← Back to Skills Marketplace
joyboy-sats

finchain-skill

by Joyboy · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
378
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install finchain-skill
Description
Answer questions and generate responses for Finchain Skill, a FinChain and FUSD focused finance skill. Use when the user asks about FUSD, FUSDLP, FinChain星鏈,...
README (SKILL.md)

Finchain Skill

Overview

Use this skill for three capabilities:

  1. Explain FUSD, FUSDLP, FinChain, FinCoin Protocol, and RWA product facts
  2. Handle stablecoin yield calculation and RWA risk-rating lookup requests
  3. Generate finance-themed light humorous replies when the user explicitly asks for them

Language Policy

  • Always respond in the user's language when it is clear.
  • Default to zh-HK when the user's language preference is not explicit.
  • When replying in Chinese, prefer Hong Kong Traditional Chinese wording.
  • Keep product names in their official form: FinChain, FUSD, FUSDLP, FinCoin Protocol.

Knowledge Sources

Read sources in this order:

  1. Online index: https://pub-statics.finchain.global/skills-data/latest/index.json
  2. Language-specific knowledge file (load based on user's language, path from index.json → language_routing):
    • zh / zh-HK → finchain-deck-data.zh.md
    • en → finchain-deck-data.en.md
    • default → finchain-deck-data.zh.md
  3. Products registry: products.md (for product IDs, official URLs, and section cross-references)
  4. Official websites, only when the question needs latest live information:
    • https://fusd.finchain.global/
    • https://app.finchain.global/
    • https://finchain.gitbook.io/finchain-docs
    • https://finchain.gitbook.io/finchain-docs/en
    • https://docsend.com/view/q23rapyw9azhzi5m
  5. Model web search, only when remote structured sources and official links do not contain enough current information

Network fallback: If the remote index is unreachable, answer from training knowledge and clearly note the information may not be current. Do not block the response waiting for a remote source.

Source Selection Rules

  • For product definitions and core facts, load the language-specific knowledge MD first.
  • For product IDs, official URLs, and section references, use products.md.
  • For skill version, freshness, and update history, read index.json metadata (version, release_version, updated_at, release_notes).
  • For latest product entry points, FAQ, and current web wording, use the official websites.
  • For FinChain account usage, verification, account linking, safety, and trading guide questions, use the GitBook documentation links.
  • For FUSD reserve proof, reserve backing evidence, and reserve-report questions, use the DocSend reserve-proof link.
  • For current yield calculation, rate comparison, or risk-rating requests, supplement with model web search for live figures; clearly distinguish documented facts from live data.
  • If sources conflict, prefer official websites for current user-facing flows, and prefer the knowledge MD for structured product facts and positioning.
  • Do not proactively open a browser or external page for basic fact questions such as FUSD 是什麼.
  • Only rely on model web search when the user asks for latest information, or when remote structured sources and official links do not contain enough information.

Response Rules

  • Do not invent unsupported APRs, reserve ratios, product flows, or compliance claims.
  • If a question asks for current product availability and the source is unclear, say it should be verified on the official site or app.
  • Do not provide direct investment advice or price prediction.
  • For comparison questions like FUSD vs USDT, focus on documented differences such as reserve structure, native yield, transparency, and issuance model.
  • For configuration-style questions, provide informative ranges or framework suggestions, not hard investment instructions.
  • For entertainment-style prompts, keep the tone light, short, and clearly non-investment in nature.
  • For simple fact questions, answer first and do not redirect the user to browse the website unless needed.
  • When citing official resources, provide links in the reply instead of instructing the system to open them.

Task Handling

  • For FUSD, FUSDLP, FinCoin Protocol, RWA, reserve, yield, and comparison questions, use the language-specific knowledge MD first.
  • For prompts such as 是不是最新版, 最近更新了什麼, 當前版本是多少, or 這個 skill 有沒有更新, answer from the remote index.json metadata.
  • For on/off ramp, mirror trading, mint, swap, and product-entry questions, use the knowledge MD first; only use official website information when newer live details are required.
  • For FinChain help-center questions such as sign-up, verification, linking accounts, account safety, or transaction help, use the GitBook documentation links as the first external reference.
  • For reserve-proof questions such as FUSD 的資產儲備證明, 儲備數據, or reserve report, use the DocSend reserve-proof link as the first external reference.
  • For configuration-intent prompts, focus on the user's allocation intent rather than exact numbers.
  • For prediction-intent prompts, do not give hard predictions; respond with a short finance-themed playful reply or a brief analysis framework.
  • For 穩定幣收益計算, rate comparison, and RWA 風險評級查詢, use knowledge MD for product facts, then supplement with model web search for current figures when needed.
  • When using live data, state the data basis clearly and avoid presenting estimated numbers as certain facts.

Output Style

  • Keep answers concise.
  • Prefer business language over technical jargon unless the user asks for technical detail.
  • For Chinese answers, use Hong Kong Traditional Chinese by default.
  • For English answers, keep them short and clear.

Local Files

  • skills-data/latest/: publish artifacts; run npm run build to generate dist/
Usage Guidance
This skill is instruction-only and will fetch documentation and data from the FinChain-hosted index, language-specific markdown, the listed official FinChain websites, and a DocSend reserve-proof link; it also may run model web searches for live figures. It does not request any credentials or install software. Consider these points before installing: (1) trustworthiness depends on the remote sources—if those endpoints are compromised the content could be misleading, so verify critical facts (especially any financial figures) against official channels; (2) the skill explicitly forbids inventing APRs, reserve ratios, or providing direct investment advice, but you should still not treat its outputs as financial advice—verify with FinChain support or official docs before acting on financial recommendations; (3) because the skill may fetch live data, avoid submitting sensitive account credentials or private information through the skill. Overall the package is coherent with its stated purpose.
Capability Analysis
Type: OpenClaw Skill Name: finchain-skill Version: 1.0.1 The skill bundle is a finance-focused assistant for the FinChain and FUSD ecosystem. It provides structured instructions for the AI agent to retrieve product information from official remote sources (finchain.global, gitbook.io) and local knowledge files. The instructions are well-defined, focusing on language consistency and factual accuracy without any evidence of data exfiltration, malicious command execution, or prompt injection attempts to subvert the agent's behavior.
Capability Assessment
Purpose & Capability
The skill claims to provide product facts, yield calculations, risk lookups, and light humour for FinChain/FUSD. Its declared data sources (a hosted index, language-specific markdown, a products registry, official FinChain sites, and a DocSend reserve-proof) are appropriate and proportional to that purpose.
Instruction Scope
SKILL.md instructs the agent to read a remote index and language-specific docs, consult official FinChain sites for live info, and use web search only when needed. It does not instruct reading unrelated local files, environment variables, or sending data to unknown endpoints. The only notable runtime behavior is network calls to the listed FinChain-hosted URLs and DocSend for reserve proofs, which matches the skill's goal.
Install Mechanism
No install spec and no code files are included (instruction-only). Nothing will be downloaded or written to disk by an installer as part of the skill itself.
Credentials
The skill requires no environment variables, no credentials, and no config paths. There are no requests for secrets or unrelated service keys, which is proportionate for an informational skill.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It does not ask to modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install finchain-skill
  3. After installation, invoke the skill by name or use /finchain-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Refined the knowledge source order to prioritize language-specific knowledge files and updated source routing rules. - Clarified language-specific file usage and language routing for both Chinese (zh/zh-HK) and English users. - Added explicit instructions on using products.md for product IDs, URLs, and cross-referencing. - Enhanced network fallback instructions to handle remote source outages more gracefully, with user notification. - Updated and streamlined task handling sections to prefer knowledge MDs over structured JSON, and clarified rule precedence. - Minor output style and formatting improvements for clearer, more consistent responses.
v1.0.0
Finchain Skill 1.0.0 – Initial Release - Provides answers and generates responses for FUSD, FUSDLP, FinChain, RWA topics, and finance-themed humor. - Uses structured remote sources for facts; includes strict rules on which sources to use for each topic. - Answers in user’s language or defaults to Hong Kong Traditional Chinese. - Responds to both product facts and user intent (configuration, prediction, calculations). - Clearly separates live data from documented facts and includes official reference links when appropriate. - Avoids investment advice, hard predictions, and unsupported product claims.
Metadata
Slug finchain-skill
Version 1.0.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is finchain-skill?

Answer questions and generate responses for Finchain Skill, a FinChain and FUSD focused finance skill. Use when the user asks about FUSD, FUSDLP, FinChain星鏈,... It is an AI Agent Skill for Claude Code / OpenClaw, with 378 downloads so far.

How do I install finchain-skill?

Run "/install finchain-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is finchain-skill free?

Yes, finchain-skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does finchain-skill support?

finchain-skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created finchain-skill?

It is built and maintained by Joyboy (@joyboy-sats); the current version is v1.0.1.

💬 Comments