motiful/product-shots / skills/product-shots-social-post
product-shots-social-post
VerifiedDesigns social-platform-native visuals (Feed, Story, Reel, Carousel formats) for Instagram, TikTok, Facebook, Pinterest, RedNote, LinkedIn, X/Twitter and other social platforms — with platform-correct dimensions, safe zones, industry visual DNA, engagement hooks, and cross-slide consistency. Use when the user says "social post", "Instagram post", "IG post", "TikTok post", "Facebook post", "Pinterest pin", "social carousel", "feed post", "story post", "make a post", "design a social visual", "社媒帖", "做一个社媒图", or any underspecified social-media visual request. Routed from `product-shots` for the organic-social branch (non-ad).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.0 KB |
| references/carousel-framework.md | markdown | 5.2 KB |
| references/grid-and-caption.md | markdown | 3.8 KB |
| references/hard-constraints.md | markdown | 8.5 KB |
| references/industry-dna.md | markdown | 7.7 KB |
| references/workflow-and-self-check.md | markdown | 9.2 KB |
references/carousel-framework.md
View on GitHub---
name: carousel-framework
description: 'Section 3 — Carousel Standards. The 7-Slide Framework (Hook / Context / Value × 4 / CTA), Swipe Psychology, and Visual Consistency and Typography rules including the verbatim cross-slide consistency anchor template that must be repeated at the start of every slide''s prompt. EP: build_carousel(content, hook_type, industry_bundle, brand_color, engagement_goal) → 7 slide prompts.'
---
# Section 3 — Carousel Standards
Applies when format = Carousel. Carousel is the highest-failure-rate format because each slide is generated independently — without explicit per-slide consistency anchoring, fonts / colors / layouts drift between slides.
## Execution Procedure
```
build_carousel(content, hook_type, industry_bundle, brand_color, engagement_goal) → 7 slide prompts
# A. Map content to the 7-slide framework
slide_1 = render_hook(hook_type) # Bold Claim / Curiosity Gap / Visual Shock
slide_2 = build_context(content) # establish pain or promise
slide_3..slide_6 = expand_value(content, ascending_value=True) # one insight per slide; strongest at slide 6
slide_7 = build_cta(engagement_goal) # save / share / follow
# B. Apply Swipe Psychology
assert slide_1 promises an answer that requires swipe to reveal
assert "cross-slide elements" hint at swipe (visual continuity)
assert strongest insight placed at slide 6
# C. Visual Consistency and Typography
anchor = build_consistency_anchor(industry_bundle, brand_color) # see §C
for n in 1..7:
slide_n.prompt = anchor.replace("[N]", n) + slide_n.body_prompt # anchor REPEATED verbatim per slide
assert font family + weight identical across slides
assert text alignment identical across slides
assert background color / style identical across slides
# Other rules
assert each slide < 40 words text, body < 5 lines
assert ratio = 4:5 (preferred 1080×1350) and ALL cards share the same ratio
```
## TOC
- [A. The 7-Slide Framework](#a-the-7-slide-framework)
- [B. Swipe Psychology](#b-swipe-psychology)
- [C. Visual Consistency and Typography](#c-visual-consistency-and-typography)
- [Other Rules](#other-rules)
## A. The 7-Slide Framework
| Slide | Function | Technical Requirement |
|---|---|---|
| Slide 1: Hook | Apply the hook type chosen in Step 4 (Bold Claim / Curiosity Gap / Visual Shock) | Must stand alone in the profile grid |
| Slide 2: Context | Establish the pain point or promise | Reinforce why the viewer should keep swiping |
| Slide 3-6: Value | One insight per slide, numbered | Ascending value — strongest insight on Slide 6 |
| Slide 7: CTA | Explicit call-to-action: save / share / follow | CTA matches the engagement goal (SAVE → "Save this for later"; SHARE → "Tag someone who needs this"; COMMENT → "Which one are you?") |
## B. Swipe Psychology
| Principle | Implementation |
|---|---|
| Curiosity Gap | Slide 1 must promise an answer that can only be revealed by swiping |
| Visual Continuity | Ask the AI to design "cross-slide elements" that hint at swipe |
| Ascending Value | Strongest insight goes on Slide 6 (not Slide 7 — Slide 7 is the CTA) |
## C. Visual Consistency and Typography
> **Warning**: Cross-slide consistency is the most common Carousel failure. AI models generate each Carousel slide independently and will not preserve cross-slide visual unity by default. The constraints below **must be repeated verbatim in every slide's prompt**.
### Font Consistency Rules
- All slides must use **the same font family and weight** for headlines (e.g., `bold sans-serif` or `light serif`) — repeat this declaration in every slide's prompt.
- All slides must use **the same font family** for body, at the same size.
- Specify font specs explicitly per slide, e.g.:
`title: 60pt bold sans-serif white, body: 32pt regular sans-serif light gray`
### Alignment Rules
- Once alignment is established in Slide 1's prompt, all subsequent slides must follow the same alignment.
- **Left-aligned recommended** (natural reading flow, most stable across slides); centered alignment is acceptable for headline and CTA slides.
- State explicitly per slide: `text left-aligned` or `text centered` — do not let the model decide.
### Background Consistency Rules
- All slides must use **the same background color or background style** — repeat the background description in every slide's prompt.
- For gradients, specify exact color values, e.g., `background: linear gradient from #1a1a2e to #16213e`.
### Cross-Slide Prompt Template (Consistency Anchor)
Every slide's prompt should begin with a fixed "consistency anchor", e.g.:
```
Carousel slide [N] of 7. Consistent style: white background,
bold black sans-serif title (60pt, left-aligned),
regular gray sans-serif body (32pt, left-aligned),
accent color #E53E3E for highlights.
Same layout grid as all other slides.
```
This anchor is **repeated verbatim in every slide's prompt**, ensuring the model honors the same visual specs while generating each slide independently.
## Other Rules
- **Typography**: < 40 words per slide, body < 5 lines.
- **Aspect Ratio**: prefer 4:5 (1080×1350); **all cards must share the same ratio** (see Dimensions table in `references/hard-constraints.md`).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |