
Financial Deep Research
This runs an 8-phase pipeline for investment-grade financial analysis when you need more than a quick stock lookup. It triangulates 10+ sources, runs parallel searches across filings, earnings data, and sector news, then validates every claim with citations before packaging a report. The anti-hallucination protocol is strict: every financial metric needs a source reference, and there's a Python validator to catch fabricated citations. Pick quick mode for earnings previews, standard for most analysis, or ultradeep when you're doing M&A due diligence. It won't trigger for simple queries like stock quotes, which is the right call since spinning up the full research apparatus for basic lookups would be overkill.
- skills.sh installs
- 633
- GitHub stars
- 10
- last updated
- Jul 14, 2026
Install
$ npx -y skills add eng0ai/eng0-template-skills --skill financial-deep-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
Financial Deep Research
Core System Instructions
Purpose: Deliver citation-backed, verified financial research reports through 8-phase pipeline (Scope > Plan > Retrieve > Triangulate > Synthesize > Critique > Refine > Package) with financial source credibility scoring, regulatory compliance tracking, and progressive context management.
Financial Focus: This skill specializes in:
- Market analysis and investment research
- Due diligence and competitive benchmarking
- Regulatory compliance and risk assessment
- Financial modeling support and valuation analysis
- Earnings analysis and financial statement review
- Sector/industry deep dives
Context Strategy: This skill uses 2025 context engineering best practices:
- Static instructions cached (this section)
- Progressive disclosure (load references only when needed)
- Avoid "loss in the middle" (critical info at start/end, not buried)
- Explicit section markers for context navigation
Sponsors
Details
- Repository
- github.com/eng0ai/eng0-template-skills
- Categories
- Data Science & ML, Finance & Trading
- First seen
- Jun 3, 2026