creative-brief
Skill7 starsChanged 5 months agoMITView on GitHub
This skill should be used when the user asks to "write a creative brief", "build a motion brief", "the client doesn't know what they want", "turn this vague client request into a brief", "what questions should I ask the client", or "make a brief I can get sign-off on". It turns a fuzzy client ask into a structured, sign-off-ready motion design brief and the exact clarifying questions to send back.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- willlee1995/skillsword for word, first seen Oct 13, 2026
- tarsluna/my-custom-skillstheir own version, first seen Sep 2, 2026
- sidchaudhary/gtm-skillstheir own version, first seen Aug 21, 2026
- styfinity/claude-marketing-departmenttheir own version, first seen Jul 8, 2026
- Infinite-Labs-AI/infinite-skillstheir own version, first seen Jul 2, 2026
- efesorjm/creative-brieftheir own version, first seen Jun 29, 2026
Used with
Projects with it also use email-sequence.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillemail-sequence
Design and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performance benchmarks. Use when building onboarding, lead nurture, re-engagement, win-back, or product launch flows, when you need a complete drip campaign with A/B test suggestions, or when mapping a sequence end-to-end with a flow diagram.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 1
- willlee1995/skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 7
- Infinite-Labs-AI/infinite-skills★ 43same name
- coleschaffer/copywritingskills-rmbc★ 32same name
- tarsluna/my-custom-skills★ 15same name
- styfinity/claude-marketing-department★ 6same name
- Zenobia0000/dtc-copywriting-skills★ 4same name
- efesorjm/creative-brief★ 3same name
- sidchaudhary/gtm-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- brand-motion-guidelinesSkill
- client-revisionsSkill
- motion-pricingSkill
- video-delivery-specsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 82
Intake: Read the raw client ask. Extract whatever maps to the 11 dimensions.
- Distinctive: line 85
Pressure-test: Check the message is singular, the tone has a "but not," deliverables have counts and durations, and distribution maps to …
- Distinctive: line 141
Do not ask the client to design.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Creative Brief
Convert a vague client ask ("we need a cool animated explainer") into a structured, sign-off-ready creative brief, and generate the exact clarifying questions to send when the client cannot articulate what they want.
When to use
Use when starting any motion project, when a client request lacks the detail needed to scope or quote, when a brief needs to be drafted for client approval, or when a "make it cool" request must be translated into concrete direction. A locked brief is the contract for creative intent; everything downstream (estimate, scope, revisions, delivery) depends on it.
Core principle
A brief is not a wish list — it is a decision document. Every project decision should trace back to one line in the brief. The job is to interrogate eleven dimensions until each has a concrete, written answer, then lock it with a sign-off line. Vague answers are not acceptable; convert each one into a specific, testable statement.
Decision tree — how far to take the brief
The judgment is how much rigour this brief needs and what to do with each gap. Don't over-process a one-day social cutdown; don't under-process a broadcast campaign.
Is the creative intent already clear and agreed in writing?
├─ YES → write a 1-page lightweight brief, confirm, proceed. Don't re-interrogate.
└─ NO → run full 11-dimension interrogation.
│
For each dimension, classify the answer:
├─ Concrete & testable → record it, move on.
├─ Vague ("cool", "modern") → run vague-translator → offer bounded choice.
├─ Blank → pull matching clarifying question (by gap).
└─ Contradictory / 3 messages → force-rank, surface the conflict to the
decision-maker, do NOT average them.
│
Can you proceed without the answer?
├─ Cosmetic gap → write best assumption, flag [ASSUMPTION — confirm].
└─ Scope/cost-defining → BLOCK. No budget, no air date, no single message,
gap (budget, no named placements = stop and resolve before
date, message, design. These set the price and the spec.
distribution)Rule of thumb: gaps that change the price or the spec are blockers; gaps that only change execution detail become flagged assumptions.
The 11 interrogation dimensions
Capture a concrete answer for each. If the client cannot answer, send the matching clarifying question (see references/clarifying-questions.md).
- Business goal — what the business needs to change (awareness, sign-ups, sales, comprehension). Must be measurable, not "engagement."
- Audience — who watches, where their head is at, their objection. Specific persona, not "everyone."
- Core message — the ONE thing a viewer must remember. One sentence. If there are three, the brief is not done.
- Tone / feel — 3-5 adjectives plus a "but not" (e.g. "playful but not childish"). Tie to reference frames.
