social-post-authoring

social-post-authoring is a skill for Claude Code from landim32/awesome-ai-skills. It costs 64 tokens per session (3,062 once invoked), scanned A, original, MIT.

A writing guide for preparing one social-media post per network, including the required format, image or video shape, character limits, hashtags, and caption text.

In plain words
What is it for?
Use it to create or edit copy and media details for campaign posts that are ready to paste into each supported network.
Why use it?
It reduces the need to remember different publishing rules for YouTube, Instagram, TikTok, X, and Threads.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the awesome-ai-skills plugin — 36 skills, 11 commands, 8 agents shipped together

Good fit Use it to create or edit copy and media details for campaign posts that are ready to paste into each supported network.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/landim32/awesome-ai-skills/social-post-authoring
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.

Any agent
npx skills add landim32/awesome-ai-skills --skill social-post-authoring
Clone the repo
git clone --depth 1 https://github.com/landim32/awesome-ai-skills

Made for: Claude Code.

Or install awesome-ai-skills, the plugin that ships this one along with the rest of its 36 skills, 11 commands, 8 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for social-post-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/landim32/awesome-ai-skills/social-post-authoring/github.svg)](https://agentmods.dev/skills/landim32/awesome-ai-skills/social-post-authoring)
Your own site
<a href="https://agentmods.dev/skills/landim32/awesome-ai-skills/social-post-authoring"><img src="https://agentmods.dev/badge/skills/landim32/awesome-ai-skills/social-post-authoring/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for social-post-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/landim32/awesome-ai-skills/social-post-authoring"><img src="https://agentmods.dev/badge/skills/landim32/awesome-ai-skills/social-post-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,062 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00064 $0.03062
Opus 5 $0.00032 $0.01531
Sonnet 5 $0.00013 $0.00612
Haiku 4.5 $0.00006 $0.00306

Measured 12d ago against content hash 2f958ef04756, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-post-authoring 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 12d 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.

skills/social-post-authoring/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Post Authoring

How to compose one social post per network so it is ready to copy-paste. This skill is platform mechanics only — it knows nothing about the campaign's domain (a band album, an online game, a product launch). It expects a campaign project under social-media/ with a config.md holding cross-cutting settings (mandatory hashtags, X account tier, allowed media folders). Read config.md before authoring.

The literal on-disk tokens written into posts (status values, the ## section headings, FALTANTE, field labels) are kept verbatim because the generated posts target a PT-BR audience. The documentation around them is in English.

Post file format

One .md file per network that receives the post on a given day. Threads has no own file — it is replicated from instagram.md (note "replicar no Threads" in the Instagram file's ## Observações). The <network> files are youtube.md, instagram.md, tiktok.md, x.md.

# <Tema> — <Rede>
- Data: YYYY-MM-DD · Tipo: <tipo> · Item: <item|Geral>
- Formato: <vídeo long-form|reels|short|imagem|texto|enquete>
- Status: falta-conteudo | planejado | agendado | publicado | cancelado | aguardando
- Material: <path(s) or "FALTANTE — requisitar">

## Legenda
<final copy in plain text, with emojis + CTA>

## Hashtags (máx. 5)
<#... — at most 5, lowercase>

## Observações
<e.g. replicar no Threads>

The Item: field names the campaign item the post primarily promotes (a domain pack may rename it — e.g. a music album pack uses Faixa:). The status values and lifecycle are owned by the social-media-scheduling skill.

Network × post-type matrix (hard rule)

Network Receives Format
YouTube only full long-form videos + excerpt shorts of the content itself (teaser/catalog) long-form 16:9 / Short 9:16 (excerpt) — no image posts; no info/announcement/backstage/countdown/concept/poll/eve shorts
Instagram short videos (Reels = video only) + image posts (feed 1:1 or carousel) Reels 4:5 video / feed 1:1 image — no long-form videos, no photo slideshow as Reels
TikTok long-form + short videos — video only, no photo carousel/slideshow; no polls long-form 16:9 (same file as YouTube/X) / short 9:16
X.com long-form + short videos + image/text video 16:9 / short 9:16 / image 16:9 / text
Threads mirrors Instagram replicate the Instagram content

Read the full file on GitHub · 204 lines

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. 12d ago First seen · 204 lines · 64 tokens per session scan A 2f958ef04756

Subscribe to this mod's changes

social-post-authoring is a skill published in the GitHub repository landim32/awesome-ai-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 3,062 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

laravel-specialist

Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…

Jeffallan/claude-skills · 86 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens

devops-engineer

Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…

Jeffallan/claude-skills · 107 tokens

django-storages-s3

Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…

Jeffallan/claude-skills · 138 tokens

fine-tuning-expert

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning…

Jeffallan/claude-skills · 129 tokens

kubernetes-specialist

Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies…

Jeffallan/claude-skills · 79 tokens