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 pwdev-solucoes/pwdev-claude-marketplace --skill prompt-craftgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/prompt-craft)<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.
<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>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 | $0.00089 | $0.01050 |
| Opus 5 | $0.00044 | $0.00525 |
| Sonnet 5 | $0.00018 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
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.
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"
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.
- 8d ago First seen · 117 lines · 89 tokens per session scan A 03249cc42c17
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.
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.
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.
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.
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.
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.
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.