- Mandatories — brand assets, logo lockup rules, colour/font system, legal disclaimers, super/endcard, clearcast/regulatory needs.
- Deliverables — exact count, durations, and versions (e.g. 1× 30s hero, 3× 6s cutdowns, 1× static endframe).
- Distribution — exact placements (IG Reels, paid YouTube pre-roll, trade-show loop, broadcast). This drives spec and aspect ratios.
- References — 2-4 links with a note on what to steal from each ("the pacing here, not the colour"). Also anti-references.
- Timeline — final air date working backwards through delivery, revisions, animation, design, script/board, kickoff.
- Budget — a real number or a band. "No budget yet" is a red flag to resolve before design starts.
- Success metric — how success is judged 30 days post-launch. Defines "done well," not just "done."
Question bank by gap (which question fixes which hole)
Match the gap to the single highest-leverage question. Full send-ready bank in references/clarifying-questions.md.
| Gap in the ask | The one question that closes it |
| No measurable goal | "If this works, what number on a dashboard moves?" |
| Audience = "everyone" | "Who must act first? That's the audience." |
| Three messages | "Rank these 1-3; the brief carries #1, the rest become later assets." |
| Tone with no guardrail | "Pick 3-5 words — then the important one: what must it NOT feel like?" |
| Vague tone ("modern") | Run vague-translator → "Closer to A (calm/slow) or B (punchy/fast)?" |
| No mandatories listed | "Send logo files, brand guide, fonts, colours, and any legal super." |
| Fuzzy deliverables | "Exactly how many videos, what durations, which ratios/versions?" |
| "Social" (no platform) | "Which exact placements — Reels, TikTok, pre-roll, web hero, TV?" |
| No / endless references | "Send 2-4 you love (one line each on what to steal) + 1 you hate." |
| No date | "What's the hard air date, and who gives the final yes?" |
| No budget | "Projects like this run X-Y — which end are we?" |
| No success metric | "30 days out, what makes this a win?" |
Workflow
- Intake. Read the raw client ask. Extract whatever maps to the 11 dimensions; mark the rest as gaps.
- Triage gaps. For each blank or vague dimension, pull the matching clarifying question. Group them into one consolidated email — never drip-feed questions across days.
- Draft the brief. Fill the template below. Where the client was vague, write the best assumption and flag it
[ASSUMPTION — confirm]. - Pressure-test. Check the message is singular, the tone has a "but not," deliverables have counts and durations, and distribution maps to real specs.
- Send for sign-off. Include the sign-off block. No design work begins until it is returned approved.
The brief template
PROJECT BRIEF — [Project name] Date: ___ Version: ___
Client: ___ Main contact (decision-maker): ___ Prepared by: ___
1. BUSINESS GOAL
We are making this so that: [measurable change]
2. AUDIENCE
Primary: [persona, context, mindset, key objection]
3. CORE MESSAGE (the one thing)
After watching, the viewer thinks/does: [one sentence]
4. TONE / FEEL
It feels: [adj, adj, adj] — but NOT [adj, adj]
5. MANDATORIES
Logo: [lockup + rules] Colour/Type: [system]
Legal/super/endcard: [required text] Regulatory: [Y/N — body]
6. DELIVERABLES
[count × duration × ratio × format] (full list in delivery section)
7. DISTRIBUTION
Placements: [exact channels + paid/organic]
8. REFERENCES
• [link] — take: [what to steal]
• Anti-ref: [link] — avoid: [what]
9. TIMELINE (back from air date)
Air: ___ Final delivery: ___ Rev rounds: ___ Animation: ___
Design/boards: ___ Script: ___ Kickoff: ___
10. BUDGET
[number or band] — covers: [scope]
11. SUCCESS METRIC
30 days out, success = [metric + target]
ASSUMPTIONS TO CONFIRM
• [ASSUMPTION] ...
SIGN-OFF
This brief is the agreed creative intent. Changes after sign-off are
handled as change requests.
Approved by: __________ Title: ______ Date: ______Handling "I don't know what I want"
Do not ask the client to design. Offer bounded choices instead of open questions:
- Replace "What tone do you want?" with "Closer to A (calm, premium, slow) or B (punchy, bold, fast)?"
- Replace "Any references?" with "Of these three styles, which is nearest — and what's wrong with it?"
- Force a single message: "If the viewer forgets everything but one line, which line?"
