Systematic investigation framework for research, root cause analysis, and evidence-based inquiry. Use when the user needs to investigate a technical question, debug a systemic issue, or research an unfamiliar area with structured evidence gathering. Triggers when user says "investigate this", "research this topic", "root cause analysis", "I need to understand how X works", "dig into this", or wants a structured investigation with findings and recommendations.
From project-docsnpx claudepluginhub ichabodcole/project-docs-scaffold-template --plugin project-docsThis skill uses the workspace's default tool permissions.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Retrieves current documentation, API references, and code examples for libraries, frameworks, SDKs, CLIs, and services via Context7 CLI. Ideal for API syntax, configs, migrations, and setup queries.
Uses ctx7 CLI to fetch current library docs, manage AI coding skills (install/search/generate), and configure Context7 MCP for AI editors.
A structured approach to conducting investigations that produces defensible, evidence-based conclusions.
Use this methodology when you need to:
Key indicator: The answer isn't immediately obvious and requires gathering evidence from multiple sources.
Define boundaries before diving in:
Stopping point: You have 2-3 testable hypotheses and know where to look for evidence.
Cast a wide net, then focus:
Stopping point: You have enough evidence to evaluate all hypotheses, or you've exhausted available sources.
Evaluate evidence against hypotheses:
Stopping point: You have a conclusion that explains all evidence, or you know why a conclusion isn't possible.
Structure findings for action:
Stopping point: Someone unfamiliar with the context could follow your reasoning.
Evidence Hierarchy: Prioritize by reliability:
Adversarial Thinking: Actively consider:
Timeline Reconstruction: Build chronological event sequences—time-based analysis often reveals causation that static analysis misses.
Follow the Data: Let evidence guide conclusions. When evidence contradicts hypotheses, abandon the hypothesis—not the evidence.
Document the Journey: Record not just what you found, but how you found it. Your investigation path may be valuable for future researchers.
Structure investigation outputs using the templates in
docs/investigations/README.md. Key sections:
# Investigation: [Topic]
## Summary
[2-3 sentence overview of findings]
## Background
[Context and why this investigation was needed]
## Methodology
[How you investigated - sources, approach]
## Findings
[Organized by theme or chronology]
### Finding 1: [Title]
**Evidence**: [What you found] **Source**: [Where you found it]
**Significance**: [What it means]
## Conclusions
[Your interpretation of the findings]
- Confidence level: [High/Medium/Low]
- Key uncertainties: [What you don't know]
## Recommendations
[What should be done based on findings]
## Appendix
[Supporting evidence, raw data, timelines]
Before concluding any investigation:
Simple investigation (clear problem, limited scope):
Moderate investigation (unclear cause, multiple systems):
Complex investigation (systemic issue, many unknowns):
Too complex? Consider breaking into multiple focused investigations.