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.
npx skills add landim32/awesome-ai-skills --skill social-media-assetsgit clone --depth 1 https://github.com/landim32/awesome-ai-skillsWrote 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.
[](https://agentmods.dev/skills/landim32/awesome-ai-skills/social-media-assets)<a href="https://agentmods.dev/skills/landim32/awesome-ai-skills/social-media-assets"><img src="https://agentmods.dev/badge/skills/landim32/awesome-ai-skills/social-media-assets/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.
<a href="https://agentmods.dev/skills/landim32/awesome-ai-skills/social-media-assets"><img src="https://agentmods.dev/badge/skills/landim32/awesome-ai-skills/social-media-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.00994 |
| Opus 5 | $0.00032 | $0.00497 |
| Sonnet 5 | $0.00013 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
social-media-assets 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media Assets
Owns the media layer of a campaign under social-media/: what exists, what is
missing, where media may come from, how often a piece may be reused, and how to
request what is missing. The agent never creates media — the user produces all
media; this skill only catalogs, tracks usage, and requisitions.
Literal artifact tokens (
materiais.md, theMaterial:field,FALTANTE, the "A produzir / requisitar" section label) are kept verbatim; the generated files target a PT-BR audience. The documentation is in English.
Inventory and usage derived from posts
materiais.mdis the inventory of what is available or missing per item — it does not store usage.- Usage is derived from the posts (single source, no duplication): before
assigning media to a new post, Grep the
Material:lines across**/posts/**/*.mdto see which clips/images were already used and where. Never persist a usage log — recompute it from the posts. - Every post records the path of the media it uses in its
Material:field.
Allowed media sources (hard rule)
You may locate, assign, and reference media only from the folders listed under
"Pastas de mídia permitidas (fontes)" in config.md (each folder including all
its subfolders). That table is the single source of truth — never hardcode
the folder list here. When you need media, run Glob/Grep scoped to those paths. A
file outside the allowed folders must not appear in a Material: field; if a
post can only be satisfied by media outside them, treat it as FALTANTE and
requisition it. To change the sources, the user edits the table in config.md.
Reuse policy (hard) — caps come from config
Each source folder has a reuse cap per network, defined in the cap table in
config.md (the domain pack populates the values and the concrete folders). This
skill applies the generic mechanism without hardcoding the values:
- Cap "1 use" / forbidden beyond the cap (e.g. backstage, sensitive material).
Hard cap — there is no
⚠️ FALTANTEfallback; reuse simply isn't allowed. If a 2nd assignment on the same network is needed, swap it for a different file or mark the post as pending fresh material. - Cap "N uses" with fallback (e.g. shorts/excerpts). Allows up to N distinct
dates (same network) to share the material before any marker. From the (N+1)-th
use onward, mark the post
⚠️ FALTANTE não-bloqueante(material reused, fresh would be ideal) and propagate to cronograma/agenda (social-media-scheduling). - Structural material (e.g. art/cover). Use as needed, but mark
⚠️ FALTANTE não-bloqueantewhen reuse forces same-material on consecutive posts on the same network.
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.
- 12d ago First seen · 72 lines · 63 tokens per session scan A d0449e6f3f1c
social-media-assets is a skill published in the GitHub repository landim32/awesome-ai-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 994 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.
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…
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…
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…
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…
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…
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…