- Anchor budget with a band: "Projects like this usually land between X and Y — which end are we?"
Convert every vague adjective using the translator in references/vague-translator.md ("clean" → which of: minimal layout / lots of negative space / limited palette / slow easing?).
Worked examples
GOOD — a core-message line that closes decisions:
After watching, the viewer thinks: "Invoicing that takes 30 seconds."
One sentence, one idea, testable. Every scene can be checked against it; pacing, copy, and the endcard all trace back to this line. Full start-to-finish brief in references/worked-example.md.
ANTI-PATTERN — the "kitchen-sink" brief that guarantees revisions:
Goal: drive engagement and awareness and sign-ups. Audience: everyone who'd love our product. Message: we're innovative, affordable, easy to use, and trusted. Tone: modern, cool, fun but professional. Make it pop.
Why it fails: no measurable goal, no real audience, four competing messages, a tone with no guardrail, and an untranslated "pop." Nothing here can be approved or disproven, so round 1 becomes a discovery session on the client's dime. The fix is the entire workflow above: force one goal, one audience, one message, one "but not," and translate "pop" into a bounded choice before any design.
Common mistakes
| Symptom | Why it happens | Fix |
| Brief reads like a wish list | Captured the client's words verbatim instead of decisions | Convert every line to a concrete, testable statement |
| Round 1 turns into "what do you actually want?" | Started design with blockers unresolved | Block on goal/budget/date/message/platform before design |
| Tone keeps drifting in reviews | No "but not" guardrail set | Add the guardrail adjective; it prevents ~80% of tone revisions |
| Three messages, muddy film | Averaged competing messages instead of ranking | Force-rank; carry #1, park the rest as future assets |
| Spec/quote keeps changing | Distribution left as "social" | Pin exact placements — they define ratio, length, and price |
| Client "approves" then reopens it | No sign-off block / decision-maker unclear | Identify the single decision-maker; lock with the sign-off line |
| References pull in five directions | Endless refs, no "take" notes | Cap at 4, require a "what to steal" note + 1 anti-reference |
Deliverable spec — what a good brief contains
The output is a one-page document (the filled template) plus, when gaps exist, one consolidated clarifying email. A good brief:
- Fits roughly one page — long enough to decide, short enough to read.
- Has a concrete, testable answer in every one of the 11 dimensions (or a flagged
[ASSUMPTION]). - Carries exactly one core message and a tone with a "but not."
- Lists deliverables with counts, durations, and ratios, and distribution as named placements.
- Names the single decision-maker and ends with the sign-off block.
Before you finish — checklist
- Core message is ONE sentence (not two, not three).
- Tone has a "but not" guardrail.
- Goal is measurable; success metric has a target and a timeframe.
- Budget is a real number or an agreed band (no "TBD").
- Air date set; schedule runs backwards from it.
- Deliverables have counts + durations + ratios; distribution is named placements.
- References capped at 4, each with a "take," plus 1 anti-reference.
- Every vague adjective was translated to a concrete choice.
- Assumptions flagged
[ASSUMPTION — confirm]; decision-maker named; sign-off block present.
Related frameworks
The brief sets intent; two sibling skills turn that intent into motion direction — reference them, don't restate them here:
motion-art-direction— once tone is locked (dimension 4), pick a named Motion Personality preset there and cite it in the brief so everyone animates to the same numeric feel.animation-principles— the Three Pillars (intent → tone → craft) are the upstream version of this brief's logic; the Primary/Secondary/Ambient motion layers and the 1/3 Rule belong in execution, not the brief — don't pull them in here.
Quick reference
| Symptom | Move |
| "Make it pop / cool / modern" | Run the vague-translator; offer 2 bounded options |
| Three core messages | Force-rank; brief carries one, others become future assets |
| No budget given | Anchor with a band before any design |
| "Everyone" is the audience | Ask who must act first; that is the audience |
| No air date | Set delivery date first, schedule backwards |
| Endless references | Cap at 4 + require a "take" note + 1 anti-reference |
| Tone with no "but not" | Add the guardrail adjective; it prevents 80% of revisions |
Reference files
references/clarifying-questions.md— the full bank of send-ready clarifying questions, one set per dimension, plus the consolidated intake email template.references/vague-translator.md— vague-adjective → concrete-question lookup table and the bounded-choice question patterns.references/worked-example.md— a real vague ask turned into a completed brief, start to finish.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

