criar-skill

A guided builder for creating new coding-agent skills, automations, and knowledge packages. It uses TDD, meaning the skill is tested before and after it is written.

In plain words
What is it for?
Use it to create a skill directory with instructions and reference files, then validate and refine the result.
Why use it?
It helps reveal whether a skill actually teaches the intended behavior and closes gaps found during testing.

Command

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.

agentmods
npx agentmods add commands/georgemarmelstein/superjurista-dev/criar-skill
Clone the repo
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-dev
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.07552
Opus 5 $0.00015 $0.03776
Sonnet 5 $0.00006 $0.01510
Haiku 4.5 $0.00003 $0.00755

Measured yesterday against content hash 04b863994ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

criar-skill 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 yesterday.

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.

commands/criar-skill.md · 847 lines

How it starts

The opening of the file, as written. The whole thing — 847 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orquestrador: criar-skill v3.0

Propósito: Meta-orquestrador para criação de skills com TDD (Test-Driven Development) e CSO (Claude Search Optimization).

Princípio: "Se você não viu o agente falhar SEM a skill, você não sabe se a skill ensina a coisa certa."

Padrão: RED (teste sem skill) → GREEN (skill mínima) → REFACTOR (fechar brechas)

Nota de versão: este "v3.0" é a linhagem própria desta skill (TDD + CSO), independente do "v3.0" dos pipelines (retomada/gate/disco). Para skills que EMBARCAM scripts, a seção "Isolamento de Contexto" já traz context: fork; a Fase 4 acrescenta o padrão de gate/output.

<meta_orquestrador> Criador de Artefatos com TDD <artefato_alvo>Skill (diretório + SKILL.md + references/)</artefato_alvo> <spec_referencia>${CLAUDE_PLUGIN_ROOT}/spec/templates/skill.md</spec_referencia> <checklist_referencia>${CLAUDE_PLUGIN_ROOT}/spec/referencias/checklist-validacao-skill.md</checklist_referencia> <guia_referencia>${CLAUDE_PLUGIN_ROOT}/skills/criar-skill/references/skill-writing-guide.md</guia_referencia> </meta_orquestrador>

<contratos_dados>

Fase Entrada Saída Validação
0 $ARGUMENTS Variáveis calculadas $NOME, $TIPO e $USAR_FORK definidos
1 Ideia geral Especificação + cenário de teste Perguntas respondidas
2 Especificação Campos preenchidos com CSO Description otimizada, fork avaliado
3 Cenário de teste Resultado RED Falha documentada
4 Skill mínima Resultado GREEN Compliance verificado
5 Skill refinada Validação final Checklist ≥ 96 pts
</contratos_dados>

Read the full file on GitHub · 847 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. yesterday First seen · 847 lines · 31 tokens per session scan A 04b863994ef9

Subscribe to this mod's changes

criar-skill is a command published in the GitHub repository georgemarmelstein/superjurista-dev (20 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 7,552 once invoked, about $0.0002 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 2026-08-30.