deep-research SKILL.md skillA
deep-research from joaoguirunas/team-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add joaoguirunas/team-os/deep-research@v1.0Pins v1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- joaoguirunas/team-os
- Path
.claude/skills/deep-research/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0, committed Sep 26, 2026
- First version recorded
- Apr 24, 2026
- Size
- 5,770 bytes
- Repository stars
- 5
- License
- MIT
Pesquisa multi-fonte com rastreio de citações, persistência de evidências e relatório estruturado. Use quando o usuário pedir 'deep research', 'análise abrangente', 'relatório de pesquisa', 'compare X vs Y', 'tendências' ou 'estado da arte'. Não use para consultas simples, debugging ou perguntas respondidas com 1–2 buscas.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Deep Research **Quando usar esta vs. `brand-research`:** esta é pesquisa multi-fonte genérica com rastreio de citações e relatório estruturado sobre qualquer tema. Para auditar uma marca, mapear concorrentes e territórios de posicionamento, use `brand-research`. ## Workflow nativo vs esta skill O Claude Code tem um workflow bundled `/deep-research` que faz fan-out de web searches, cross-check de fontes e entrega um relatório citado. **Use o workflow nativo quando:** - A pergunta é factual e baseada em web (notícias, documentação pública, comparações rápidas) - Velocidade importa mais que rigor - Não precisa de persistência estruturada (evidence.jsonl, claims.jsonl) **Use esta skill quando:** - Precisa de rastreamento de evidências persistido em disco (`evidence.jsonl`, `claims.jsonl`) - Precisa de verificação de claims no nível atômico com ledger auditável - Relatório final em formato McKinsey (HTML/PDF com citações inline) - Research de múltiplas fases com critique e refinement - O rigor importa mais que a velocidade Para ativar o workflow nativo: `/deep-research <pergunta>` ou use a keyword `ultracode` no prompt. Monitore com `/workflows`. --- ## Core Purpose …
Read the whole file at its exact version.
How to install
mdr add joaoguirunas/team-os/deep-research@sha256:ba21e0b365b7c947The line at the top of this page pins the label v1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6eewl5564abyfmi6)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 24, 2026 and Sep 26, 2026, about one every 39 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0 latest | 2026-09-26 | 8a9bf22 | 5,770 B | A | view · diff |
| v1.0 | 2026-09-05 | 1e1acb4 | 5,443 B | A | view · diff |
| git:20260619.827a48d | 2026-06-19 | 827a48d | 5,282 B | A | view · diff |
| git:20260503.a9b33f7 | 2026-05-03 | a9b33f7 | 4,355 B | A | view · diff |
| git:20260424.dbc5eaa | 2026-04-24 | dbc5eaa | 4,343 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5770 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
joaoguirunas/team-os · 5 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6eewl5564abyfmi6 GET https://markdownregistry.com/api/v1/resolve?ref=joaoguirunas/team-os/deep-research GET https://markdownregistry.com/api/v1/blob/ba21e0b365b7c947ab98a6239bf235f0fb8ede35fdca8da7dcedc981456f17f2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from joaoguirunas/team-os
Every file in joaoguirunas/team-os