Stock Qualitative Analysis

fakehank/stock_qualitative_analysis_skills

This is a structured workflow for generating buy-side style qualitative stock reports with mandatory source citations. It pulls SEC filings via EDGAR, extracts sections like Item 1A and 7 from 10-Ks, and fills out a chapter-by-chapter template in either Chinese or English. The core rule is strict: no claim without a citation, and if evidence is missing, you drop in a placeholder describing what's needed. It's built for Chinese market analysis but works for US listings too. The agent writes each section progressively and rewrites the executive summary only after all chapters are done. Honest take: the anti-hallucination discipline is real, but you'll need clean filings and patience for the section-by-section loop.

skills.sh installs: 148
GitHub stars: 28
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add fakehank/stock_qualitative_analysis_skills --skill stock-qualitative-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Stock Qualitative Analysis Skill

When to use

Use this skill when a user asks for a qualitative stock analysis report (定性分析) that must be evidence-based and formatted as a structured report. This skill emphasizes strict citations and non-hallucination behavior.

Inputs

Company name (required)
Ticker / exchange (optional but recommended)
Market context (US / HK / CN / other)
Time window (e.g., FY2015–FY2024; latest quarterly)
Language preference (Chinese default; English if requested)
Sources:
- User-provided filings (PDF or HTML)
- SEC EDGAR fetch (optional, if allowed)
- Other public sources (only if cited)

Outputs

A Markdown report following the template structure in assets/report-template.md
Each section contains: 结论要点 / 详细情况 / 证据与出处 (or English equivalents when English output is requested)
Final 来源清单 with SEC filings and other sources in reverse-chronological order

SKILL.md on GitHub