Quiver — Skills de Pesquisa Profunda e Análise GTM
rainearcher/quiver
Pesquisa web profunda com citações, análise competitiva e relatórios GTM estruturados
Ver no GitHubColeção de skills para Claude Code e agentes que implementam pesquisa web profunda com citações via Perplexity, análise competitiva e auditoria GTM. Inclui workflow de aprovação de plano, orçamento por requisição e relatórios estruturados com fontes, comparações tabulares e análise de divergências entre fontes.
Instalação
npx convez-ai rainearcher/quiver1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Análise competitiva e pesquisa de concorrentes com citações
- Pesquisa de mercado, auditoria GTM e landing pages
- Matrizes de comparação de features e vendors
- Briefs para investidores e due-diligence
- Relatórios estruturados multifonte com confiança explícita
Veredito

Skill maduro e bem-documentado que sistematiza pesquisa profunda via Perplexity com controle de custos e qualidade de saída. Essencial para times de GTM, product e análise que precisam de pesquisa sourced em escala sem gastar sem limite.
README
A tradução para o português deste README ainda está na fila.
quiver
A collection of Claude Code skills and plugins by Raine Soriano. Each skill is an arrow you can pull out when you need it.
Install
The skills work with Claude Code, OpenCode, Codex, Cursor, and 40+ other agents via the skills CLI:
# Install a specific skill
npx skills add rainearcher/quiver perplexity-research
# Or browse all skills interactively
npx skills add rainearcher/quiver
Claude Code users can also install via the plugin marketplace:
/plugin marketplace add rainearcher/quiver
/plugin install perplexity-research@quiver
From the shell (non-interactive):
claude plugin marketplace add rainearcher/quiver
claude plugin install perplexity-research@quiver
Skills
perplexity-research — deep web research with citations
Multi-step web browsing via Perplexity's Agent API, enforced with a plan-approval workflow. Good for:
- Competitive analysis & competitor research
- Market research, GTM audits, landing-page audits
- Feature comparisons, vendor matrices
- Market stack-rank for expansion
- Investor-memo background, due-diligence briefs
- Any "sourced brief" or "research report" that benefits from many sources + inline citations
Methodology: enforces the Growth Unhinged GTM deep-research playbook — five-dimension intake, plan approval before API spend, per-call output-budget gating, and a structured sourced report (TL;DR, comparison tables, inline citations, Sources table, Where-sources-disagree, Confidence & gaps).
Prerequisites:
- A Perplexity API key — get one at https://www.perplexity.ai/account/api
curlandjq(pre-installed on most Unix systems)
Setup:
# After installing the skill
export PERPLEXITY_API_KEY=pplx-...
# Verify everything is wired up
bash skills/perplexity-research/scripts/check-setup.sh
To make the key permanent, add the export to your shell rc (~/.zshrc, ~/.bashrc) or ~/.claude/.env, then restart the CLI.
Usage: ask your agent for "deep research on X" or "a sourced brief on Y". The skill will gather context, draft a research plan, wait for your approval, then run the research and write a markdown report to ./docs/research/<topic>/.
A typical run takes 2–5 minutes and costs $0.30–$1.50. See skills/perplexity-research/SKILL.md for the full workflow and skills/perplexity-research/TROUBLESHOOTING.md for recovery from HTTP 429, empty Sources, truncation, etc.
Examples: see skills/perplexity-research/examples/ for simple queries, dependency-driven multi-call splits, and expert-comparison patterns.
Updating
/plugin marketplace update quiver
Claude Code refreshes the marketplace and pulls any plugin changes. For npx skills, run npx skills update.
Uninstalling
Claude Code:
/plugin uninstall perplexity-research@quiver
Skills CLI:
npx skills remove perplexity-research
Contributing
Issues and PRs welcome at https://github.com/rainearcher/quiver. Each skill lives under skills/<name>/ with its own SKILL.md, scripts, examples, and troubleshooting doc.
License
MIT — see LICENSE.
Author
Raine Soriano — AI software engineer building EDA, agentic, and full-stack apps.
- GitHub: @rainearcher
- LinkedIn: rainesoriano
- Email: raine.a.soriano@gmail.com