prompt-craft

prompt-craft is a skill for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 89 tokens per session (1,050 once invoked), scanned A, original, Apache-2.0.

A guide for writing detailed instructions for AI image and video generators, including the subject, setting, framing, lighting, style, colors, and aspect ratio.

In plain words
What is it for?
Use it to build prompts for tools such as Ideogram, Flux, Leonardo, and other image or video generators.
Why use it?
Vague instructions often produce unwanted results and require more attempts to fix.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pwdev-social-media plugin — 19 skills, 5 commands, 4 agents shipped together

Good fit Use it to build prompts for tools such as Ideogram, Flux, Leonardo, and other image or video generators.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft
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 pwdev-solucoes/pwdev-claude-marketplace --skill prompt-craft
Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-social-media, the plugin that ships this one along with the rest of its 19 skills, 5 commands, 4 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 prompt-craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft)
Your own site
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft/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 prompt-craft

Your own site · 80×15
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,050 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 $0.00089 $0.01050
Opus 5 $0.00044 $0.00525
Sonnet 5 $0.00018 $0.00210
Haiku 4.5 $0.00009 $0.00105

Measured 8d ago against content hash 03249cc42c17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-craft 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 8d 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.

plugins/pwdev-social-media/skills/prompt-craft/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Construção de Prompt

Você escreve a instrução que a máquina executa. Com APIs no centro, esta é a habilidade que mais economiza dinheiro: prompt ruim é retrabalho pago.

Princípio central

Cada tentativa custa. Um prompt bem construído acerta em 2 variações; um prompt vago acerta em 12 — e a diferença sai do orçamento da campanha.

Antes de escrever

Leia a seção 3 (brand kit) e 4 (identidade) do contexto. Prompt que ignora a paleta da marca gera imagem que exige tratamento — retrabalho que custa mais que gerar de novo.

Estrutura

[sujeito] [ação ou estado], [ambiente],
[enquadramento], [iluminação], [estilo], [paleta], [proporção]

Ordem importa: os geradores pesam mais o começo do prompt. O que é essencial vem primeiro.

Exemplo

Vago — vai custar 8 tentativas

"uma imagem sobre saúde pública moderna"

Específico — costuma acertar em 2

"profissional de saúde consultando tablet em posto de atendimento, ambiente claro e organizado, plano médio à altura dos olhos, luz natural difusa de janela lateral, fotografia documental, paleta verde-azulada dessaturada, proporção 4:5"

Por ferramenta

Ferramenta O que responde bem O que evitar
Ideogram texto entre aspas na arte; instrução tipográfica cena complexa com muitos sujeitos
Leonardo estilo consistente via modelo fixo e referência prompt longo demais dilui o estilo
Flux descrição fotográfica: lente, luz, profundidade vocabulário de ilustração
Runway movimento de câmera explícito mudança de cena dentro do clipe

Texto dentro da imagem

Só Ideogram entrega com confiabilidade. Nos demais:

Deixe espaço vazio no prompt e componha o texto no Figma.

Resultado sempre melhor, custa menos e o texto fica editável. Pedir texto ao Flux é o desperdício mais comum desta stack.

Negativa

Funciona mal na maioria dos modelos atuais. Descreva o que quer, não o que não quer.

❌ "sem pessoas, sem texto, não desfocado" ✅ "ambiente vazio, superfície limpa, foco nítido em toda a cena"

Read the full file on GitHub · 117 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. 8d ago First seen · 117 lines · 89 tokens per session scan A 03249cc42c17

Subscribe to this mod's changes

prompt-craft is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 89 tokens to every session and 1,050 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

Emily2040/seedance-2.0 · 48 tokens

seedance-examples-ja

This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.

Emily2040/seedance-2.0 · 43 tokens

seedance-filter

This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.

Emily2040/seedance-2.0 · 57 tokens

seedance-prompt-short

This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.

Emily2040/seedance-2.0 · 47 tokens

seedance-vocab-zh

This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.

Emily2040/seedance-2.0 · 55 tokens