Not in the top 1,000 by GitHub stars

clxxxy/ratar-ia

RatarIA | Skill para agentes de IA pesquisarem aplicações, sites, features e produtos em profundidade.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/rataria/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → b81c9c236b3a

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit b81c9c236b3a9231b87f6744fc9b64d0f8ea0524

git clone --filter=blob:none --no-checkout https://github.com/clxxxy/ratar-ia.git .hotskills/clxxxy-ratar-ia && git -C .hotskills/clxxxy-ratar-ia checkout --detach b81c9c236b3a9231b87f6744fc9b64d0f8ea0524 # Copy each selected skill directory from .hotskills/clxxxy-ratar-ia into .claude/skills/<skill-name>/
3GitHub stars
Not availablestars in 7 days
1skill in this repository
8commits in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Nov 6, 2026Nov 6, 20263

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

rataria

When your agent uses it

Use when the user requests pesquisa aprofundada, pesquisa estilo rato, investigar por todos os cantos, levantamento completo, deep research, or a source-grounded study of a product, API, tool, process, market, or unfamiliar subject. Also use when competing claims, outdated tutorials, or scattered sources make a single-page answer insufficient.

What it loads into context

Frontmatter

75 tokens

Always available to the agent

SKILL.md

1,344 tokens

When the skill is activated

Reference documents

8,010 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Regras permanentes
  2. Contrato de entrada
  3. Recursos por necessidade
  4. Ciclo de investigação
  5. Encerramento e atualização

Scripts executed separately

  • scripts/validar-acervo.mjs

Files

  • ../../.claude-plugin/marketplace.jsonasset332 bytes
  • ../../.claude-plugin/plugin.jsonasset387 bytes
  • SKILL.mdcore6,083 bytes
  • assets/estrutura-relatorio.mddoc5,277 bytes
  • assets/exemplo-acervo.jsonasset3,328 bytes
  • references/acervo.mddoc9,336 bytes
  • references/coordenacao.mddoc4,757 bytes
  • references/descoberta.mddoc5,895 bytes
  • references/metodo.mddoc10,051 bytes
  • scripts/validar-acervo.mjsruns17,157 bytes
Read SKILL.md

# RatarIA

Investigar sistematicamente todas as superfícies pertinentes e acessíveis,
preservar os achados e demonstrar o que ainda falta. Amplitude não é onisciência:
não transformar documentação, relatos ou ausência de evidência em fato operacional.

## Regras permanentes

- Material fornecido, simulação e navegação real são diferentes. Nunca invente
  consultas, rodadas, saturação, leitura integral, bloqueios ou testes.
- Uma página pedir login não prova que outras fontes sejam privadas. Peça acesso
  somente à lacuna demonstrada; o usuário autentica em conta existente no navegador.
  Nunca receba senha, token, cookie ou MFA no chat. Sem acesso, continue o restante.
- Não criar nem orientar criar trial, conta ou contratação; não aceitar termos,
View the complete source on GitHub

Skills included

  • rataria

Repository facts

License
MIT
Created
Nov 4, 2026
Last pushed
Nov 6, 2026
Forks
0
Open issues
0
Project activity
Active

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 7, 2026

Show all 11 signals by file

.claude-plugin/plugin.json

  • Network accessline 4
    "description": "Pesquisa aprofundada com fontes rastreaveis, acervo persistente e auditoria de cobertura.",   "author": { "name": "clxxxy" },   "homepage": "https://github.com/clxxxy/ratar-ia",
  • Network accessline 5
    "author": { "name": "clxxxy" },   "homepage": "https://github.com/clxxxy/ratar-ia",   "repository": "https://github.com/clxxxy/ratar-ia",
  • Network accessline 6
    "homepage": "https://github.com/clxxxy/ratar-ia",
  • Network accessline 7
    "repository": "https://github.com/clxxxy/ratar-ia",

skills/rataria/assets/exemplo-acervo.json

  • Network accessline 37
    {       "id": "S2",       "url": "https://example.invalid/limits.pdf",
  • Network accessline 38
    "id": "S2",       "url": "https://example.invalid/limits.pdf",       "title": "Limites, apenas mencionado no pacote",
  • Network accessline 39
    "url": "https://example.invalid/limits.pdf",
  • Network accessline 71
    "id": "F1",       "question": "Obter e examinar notas do PDF de limites",       "url": "https://example.invalid/limits.pdf",
  • Network accessline 72
    "question": "Obter e examinar notas do PDF de limites",       "url": "https://example.invalid/limits.pdf",       "source_ids": ["S1", "S2"],
  • Network accessline 73
    "url": "https://example.invalid/limits.pdf",

skills/rataria/scripts/validar-acervo.mjs

  • Executable scriptline 1
    Executable file

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 1 fact

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/rataria/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/rataria/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/rataria/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/rataria/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/rataria/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.