concept-engine

A creative-planning guide that turns rough material—such as brainstorm notes, meeting transcripts, competitor observations, or a blank idea—into structured advertising concepts. It uses audience, customer problem, awareness stage, format, hook, and performance data to shape the concepts.

In plain words
What is it for?
Use it to generate two to five ad concepts, with emphasis on hooks, formats, audiences, or a balanced mix. The concepts can then feed into an advertising brief or hook-writing task.
Why use it?
It gives unstructured ideas a consistent direction and connects them to available advertising results. This makes the output easier to develop into a brief or advertising copy.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/motion-creative/motion-creative-plugin/concept-engine
Any agent
npx skills add Motion-Creative/motion-creative-plugin --skill concept-engine
Clone the repo
git clone --depth 1 https://github.com/Motion-Creative/motion-creative-plugin

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00086 $0.02799
Opus 5 $0.00043 $0.01399
Sonnet 5 $0.00017 $0.00560
Haiku 4.5 $0.00009 $0.00280

Measured 2d ago against content hash aa6036b933c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Plugin/skills/concept-engine/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Concept Engine — Data-Grounded Creative Concept Generator


Phase 0: Orient

  1. Acknowledge: "I'll map your input through the creative strategy framework and produce grounded concepts."
  2. Ask for input: "What's the raw input — brainstorm notes, meeting transcript, competitor observation, or blank slate?"
  3. Connected workflow: After concepts, you can brief one (/build-brief), write hooks for it (/write-hooks), or iterate on a specific angle.

If the user already provided raw input in their message, skip questions and proceed.


Transform any input into structured, briefable ad concepts grounded in performance data and the Creative Strategy Engine framework.


Phase 1: Discovery

1a. Parse Arguments

  • Raw input ($ARGUMENTS): The source material. Can be anything — a raw idea, meeting transcript, brainstorm notes, competitor observation, a single sentence, or empty.
  • --count: Number of concepts to generate. Default: 3. Range: 2-5.
  • --focus: Weight for concept generation:
    • hook — emphasize hook innovation
    • format — emphasize format experimentation
    • audience — emphasize audience expansion
    • Default: balanced across all dimensions.

1b. Load Context

  1. Read ${CLAUDE_PLUGIN_ROOT}/motion-creative.config.md for brand guidelines, production constraints, primary KPI, target audience. If the file does not exist, use these defaults and suggest the user run /customize:
    • primary_kpi: use goalMetric from first get_creative_insights response
    • default_date_preset: LAST_30_DAYS
    • default_creative_limit: 10
    • production_capabilities: all formats
    • max_production_difficulty: High
    • Brand guidelines: pull from get_workspace_brand
  2. Read ${CLAUDE_SKILL_DIR}/../creative-strategist/SKILL.md for methodology.
  3. Read ${CLAUDE_SKILL_DIR}/../creative-strategist/references/concept-standards.md for quality bar.
  4. Read ${CLAUDE_SKILL_DIR}/references/creative-strategy-engine.md for the full strategic framework.
  5. Use default_date_preset from settings as the datePreset for all calls unless the user specified a date range. Use default_creative_limit from settings as the limit unless the user specified otherwise.

Read the full file on GitHub · 271 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 271 lines · 86 tokens per session scan A aa6036b933c0

Subscribe to this mod's changes

concept-engine is a skill published in the GitHub repository Motion-Creative/motion-creative-plugin (20 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 2,799 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens