Skip to content

motiful/product-shots / skills/product-shots-social-post

product-shots-social-post

Verified

Designs 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).

references/grid-and-caption.md

View on GitHub
---
name: grid-and-caption
description: Section 5 (Feed Grid Aesthetics — five grid strategies + grid rules) and Section 7 (Caption & Copywriting — in-image text vs caption distinction, caption logic, Social Caption Persona with example).
---

# Feed Grid + Caption

## Execution Procedure

```
finalize_grid_and_caption(format, user_supplied_caption, brand_account_context) → grid_strategy + caption

# Section 5 — Feed Grid Aesthetics
if brand_account_series:
    confirm grid consistency need
    if user has existing posts → reference their tone / style / palette
strategy = pick_grid_strategy(brand_intent)   # see §Common Grid Strategies
apply_grid_rules(format, strategy)            # carousel only Slide 1 visible; reel cover center-cropped to 4:5

# Section 7 — Caption & Copywriting
in_image_text   = bounded by §In-Image Text vs Caption
if user_supplied_caption:
    extract emotion + tone for visual prompt
    do NOT modify or regenerate unless asked
else:
    generate caption per §Social Caption Persona
```

## TOC

- [Section 5 — Feed Grid Aesthetics](#section-5--feed-grid-aesthetics)
- [Section 7 — Caption & Copywriting](#section-7--caption--copywriting)

## Section 5 — Feed Grid Aesthetics

### Common Grid Strategies

| Strategy | Description | Best For |
|---|---|---|
| Unified Tone | All content uses the same filter / color preset for overall harmony | Safe choice for most brand accounts |
| Checkerboard | Alternates two styles (e.g., product photo + text-graphic) | Knowledge accounts, coaches / consultants |
| Row Theme | Every 3 posts form one row with the same theme / palette | Product launches, series content |
| Gradient | Tone gradually shifts (e.g., warm → cool) across the grid | High-aesthetic lifestyle accounts |
| Puzzle | One large image is split across 3 / 6 / 9 grid tiles to form a complete picture | Major brand campaigns, product launches |

### Grid Rules

- Confirm whether the user needs grid consistency (one-off output vs. brand-account series).
- For a series, ask about — or reference — the existing posts' tone / style.
- **Carousel shows only Slide 1 in the grid** — Slide 1 must satisfy both the "grid aesthetic" and the "Carousel hook" requirements.
- **Reel Cover renders in the grid as a 4:5 center-crop** — make sure the cropped frame stands alone.

## Section 7 — Caption & Copywriting

### 7.1 In-Image Text vs. Caption

| Type | Definition | Rule |
|---|---|---|
| Graphic Text (in-image) | Short, high-impact headline rendered onto the visual | Max 8-10 words; obey Section 0 Text Overlay Rules (see `references/hard-constraints.md`) |
| Caption (post text) | Long copy returned as a separate chat message | **Never rendered onto the visual** |

> Only "graphic text" is allowed to appear on the image. The full caption is always a separate text output.

### 7.2 Caption Logic

```
IF user supplied a caption THEN
    analyze it to extract "mood" and tone for the visual prompt
    do NOT modify or regenerate unless explicitly asked
ELSE
    generate caption using the Social Caption Persona below
END IF
```

### 7.3 Social Caption Persona

- **Tone**: short, aesthetic, each line as an independent micro-statement.
- **Structure**: hook line → 2-3 value lines (with line breaks) → CTA → 3-5 hashtags.
- **Line breaks**: use frequent line breaks for breathing space — social aesthetic favors whitespace in captions.
- **Hashtags**: mix high-traffic (500K+ posts) with niche-specific tags; **3-5 total, never 30**.

Example:

```
This changed everything.

The one ingredient dermatologists actually agree on →
Niacinamide. Not the trendy kind. The proven kind.

Save this for your next restock ↓

#skincaretips #niacinamide #skinbarrier
```

> **Note**: "Social Caption Persona" is a caption-tone rule, not a skill-level Persona. The skill itself does not declare a persona name.
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall