Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Generate Social

ASecurity

Generates platform-sized, on-brand social templates as SVG from the active brand profile, with editable headline, subhead, and call-to-action zones. Vector output needs no account, key, or network. Use when a user asks for an Instagram post or story, an Open Graph or social card, a YouTube thumbnail, or a banner. Trigger with "make an Instagram post", "social card", or "/brand-make social".

2,785 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsgobashnodedocumentation

Works with

claude codecli

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add jeremylongshore/claude-code-plugins-plus --skill generate-social --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Generate Social?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Generate Social
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jeremylongshore-generate-social-81f53444/badge)](https://www.skillsdirectory.com/skills/jeremylongshore-generate-social-81f53444)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: generate-social
description: |
  Generates platform-sized, on-brand social templates as SVG from the active
  brand profile, with editable headline, subhead, and call-to-action zones.
  Vector output needs no account, key, or network.
  Use when a user asks for an Instagram post or story, an Open Graph or social
  card, a YouTube thumbnail, or a banner.
  Trigger with "make an Instagram post", "social card", or "/brand-make social".
allowed-tools: Read, Write, Glob, Bash(node:*)
argument-hint: '[platform] [headline] [optional subhead] [optional cta]'
version: "0.5.1"
author: localplugins <localplugins@proton.me>
license: MIT
compatibility: Designed for Claude Code
tags:
- branding
- social-media
- svg
- templates
- marketing
---

# Generate Social

Generates a platform-sized, on-brand social template as SVG from the active brand profile, with editable text zones the user can tweak afterward.

## Overview

The generate-social skill turns a headline (and optional subhead and call-to-action)
into a correctly sized social graphic that uses the brand's palette and fonts. Output
is vector SVG, so it scales cleanly and needs no account, key, or network call. The
generator (`lib/social.mjs`) lays out a brand band, a wrapped headline, an optional
subhead, and an optional accent pill; the skill resolves the active profile, picks the
platform, runs the generator, and saves the file. For a photographic background behind
the template, the raster path lives in the `generate-graphic` skill.

## Prerequisites

- An active brand profile created with `/brand-new` (a `brand/` directory, or `brands/[slug]/`). Read loads its `color-system.json` and `typography.json`.
- Node.js on the PATH — the generator runs as `node lib/social.mjs`.
- Write access to an `output/` directory in the working repository.
- A headline string; subhead and call-to-action are optional parameters.

## Instructions

1. Run `/brand-status` to confirm the active brand; if none exists, tell the user to run `/brand-new` and stop.
2. Use Glob to locate the active brand directory, then Read and validate the profile with `validateProfile`. Stop with the offending field if validation fails.
3. Choose the platform preset — `instagram-square` (default), `instagram-story`, `og-card`, or `youtube-thumb`. Ask the user when unspecified.
4. Generate the template by running the node generator:

   ```js
   import { loadProfile } from '../../lib/brand.mjs';
   import { buildSocial } from '../../lib/social.mjs';
   const profile = loadProfile(activeDir);
   const { svg, platform } = buildSocial(profile, {
     platform: 'instagram-square',
     headline: 'We just raised our Series A',
     subhead: 'Building the future of logistics',
     cta: 'Read the story',
   });
   ```

5. Write the result with the Write tool to `output/[slug]-[platform].svg`.
6. Hand the file to the `visual-guardian` subagent for a palette, contrast, and type pass; apply its fixes or surface its flags.
7. Report the saved path and point out the editable zones so the user can customize or adapt the copy: `id="headline"`, `id="subhead"`, and `id="cta"`.

## Output

One SVG file under `output/`, named for the slug and platform:

```text
output/northwind-instagram-square.svg
```

- Sized to the chosen platform (for example 1080×1080 for `instagram-square`).
- Text sits in editable zones — `id="headline"`, `id="subhead"`, `id="cta"` — that wrap automatically.
- All copy is HTML-escaped before it enters the markup; colors come from the palette only. No raster is produced.

## Error Handling

| Condition | Behavior |
|-----------|----------|
| No active brand profile | Stop and direct the user to `/brand-new`. |
| Profile fails `validateProfile` | Report the offending field and stop. |
| Headline missing | Ask the user for the headline before generating. |
| Unknown platform requested | List the four supported presets and ask the user to pick one. |
| Headline too long for the canvas | The generator wraps text; verify the result and shorten copy if the guardian flags overflow. |

To troubleshoot a clipped layout, verify the copy length against `references/platform-sizes.md`, then re-run and re-check with the guardian.

## Examples

**Example — launch announcement post**

> /brand-make an instagram post announcing our Series A

Builds a 1080×1080 square with the brand band, a wrapped headline, and an accent call-to-action, saved as `output/northwind-instagram-square.svg`.

**Example — link card**

> /brand-make an og card for the blog post

Generates a 1200×630 Open Graph card sized for link previews and hands it to the guardian.

**Example — story cover**

> /brand-make an instagram story

Produces a 1080×1920 story, insetting text clear of the platform's top and bottom safe zones.

## Resources

- `references/platform-sizes.md` — every preset size, safe zones, the layout the generator produces, and how to add a preset.
- Sibling skills: generate-logo for marks, and generate-graphic for photographic backgrounds — route between them with the `/brand-make` command.
- [Open Graph protocol](https://ogp.me/) — the metadata standard `og-card` targets.
- [Agent Skills documentation](https://code.claude.com/docs/en/skills) — how skills are authored and invoked.

Attribution

jeremylongshorejeremylongshore
View sourceSee grades on GitHubMore from jeremylongshore →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →