longbridge-ark-analysis
ARK-style single-stock disruptive-innovation diagnostic. Suitability gate on 4 dimensions (platform fit / innovation revenue / R&D intensity / management vision); if it passes, builds TAM (low/base/high), Wright's-Law cost curve with sourced learning rate, three-scenario 5-year target (Bull/Base/Bear, 15% discount), risks, conditional action frame. Data: Longbridge CLI first, MCP fallback, WebSearch only for TAM / learning rates / industry runway. Runs cross-statement reconciliation BEFORE analysis. Closes with a data-source appendix whose final row is the reconciliation summary. Independent i
npx skills add majiayu000/claude-skill-registry --skill longbridge-ark-analysis --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Prompts the agent to perform an ARK-inspired diagnostic on a single stock. It first runs a reconciliation gate, then applies a four-dimension suitability gate (platform fit, innovation revenue, R&D intensity, management vision). If it passes, it builds a TAM (low/base/high), adds a Wright's-Law cost-curve note with a sourced learning rate, and generates three 5-year scenarios (Bull/Base/Bear) with explicit assumptions. It concludes with a data-source appendix and a reconciliation summary. Outputs must be in one language chosen by user, and includes an independence disclaimer in the final section.
How it works
- Resolve symbol and fetch data via Longbridge CLI first, with MCP fallback if needed.
- Run a Reconciliation gate before any scoring; if it fails, halt downstream analysis but still print the data-source appendix and reconciliation summary describing the failure.
- Perform Suitability scoring across 4 dimensions (强/中/弱); if Young-company mode is active, assess with available history and require management-vision milestones.
- If passes, construct TAM with three tiers (low/base/high) and tag sources by priority; compute a Wright's-Law learning-rate note sourced from web data and verified against authorities.
- Generate three 5-year scenarios (Bull/Base/Bear) including TAM, market share, net margin, and terminal multiple; apply discount rate of 15% over 5 years; report scenario prices and a weighted expectation.
- In Young-company mode, adjust year-5 share count via dilution path and include runway considerations.
- Compile Risks, conditional action frame, and a final data-source appendix row with reconciliation summary; end with an independence-disclaimer variant in the user language.
When to use it
- Use when analyzing a disruptive-innovation candidate and you want a structured ARK-style diagnostic with TAM, learning-rate, and three scenario analysis.
- Suitable for cases where the company is in ARK’s platform categories and has enough forward-looking inputs to build a forward-looking model.
What it can touch
- Longbridge CLI data (symbol resolution, financials, basic info) as primary inputs.
- WebSearch for TAM and Wright's-Law inputs when Longbridge data is insufficient.
- Data-source appendix compiles sources, including WebSearch provenance with explicit tagging.
Caveats
- Output language is user-selected; all sections are in that language and must remain single-language per output.
- Independent implementation; not affiliated with ARK Invest; independence statement appears in the disclaimer.
- If reconciliation or data fetch fails, downstream analysis halts and the halt is disclosed with the failing check and gap described in the reconciliation section.
# longbridge-ark-analysis Prompt-only ARK-inspired diagnostic for a single ticker. Runs a suitability gate (must be a disruptive-innovation name), then builds TAM, a Wright's-Law cost-curve note, and a three-scenario 5-year target price. Closes with a mandatory data-source appendix whose final row is a one-line reconciliation summary. > **Response language**: detect the user's input language (Simplified Chinese / Traditional Chinese / English) and render the **entire report — every section heading, label, scenario write-up, narrative, education block, appendix row, reconciliation summary, and disclaimer — in that one language**. Do not mix languages within a single output. The output template in `references/output.md` is shown in English for reference; translate it as a whole into the user's language using the label-translation lookup in that file. The error / source tables inside *this* SKILL.md remain 3-column because they document what the skill says under each language — that 3-column form is for the skill's reference docs, not for the user-facing report. > **Independence statement (mandatory)**: this skill is an independent implementation inspired by ARK Invest's publicly desc
- When to use
- Cognitive frame (do not skip)
- Workflow
- CLI
- WebSearch fallback — only for items not available from Longbridge
- Reconciliation (勾稽校验)
- Output
- Error handling
- MCP fallback
- Related skills
- File layout
Balance sheet — equity, debt, working capital (for reconciliation only; ARK analysis is forward-looking) longbridge financial-report <SYMBOL> --kind BS --report af --format json # last 3–5 annual longbridge financial-report <SYMBOL> --kind BS --report qf --format json # last 4 quarterly Income statement — revenue, segment mix, gross/operating margin, R&D longbridge financial-report <SYMBOL> --kind IS --report af --format json longbridge financial-report <SYMBOL> --kind IS --report qf --format json Cash flow — CFO, capex, FCF; for reconciliation and capital-intensity context longbridge financial-report <SYMBOL> --kind CF --report af --format json longbridge financial-report <SYMBOL> --kind CF --report qf --format json longbridge quote <SYMBOL> --format json
What does the longbridge-ark-analysis skill do?
ARK-style single-stock disruptive-innovation diagnostic. Suitability gate on 4 dimensions (platform fit / innovation revenue / R&D intensity / management vision); if it passes, builds TAM (low/base/high), Wright's-Law cost curve with sourced learning rate, three-scenario 5-year target (Bull/Base/Bear, 15% discount), risks, conditional action frame. Data: Longbridge CLI first, MCP fallback, WebSearch only for TAM / learning rates / industry runway. Runs cross-statement reconciliation BEFORE analysis. Closes with a data-source appendix whose final row is the reconciliation summary. Independent i
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill longbridge-ark-analysis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.