What is ag-criar-skill?

A tool for creating and improving coding-agent skills, which are reusable instruction sets for specific tasks. It can also evaluate existing skills, compare their performance, and improve the wording that decides when they are used.

Use it to create a skill, improve one already in the workspace, run quantitative evaluations, benchmark results, or optimize its triggering description.

It gives you a structured way to test whether a skill works, find weak instructions, and reduce cases where the wrong skill is triggered.

ag-criar-skill — Skill for Claude Code by andregusman-raiz

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 andregusman-raiz/a-gusman-claude --skill ag-criar-skill

Clone the repo

git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-criar-skill/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-criar-skill)

Your own site

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-criar-skill"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-criar-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-criar-skill"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-criar-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,421 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 4
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
medium Agent Snooping · line 33
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Rogue Agent · line 170
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.02421
Opus 5	$0.00024	$0.01210
Sonnet 5	$0.00010	$0.00484
Haiku 4.5	$0.00005	$0.00242

Measured 12d ago against content hash 4653880a70e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ag-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 12d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (eval-viewer/generate_review.py, scripts/__init__.py, scripts/aggregate_benchmark.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/ag-criar-skill/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ag-criar-skill — Criar e Melhorar Skills

Reasoning protocol (tier topo — Fable, equivalente a reasoning_effort=xhigh): Skill ruim contamina toda invocacao futura. ANTES de produzir SKILL.md: Exhaust 3+ formas de modelar a skill (escopo, gatilho, output); Verify com leitura de skills existentes do mesmo dominio; Falsify (em que casos esta skill seria invocada incorretamente?); Connect a uma dor real e mensuravel; Report os anti-patterns que a skill explicitamente evita. Detalhes: .claude/rules/deep-reasoning-directive.md.

Quem voce e

O Skill Engineer. Voce cria novas skills e melhora skills existentes atraves de um ciclo iterativo de draft, teste, avaliacao e refinamento.

Como voce e acionado

/ag-criar-skill criar [descricao]     → Criar nova skill do zero
/ag-criar-skill melhorar [ag-XX]      → Melhorar skill existente
/ag-criar-skill avaliar [ag-XX]       → Rodar evals em skill existente
/ag-criar-skill benchmark [ag-XX]     → Benchmark com analise de variancia
/ag-criar-skill description [ag-XX]   → Otimizar description para triggering
/ag-criar-skill                       → Modo interativo

Contexto do Sistema

Este workspace possui 45+ skills em ~/.claude/skills/. Skills seguem convencoes:

YAML frontmatter: name, description
Modelo recomendado no topo
Secoes: Quem voce e, Modos, Output, Anti-Patterns, Quality Gate
$ARGUMENTS no final para receber argumentos inline
Nomes: ag-XX-nome-do-skill para agentes, nome-pattern para patterns

Workspace de evals: ~/.claude/skills-workspace/

Loop Principal

O processo de criar/melhorar uma skill:

Decidir o que a skill deve fazer e como
Escrever um rascunho do SKILL.md
Criar test cases — prompts realistas que um usuario diria
Rodar claude-with-skill nos test cases (com baseline comparison)
Avaliar resultados qualitativamente (viewer HTML) e quantitativamente (assertions)
Melhorar a skill baseado no feedback
Repetir ate satisfeito
Otimizar description para triggering preciso

Read the full file on GitHub · 248 lines

Files

What ships with it

22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 248 lines · 49 tokens per session scan A 4653880a70e5

Subscribe to this mod's changes

ag-criar-skill is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 2,421 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.

Building agents Claude Code ai-agents automation developer-tools

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

taiyi-evolve

A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.

Dong90/oh-my-taiyiforge · 37 tokens

taiyi-diagram-c4

A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.

Dong90/oh-my-taiyiforge · 48 tokens

retrospective-audit

Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…

The01Geek/prflow · 91 tokens

docs

Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…

The01Geek/prflow · 97 tokens

tmux-lane-orchestrator

Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.

vincentkoc/dotskills · 46 tokens