | Methods |
  123. |----------|---------|
  124. | **Structural** | SIT/Goldenberg Templates, SCAMPER, TRIZ (10 principles), Morphological Analysis |
  125. | **Association** | Bisociation, Random Entry, Forced Connections, Synectics |
  126. | **Inversion** | Reverse Brainstorming, Worst Possible Idea, Provocation PO |
  127. | **Perturbation** | Oblique Strategies, Six Thinking Hats, Disney Creative Strategy |
  128. | **Volume** | Crazy 8s, Brainwriting 6-3-5, Starbursting |
  129. | **Bonus** | First Principles Thinking, Lateral Thinking Toolkit, Design Sprint Sketch |
  130. ## Evaluation System
  131. <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%">
  132. Three parallel scoring systems calibrated against real campaigns:
  133. - **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)
  134. - **HumanKind Scale** (Leo Burnett) — 1-10, from "Destructive" to "Changes the World"
  135. - **Grey Scale** (Grey Group) — 1-10, from "Toxic" to "Best in the World"
  136. Anti-inflation rules: batch control, normal distribution enforcement, real analogues test, specificity test, time test, **empirical saturation cap from case library**.
  137. ## Idea Taxonomy (Pollard 7-level)
  138. | Level | When required | Lifespan |
  139. |-------|---------------|----------|
  140. | `business` | new venture, repositioning the entire company | years |
  141. | `brand` | rebranding, brand platform — "what does the brand stand for?" | 5–10+ years |
  142. | `tagline` | short phrase that crystallizes brand idea | 5–10+ years |
  143. | `advertising` | central thought across all comms — recognizable without logo | 3–5 years |
  144. | `campaign` | seasonal campaign, product launch, promo | 3–12 months |
  145. | `non_advertising` | activation/utility/cultural object that lives without ads | varies |
  146. | `execution` | one-off channel/format/mechanic | days–weeks |
  147. **Activation diagnostic:** if brief mentions activation/stunt/utility — apply the test "remove the campaign, does it still have meaning?" → Yes = `non_advertising` / No = `execution`.
  148. ## Emotion Hierarchy (Tier 1/2/3)
  149. - **Tier 1 (forgettable):** happy, sad, angry, afraid → score ≤ 6
  150. - **Tier 2 (memorable):** nostalgic, defiant, proud, ironic, etc. → score 6–8
  151. - **Tier 3 (greatness):** bittersweet pride, ironic sincerity, vulnerable defiance, etc. → score 8–10
  152. - **Score 9+ requires Tier 3.**
  153. ## How Recursion Works
  154. ```
  155. Generate ideas (3 methods, 8-12 ideas, primed against canon)
  156. ↓
  157. Tension test on each idea
  158. ↓
  159. Score top 3 (6 criteria + HumanKind + Grey, originality capped by saturation)
  160. ↓
  161. Score ≥ 9? ──→ YES → Pattern Calibration + Pre-Mortem → Output
  162. ↓ NO
  163. Identify weak criteria → Apply different method → Rescore
  164. ↓
  165. Plateau? ──→ YES → RESTART via case-soaking
  166. ↓ (read 8-12 canonical cards, remix allowed)
  167. ↓ NO
  168. Continue refinement
  169. ↓
  170. 5 passes? ──→ YES → Output best + honest assessment
  171. ```
  172. ## Storytelling Frameworks
  173. Story Spine (Pixar) · Sparkline (Nancy Duarte) · Freytag's Pyramid · Monroe's Motivated Sequence · Pixar Rules · Hero's Journey (StoryBrand)
  174. ## Installation
  175. Via [skills.sh](https://skills.sh/smixs/creative-director-skill) — installs into any of 70+ supported agents:
  176. ```bash
  177. npx skills add smixs/creative-director-skill # asks where to install
  178. npx skills add smixs/creative-director-skill -g # globally, for all projects
  179. npx skills update creative-director # update to latest
  180. ```
  181. **The full Creative Agency pack** — `creative-director`, `image` and `video` in one command:
  182. ```bash
  183. npx skills add https://skills.sh/p/nuK9jo3sTCZGB2Ul
  184. ```
  185. Or manually (Claude Code):
  186. ```bash
  187. git clone https://github.com/smixs/creative-director-skill.git
  188. cp -r creative-director-skill/creative-director ~/.claude/skills/
  189. ```
  190. After installation, restart Claude Code session (`/clear` or new session) to pick up the skill.
  191. ### Claude Projects
  192. 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]]`.
  193. ### Other AI Agents (Cursor, Windsurf, GPT, Gemini)
  194. 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.
  195. ## Maintenance Scripts
  196. Three Python scripts (run via `uv run`, PEP 723 inline deps — no manual setup):
  197. ```bash
  198. cd creative-director
  199. uv run scripts/validate_schema.py # Validate all card frontmatter
  200. uv run scripts/generate_mocs.py # Rebuild 6 MOCs from cards
  201. uv run scripts/generate_links.py # Rebuild Related sections (idempotent)
  202. ```
  203. Run pipeline: edit/add cards → validate → regenerate MOCs → regenerate links.
  204. ## Usage Examples
  205. **Full creative cycle:**
  206. > "Come up with a campaign for [brand]. Target audience: [who]. Budget: [range]. Channels: [where]."
  207. **Insight mining:**
  208. > "Find a consumer insight for [category]. The brief says [context]."
  209. **Evaluate an existing idea:**
  210. > "Evaluate this concept: [description]. The brief objective was [goal]."
  211. **Activation / non-advertising:**
  212. > "Need a PR-stunt for [brand]. Low budget, must drive earned media in a week. Not a campaign — a one-shot activation."
  213. **Quick ideation:**
  214. > "Need 5 concepts for [brand] social media posts about [topic]."
  215. ## Next in the Pipeline
  216. 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`)**.
  217. ## What It's Not For
  218. - Media planning or budget allocation
  219. - Production management
  220. - Brand identity / logo design
  221. - Final copywriting (it generates concepts, not polished copy)
  222. - Market research data collection
  223. - Brand positioning warmaps (use a dedicated positioning skill)
  224. ## Limitations & Honest Notes
  225. - **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).
  226. - **571 source URLs are unverified.** Library was built from public award-show indexes; verify links manually before citing in client work.
  227. - **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.
  228. - **Library is static.** New campaigns from 2026+ are not auto-added; periodic manual extension required.
  229. ## Credits
  230. Created in collaboration with **Paul Deadcough**.
  231. 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).
  232. Creative Constitution based on the Voskresensky/IKRA approach.
  233. Case library curated from D&AD, Cannes Lions, One Show, Webby, and Effie shortlists 1950–2025.
  234. ## Author
  235. **Serge Shima** — [t.me/aimastersme](https://t.me/aimastersme) · [sergeshima.com](https://sergeshima.com) · [aimasters.me](https://aimasters.me)
  236. ## License
  237. **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).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.