michaelrochonnn/mckinsey-bcg-consulting/fact-based-research-mckinsey
Claude Code and agent skill by michaelrochonnn/mckinsey-bcg-consulting
- community
Checking that the SKILL.md file is still in the repository.
Use when developing business solutions to avoid template-based answers, or when initiating research to efficiently leverage internal databases, expert networks, and existing knowledge rather than reinventing solutions.
Install
npx vskill@latest install michaelrochonnn/mckinsey-bcg-consulting/fact-based-research-mckinseySKILL.md
Fact-Based Research and Solution Development
When to Use
- Tempted to apply past solutions to new problems without validation
- Starting data collection for hypothesis validation
- Need to balance efficiency (leveraging existing work) with rigor (fact-based validation)
- Risk of "hammer and nail" cognitive bias (using familiar tools for all problems)
Core Workflow
1. Avoid Cookie-Cutter Solutions
Resist the temptation to apply standard answers:
- Recognize the Trap: Avoid "if you only have a hammer, every problem looks like a nail" syndrome
- Trust But Verify: Accept that intuition is often correct, but always verify with facts before concluding
- Execute Rigorous Analysis:
- Apply specific analytical tools (demand curve analysis, break-even calculations, budget analysis)
- Complete thorough evidence gathering before making recommendations
- Recognize that tools remain consistent, but their application must be customized
- Handle Counter-Intuitive Results: Be prepared for facts to contradict intuition (e.g., while 80% of pricing studies suggest raising prices, fact-based analysis may reveal you should lower them)
- Ensure Acceptance: Fact-based conclusions are more likely to be accepted by stakeholders than intuitive judgments
2. Leverage Existing Resources
Never reinvent the wheel; assume someone has studied similar problems:
Access Internal Databases:
- Search company databases (e.g., McKinsey's PD network) for similar industries and problems
- Review recent projects and internal research reports
- Invest time filtering through large result sets to find relevant files
- Use findings to guide project direction effectively
Consult Expert Resources:
- Engage information specialists who can access multiple sources (databases, libraries)
- Consult subject matter experts in specific domains (banking, manufacturing, etc.)
- Contact colleagues who have solved similar problems
- Reach out to professionals at other companies who have addressed comparable issues
Utilize External Sources:
- Access commercial databases (Lexis/Nexis, Dun & Bradstreet, Datastream)
- Review industry publications, business journals, and books
- Use internet resources and commercial libraries
Adapt for Environment:
- In large companies: Use corporate knowledge bases, training manuals, and experienced colleagues
- Working independently: Rely on industry magazines, data packages, internet, and local libraries
Key Principles
- Efficiency Through Leverage: Time is valuable; build on existing work rather than starting from scratch
- Validation Required: Past solutions provide starting points, not final answers
- Resourcefulness: Combine internal knowledge with external data for comprehensive analysis
Output
A customized, fact-validated solution supported by existing research and new data analysis, avoiding template-based recommendations.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingfact-based-research-mckinsey/SKILL.md
Popularity
- Repository stars
- 65
- Repository forks
- 11
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/michaelrochonnn/mckinsey-bcg-consulting/fact-based-research-mckinsey)