pesquisa-profundaPesquisa profunda com pipeline de 8 fases: escopo, planejamento, recuperação, triangulação, síntese, crítica, refinamento e empacotamento. Relatórios com cit...
Install via ClawdBot CLI:
clawdbot install engsathiago/pesquisa-profundaGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/eve-agent/pesquisa-profunda/issuesAudited Apr 17, 2026 · audit v1.0
Generated May 7, 2026
A graduate student uses the 8-phase pipeline to conduct a comprehensive literature review on machine learning in healthcare, ensuring all claims are verified and cited from peer-reviewed sources.
A market analyst researches the Brazilian fintech sector, using triangulation to validate trends from multiple financial databases and news sources, producing a report with executive summary.
A government consultant analyzes the impact of a new environmental regulation on agriculture, employing the pipeline to scope key stakeholder groups and critiquing biases in reports.
A business strategist gathers intelligence on competitors in the e-commerce space, synthesizing findings into a structured report with citations from public filings and news articles.
Offer deep-dive research reports to corporate clients on-demand. Use the 8-phase pipeline to ensure quality and citations, charging per report or subscription tier.
License the skill to universities or research institutions as a tool for students and faculty to conduct rigorous literature reviews, with customization for academic citation styles.
Integrate the skill into consulting engagements for strategy or policy work, providing clients with verified insights as a differentiator. Charge as part of overall consulting fees.
💬 Integration Tip
Start by using the pipeline end-to-end on a small topic to train users. Then integrate via API calls that trigger the agent to run the phases sequentially, outputting a final report.
Scored May 7, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.