Tech Earnings Deep Dive

v1.0.0

科技股财报深度分析与多视角投资备忘录系统(v3.0)。覆盖A-P共16大分析模块、6大投资哲学视角、机构级证据标准、反偏见框架和可执行决策体系。当用户提到某科技公司财报分析、季报/年报解读、earnings call、收入增长分析、利润率变化、guidance指引、估值模型、DCF、反向DCF、EV/EBITDA...

0· 130·2 current·2 all-time
byStar@star23
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
The name/description promise (institutional-grade earnings deep-dive for tech stocks) matches the SKILL.md content. The skill does not request unrelated binaries, environment variables, or credentials.
Instruction Scope
SKILL.md stays focused on earnings/financial analysis and outlines a detailed 16-module workflow. However the instructions refer to local reference files (e.g., references/valuation-models.md, references/investing-philosophies.md, references/bias-checklist.md) that are not present in the repository manifest (only README.md and SKILL.md exist). The skill also instructs it should trigger on broad, common prompts (e.g., 'help me look at NVDA'), which is coherent with its purpose but means it may activate frequently for short/ambiguous queries.
Install Mechanism
There is no install spec in the registry (instruction-only skill), which is lower-risk. README suggests installing via a GitHub raw URL (/install-skill https://github.com/Day1Global/Day1Global-Skills/raw/main/tech-earnings-deepdive.skill) — GitHub raw is a common host, but any install-from-URL action fetches external content and should be inspected before installing.
Credentials
The skill requires no environment variables, credentials, or config paths. The referenced data sources (SEC filings, Glassdoor, etc.) are external public data and do not require secrets, so requested access is proportionate.
Persistence & Privilege
always:false (normal). disable-model-invocation:false (the agent may autonomously invoke the skill when relevant) — combined with the SKILL.md instruction to trigger on many common prompts, this means the skill could be invoked often. This is expected for a topic-based analysis skill but worth being aware of.
Assessment
This skill appears to do what it says (institutional-style, multi-perspective earnings analysis) and doesn't request credentials or unusual system access. Before installing: 1) Be aware the SKILL.md references supporting files (references/*.md) that are not included — ask the publisher or check for a complete package if you expect those templates. 2) The README suggests installing via a GitHub raw URL; if you follow that, inspect the downloaded .skill file content before installing to ensure it contains only expected instructions. 3) The skill is designed to trigger on broad, common prompts about earnings; if you prefer fewer autonomous activations, consider controlling invocation or checking your agent's skill-trigger settings. 4) Confirm how the agent will fetch primary sources (web access) and whether that aligns with your privacy expectations. If you want higher assurance, request the missing reference files and/or a published homepage or source repository with full contents and version history before installing.

Like a lobster shell, security has layers — review code before you run it.

latestvk97c2vjk634x94edm9341hyx1n839wnh

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments