Borrowing it
Nothing to install: this file belongs to gianverdum/ai-dev-skillset. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gianverdum/ai-dev-skillset/main/.agents/skills/workflow-criar-skills/SKILL.mdgit clone --depth 1 https://github.com/gianverdum/ai-dev-skillsetWrote 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/gianverdum/ai-dev-skillset/workflow-criar-skills)<a href="https://agentmods.dev/skills/gianverdum/ai-dev-skillset/workflow-criar-skills"><img src="https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/workflow-criar-skills/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/gianverdum/ai-dev-skillset/workflow-criar-skills"><img src="https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/workflow-criar-skills.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 | $0.00107 | $0.02122 |
| Opus 5 | $0.00053 | $0.01061 |
| Sonnet 5 | $0.00021 | $0.00424 |
| Haiku 4.5 | $0.00011 | $0.00212 |
Grade A, and why
workflow-criar-skills 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Criar / Atualizar Skills
.agents/skills/ é a fonte de verdade. Os providers (.claude/, .cursor/, .gemini/, .github/) são symlinks sincronizados pelo script.
Fluxo
- Normalize o nome da skill em letras minúsculas com hífens, usando apenas letras, números e
-. - Use um prefixo de tópico no nome para manter
skills/plano e organizado:architecture-,process-,workflow-,language-,greeting-,testing-,frontend-,backend-,quality-,framework-,security-,operational-,documentation-,coding-, ou outro prefixo claro. - Crie a pasta
.agents/skills/<prefixo>-<nome-da-skill>. - Use
templates/skill/SKILL.mdcomo base para o arquivo.agents/skills/<prefixo>-<nome-da-skill>/SKILL.md. - Ajuste o frontmatter seguindo as Diretrizes de description abaixo.
- Escreva o corpo da skill seguindo as Diretrizes de design abaixo.
- Quando a skill orientar nomenclatura, estrutura, layout ou convenções de stack, referencie as rules aplicáveis em
.agents/rules. - Rode
scripts/sync-skills.shapós criar ou alterar skills.
Diretrizes de description (frontmatter)
A description é o gatilho de triagem do agente. Skills com description fraca não carregam quando deveriam, mesmo com regra clara no corpo. Aplique:
- Inclua palavras-gatilho concretas: liste verbos e substantivos que o usuário tipicamente usa para acionar a skill (ex.: "concluído", "completo", "refatore", "extraia", "valide").
- Seja explícito sobre obrigatoriedade: quando a skill precisa rodar sempre que certa condição ocorre, use "OBRIGATÓRIO" / "SEMPRE" / "antes de" no início da description. Ex.: "OBRIGATÓRIO carregar antes de qualquer frase de conclusão".
- Liste frases que disparam a skill: para skills cross-cutting (revisão, qualidade, greeting), enumere frases-gatilho específicas. Ex.: "Frases-gatilho: 'concluído', 'pronto', 'the refactoring is complete'".
- Diga o que a skill garante: "Garante que X não seja violado silenciosamente". Torna o valor da skill explícito para o triage.
- Diga o que vira DESVIO sem a skill: "Sem rodar esta checklist, declarar conclusão é DESVIO grave". Reforça por que carregar.
- Não use description genérica: "Skill que ajuda em refatoração" é fraco. "Refatorar código legado (módulo monolítico, reorganização estrutural, split de bounded contexts) com rede de testes e passos pequenos" é forte.
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 · 142 lines · 0 tokens per session scan A 08603d6fd1fa
workflow-criar-skills is a skill published in the GitHub repository gianverdum/ai-dev-skillset (5 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 2,122 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…