investoday-fund-comprehensive-diagnosis
v1.3.0面向公募基金综合诊断，聚焦收益表现、风险收益匹配、持仓结构、基金经理与费用分红特征。基于今日投资金融数据接口，自动识别基金代码并输出结构化基金综合诊断报告。触发词：基金诊断、基金分析、收益风险、持仓怎么看、长期持有、基金体检。
⭐ 0· 132·0 current·0 all-time
byinvestoday@kenneth-bro
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill is a high-level analysis/templating layer for fund diagnostics and delegates all data access to the declared dependency investoday-finance-data. Required capabilities (entity recognition, performance, holdings, fees, manager info) align with the described diagnostic outputs.
Instruction Scope
SKILL.md confines runtime actions to calling the listed toolIDs (entity-recognition, fund/basic-info, fund/performance-attribution, etc.) and producing a Markdown report. It does not instruct reading local files, accessing unrelated environment variables, or exfiltrating data to external endpoints outside the stated data provider.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is written to disk or downloaded by this skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill relies on a separate finance-data skill for API access; any credential needs would be handled by that dependency, not this skill.
Persistence & Privilege
always is false and the skill is user-invocable. Model invocation is allowed (normal default) but the skill does not request elevated persistence or cross-skill configuration changes.
Assessment
This skill appears coherent and low-risk on its face: it only defines analysis logic and calls a separate investoday-finance-data skill to fetch public fund data. Before installing, verify the investoday-finance-data skill itself — check what network endpoints it calls, what credentials (if any) it requires, and whether it logs or stores queries. Also remember that the SKILL.md's statement 'does not record or store user queries' is policy text and cannot be enforced — confirm implementation details of the data-providing skill if you need stronger privacy guarantees. If you are concerned about autonomous invocation, you can keep disable-model-invocation enabled at the agent level or review the agent's permission settings for invoking skills.Like a lobster shell, security has layers — review code before you run it.
dividend-profilevk97cnvq8k2ng7hw1nqgcw4wyhn83res6fee-analysisvk97cnvq8k2ng7hw1nqgcw4wyhn83res6fund-analysisvk97cnvq8k2ng7hw1nqgcw4wyhn83res6fund-checkupvk97cnvq8k2ng7hw1nqgcw4wyhn83res6fund-diagnosisvk97cnvq8k2ng7hw1nqgcw4wyhn83res6fund-managervk97cnvq8k2ng7hw1nqgcw4wyhn83res6holdings-structurevk97cnvq8k2ng7hw1nqgcw4wyhn83res6latestvk97cnvq8k2ng7hw1nqgcw4wyhn83res6risk-returnvk97cnvq8k2ng7hw1nqgcw4wyhn83res6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🩺 Clawdis