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 tatagoncalvesof/imperatriz-toolkit --skill deep-market-researchgit clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-toolkitWrote 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/tatagoncalvesof/imperatriz-toolkit/deep-market-research)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/deep-market-research"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/deep-market-research/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/tatagoncalvesof/imperatriz-toolkit/deep-market-research"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/deep-market-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00224 | $0.03268 |
| Opus 5 | $0.00112 | $0.01634 |
| Sonnet 5 | $0.00045 | $0.00654 |
| Haiku 4.5 | $0.00022 | $0.00327 |
Grade A, and why
deep-market-research 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 11d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Market Research — Motor de VOC Multi-Plataforma
Captura a linguagem real do comprador em 5 plataformas, mapeia objeções por trás de cada termo e gera ponte estratégica busca → produto. Diferente de /deep-research (relatórios acadêmicos/B2B com format-control rígido), esta skill é o motor tático que abastece toda a stack de copy/persona/conteúdo da Tata com matéria-prima REAL extraída de Google/YouTube/TikTok/Instagram/LinkedIn ao vivo.
Pensar com a cabeça do comprador, não com a do dono do produto.
Quando usar
Ative quando o usuário pedir:
- "pesquisa de mercado profunda" / "pesquisa de mercado pra meu nicho"
- "o que meu público pesquisa de verdade"
- "quais as objeções do meu cliente"
- "ideias de conteúdo do zero" / "não sei sobre o que postar"
- "social listening" / "voice of customer" / "VOC"
- "mapeamento de audiência multi-plataforma"
- "thinking with the buyer's head"
- Antes de rodar
/skill-persona-profunda,/calendario-imperatriz,/briefing-copy-360quando o nicho é novo ou pouco mapeado
NÃO use pra: relatório acadêmico/literatura/policy brief (→ /deep-research), análise de concorrente específico (→ /competitors-analysis), análise de anúncio existente (→ /analise-anuncio-1000).
Modos
| Modo | Quando usar | Saída |
|---|---|---|
--full (padrão) |
Pesquisa completa 5 plataformas, 50 termos, 150 objeções | Relatório mestre + JSON canônico |
--canal=<google|youtube|tiktok|instagram|linkedin> |
Foco em um único canal | Relatório por canal |
--rapido |
20 termos top, 1 objeção por termo, 1h de execução | Mini-relatório acionável |
--auditar=<arquivo> |
Audita pesquisa existente contra os 10 anti-patterns | Relatório de drift + correções |
--atualizar=<arquivo> |
Refaz pesquisa de relatório antigo, mostra o que mudou | Diff temporal |
Workflow das 7 fases
[1] Briefing de Escopo → entrevista o usuário em 8 perguntas
[2] Plano de Queries → monta query set por plataforma
[3] Coleta Multi-Plataforma → WebSearch/WebFetch ao vivo
[4] Extração de Linguagem → captura termos EXATOS, não parafraseados
[5] Mapeamento de Objeções → 3 objeções por top-50 termo
[6] Ponte Busca → Produto → ideias de conteúdo conectando intent + oferta
[7] Empacotamento + Validação → roda 10 validadores, salva no vault
What ships with it
10 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.
- references/01-platforms-playbook.md 9.2 KB
- references/02-objection-mapping.md 6.9 KB
- references/03-content-bridge.md 7.1 KB
- references/04-output-formats.md 6.8 KB
- references/05-anti-ai-slop.md 7.3 KB
- references/06-integracao-stack.md 6.8 KB
- scripts/research_engine.py 6.5 KB runs code
- templates/relatorio-mestre.md 5.9 KB
- templates/relatorio-por-canal.md 4.0 KB
- templates/saida-canonica.json 6.2 KB
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.
- 11d ago First seen · 215 lines · 224 tokens per session scan A ddc66568b517
deep-market-research is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 224 tokens to every session and 3,268 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
feature-dev
Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.