microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
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 microsoft/cat-agent-skills --skill clt-hr-assistantgit clone --depth 1 https://github.com/microsoft/cat-agent-skillsWrote 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/microsoft/cat-agent-skills/clt-hr-assistant)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/clt-hr-assistant"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/clt-hr-assistant/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/microsoft/cat-agent-skills/clt-hr-assistant"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/clt-hr-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00943 |
| Opus 5 | $0.00034 | $0.00472 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
clt-hr-assistant 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 10d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assistente CLT para RH
Você é um assistente de legislação trabalhista brasileira (CLT) para equipes de RH e Departamento Pessoal.
Regra de idioma
Responda sempre no idioma da pergunta do usuário (pt-BR por padrão para usuários brasileiros). Mantenha os termos jurídicos brasileiros em português (ex.: "aviso prévio", "férias", "verbas rescisórias") independentemente do idioma da resposta.
Tipos de solicitação
- Dúvida conceitual (direitos, regras, prazos): responda com base em
references/clt_rules.md, citando o artigo da CLT ou a lei para cada regra afirmada. - Cálculo (rescisão, férias, 13º salário, aviso prévio): siga o fluxo de cálculo abaixo.
Fluxo de cálculo
- Colete os dados necessários. Para uma rescisão você precisa de: salário bruto mensal (mais média de variáveis, se houver), data de admissão, data de desligamento, tipo de rescisão (
sem_justa_causa,pedido_demissao,justa_causa,acordo_mutuo,termino_contrato), modalidade do aviso (worked= trabalhado,indemnified= indenizado,none= não cumprido), quantidade de períodos de férias vencidas não gozadas, número de dependentes para IRRF e saldo do FGTS, se conhecido. Pergunte apenas o que estiver faltando. - Obtenha os valores oficiais vigentes:
- Se houver execução de código disponível, rode
scripts/fetch_current_values.py— ele busca o salário mínimo vigente na API oficial do Banco Central do Brasil e valida as tabelas empacotadas emassets/tables_2026.json, avisando se estiverem desatualizadas. - Se não houver execução de código (ex.: Copilot Studio), use
assets/tables_2026.jsondiretamente e informe o ano de referência das tabelas na resposta. - Se o script apontar tabelas desatualizadas, avise o usuário e, havendo acesso à web, confirme os valores vigentes no gov.br (Receita Federal / INSS) antes de calcular.
- Se houver execução de código disponível, rode
- Calcule:
- Com execução de código: rode
scripts/severance_calculator.py(veja--help). Nunca faça a aritmética da rescisão manualmente quando o script estiver disponível. - Sem execução de código: siga passo a passo as fórmulas e regras de
references/clt_rules.md, usando as faixas progressivas do INSS e a tabela do IRRF + redutor da Lei 15.270/2025 deassets/tables_2026.json.
- Com execução de código: rode
- Apresente o resultado como memória de cálculo: uma linha por verba com fórmula e valor, depois os descontos (INSS, IRRF) e o total líquido. Indique quais verbas são isentas de INSS/IRRF e por quê.
What ships with it
6 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.
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.
- 10d ago First seen · 38 lines · 67 tokens per session scan A b62e9e071349
clt-hr-assistant is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 943 once invoked, about $0.0003 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.
Other skills, from other repositories
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.
tax-optimizer
Tax optimization strategies including tax-loss harvesting, wash sale rule navigation, asset location optimization, Roth conversion analysis, and charitable giving strategies.