Deep Company Series
Analyze a company across eight in-depth written reports covering different aspects.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/deep-company-series-xbtlin/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Use when you want a company dissected in depth — produces an eight-part written series covering the business, its economics, competition, and risks.
What this skill does
This skill produces an eight-part deep-dive written series analyzing a company across business fundamentals, competitive position, financial structure, and valuation. Each installment (4,000–12,000 words) stands alone for sharing but ties into a cohesive investment framework spanning recognition resets, moats, revenue engines, hidden assets, industry headwinds, financial mechanics, management quality, and valuation scenarios. The core differentiator is ruthless fact-checking—the skill systematically eliminates "false precision" (arbitrary probability weighting, linearly extrapolated growth, misaligned peer comparisons) that corrupts most financial writing.
What it does
- Eight-essay structure: progresses from dismantling common misconceptions → durable competitive advantages → profit drivers → off-balance-sheet value → sectoral disruption exposure → Buffett-style financial parsing → management capital allocation + succession → multi-scenario DCF with deal/exit triggers.
- Fact-checking rigor: enforces cross-paper numerical consistency (valuation multiples, share count, stake percentages), flags and eliminates unweighted probability arithmetic, requires third-party data sourcing (QuestMobile, equity research) with margin-of-error disclaimers, and eliminates causal overreach.
- Plain-language rigor: bans hedging absolutes ("evidently," "necessarily"), removes subjective puffery ("perfect," "textbook-level"), and requires two-sided argument frames for each core claim.
- Style guardrails: contrarian headlines anchored to numeric hooks or consensus breaks; no influencer comparisons ("China's Buffett"); vocabulary aligned to institutional readers (GAAP vs. Non-IFRS mouth).
- Modular workflow: completed essays stored per company; full cross-series audit performed after all eight pieces; revision cycle ties data changes to downstream references (e.g., revaluing market cap ripples through PE, FCF yield, holding % tables).
How to use it
Hand the skill a company name and your target publication surface (WeChat Official, video platforms, etc.). The skill will conduct a five-year financial deep-dive, cross-check against 2–3 independent equity research reports, and ask you to lock in 8-essay thesis points before writing begins. After delivery, you review each piece; the skill processes your edits by verifying facts against latest filings, categorizing revisions by severity (hard error vs. subjective tone), and refreshing all dependent figures across the series before final push to your repository.
Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.
Related skills
Generative Code Art
anthropics
Create algorithmic art with p5.js using randomness and interactive parameters.
PPTX Text Extractor
axoviq-ai
Extract text and speaker notes from PowerPoint presentations.
Directory Submissions Tracker
coreyhaines31
Submit your product to startup and SaaS directories for backlinks and discovery.
Executive Stress-Test Mentor
alirezarezvani
Challenge your business decisions and plans with adversarial questions before they fail.