Agent skill

Finance Core Analysis

by digoal in digoal/blog

Generate stage-2 deep financial mechanism analysis markdown from a daily-finance brief plus current web verification.

GPL-2.0Auto-check passedMarketing & SEO

Install Finance Core Analysis

skills CLI
$ npx skills add digoal/blog --skill finance-core-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog finance-core-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/finance-core-analysis .claude/skills/finance-core-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
finance-core-analysis
GitHub stars
8.6k
Token cost
~1.4k tokens
SKILL.md length
600 words
Files
1
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Generate stage-2 deep financial mechanism analysis markdown from a daily-finance brief plus current web verification.

  • Works in 3 steps: Verify & Update Data → Apply the Core Model → Validate Before Writing
  • The user wants deeper macro/market analysis beyond daily news
  • SKILL.md covers Overview, Input, Step 1: Verify & Update Data and Step 2: Apply the Core Model, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Finance Core Analysis is an agent skill from digoal/blog. Generate stage-2 deep financial mechanism analysis markdown from a daily-finance brief plus current web verification. Use this skill whenever the user wants deeper macro/market analysis beyond daily news, asks for "核心分析"、"深度分析"、"机制分析"、"为什么市场这样走"、"帮我分析一下背后逻辑", or when the user references a daily-finance output and wants the second step of the pipeline before writing a 公众号爆款文章. Even if the user only says "深挖一下今天的市场" or "帮我分析这份财经简报", use this skill. This skill feeds finance-explosive-article as stage 2 of…

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Market research. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • The user wants deeper macro/market analysis beyond daily news
  • Asks for 核心分析、深度分析、机制分析、为什么市场这样走、帮我分析一下背后逻辑
  • The user references a daily-finance output and wants the second step of the pipeline before writing a 公众号爆款文章

Example prompts

  • “为什么市场这样走”
  • “帮我分析一下背后逻辑”
  • “深挖一下今天的市场”
  • “/finance-core-analysis”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Verify & Update Data
  2. Apply the Core Model
  3. Validate Before Writing

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Finance Core Analysis loads about 1.4k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 600 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 600 words, ~1,374 tokens.

Download SKILL.mdSave it as .claude/skills/finance-core-analysis/SKILL.md (or your agent's skills folder).
name
finance-core-analysis
description
Generate stage-2 deep financial mechanism analysis markdown from a daily-finance brief plus current web verification. Use this skill whenever the user wants deeper macro/market analysis beyond daily news, asks for "核心分析"、"深度分析"、"机制分析"、"为什么市场这样走"、"帮我分析一下背后逻辑", or when the user references a daily-finance output and wants the second step of the pipeline before writing a 公众号爆款文章. Even if the user only says "深挖一下今天的市场" or "帮我分析这份财经简报", use this skill. This skill feeds finance-explosive-article as stage 2 of: daily-finance → finance-core-analysis → finance-explosive-article.

Core Financial Analysis

Overview

Generate a deep mechanism analysis grounded in stage-1 daily finance facts plus live-verified data.

Pipeline position:

daily-finance → finance-core-analysis → finance-explosive-article

Your output is a standalone, publishable 公众号 deep-analysis article — rigorous enough to stand alone, structured enough to feed the final explosive article downstream.


Input

Preferred: Read markdown/daily-finance-YYYY-MM-DD.md

Fallback order:

  1. Ask for the report date or file path if ambiguous
  2. If user pastes raw daily-finance content in chat, use that
  3. Never invent missing facts

Step 1: Verify & Update Data

Always access current external data before writing.

Use web search / browser / MCP tools to:

  • Re-check major market prices, yields, FX rates, commodities, volatility indices
  • Verify policy statements, macro releases (CPI/PMI/jobs), earnings, geopolitical facts
  • Update stale numbers from the stage-1 brief when newer reliable data is available

Source hierarchy:

  • Primary: Official releases, central banks, exchanges, regulators, company filings; Reuters, Bloomberg, FT, WSJ
  • Chinese primary: 财新, 第一财经, 财经杂志, 21世纪经济报道, 经济观察报
  • Secondary (require source backtracking): FT中文网, WSJ中文网, 新浪财经

Only add data that is source-verifiable. Never fabricate.


Step 2: Apply the Core Model

Explain market behavior through these variables:

VariableWhat to examine
流动性 LiquidityMoney supply, repo rates, bank reserves, credit conditions
利率 Interest ratesReal vs nominal; short vs long end; central bank signals
风险偏好 Risk appetiteVIX, credit spreads, EM flows, positioning
资本流动 Capital flowsCross-border flows, DXY, CNY pressure, EM vs DM
政策方向 PolicyFiscal, monetary, regulatory — direction and credibility
资产负债表压力 Balance sheetsCorporate leverage, bank stress, sovereign debt
激励约束 Incentive constraintsWhat is forcing or preventing capital allocation

Causal chain template:

事件 → 约束变化 → 资金行为 → 定价结果 → 风险信号

Use this chain to anchor every mechanism explanation.


Step 3: Validate Before Writing

Check every item:

  • Data: Dates correct? Units right? Directions accurate? Actual vs expected labeled? Intraday vs close distinguished?
  • Sources: Important claims have reliable sources?
  • Logic: Every conclusion follows from a mechanism, not mood words?
  • Causal chain: Event → constraint → capital behavior → pricing result → risk signal present?
  • Counter-case: Does the analysis include what would prove it wrong?
  • Publishability: Title, subheadings, short paragraphs, clear conclusion?

Output Format

1. Title

公众号-style: tension + mechanism. Prefer substance over clickbait.

2. 核心判断(Executive Judgment)

One paragraph: the single most important market judgment today, and what specifically changed.

Show full SKILL.md (245 more words)Show less
3. 事实基础(Fact Base)
  • Inherit 3–5 key facts from daily-finance with source labels 【实】【预】【估】【待】
  • Add newly verified data where necessary, clearly marked
  • No invented facts
4. 机制分析(Mechanism Analysis)

Analyze through 3–5 relevant lenses from the core model. For each lens:

  • What changed
  • Why it matters
  • How it transmits into asset prices

Use "不是A,而是B" contrast structure where helpful to clarify mechanism.

5. 核心矛盾(Core Contradiction)

Name the central tension driving the current market, e.g.:

  • 增长 vs 通胀
  • 政策宽松 vs 汇率压力
  • 风险偏好修复 vs 盈利压力
  • 流动性改善 vs 资产负债表收缩
6. 情景推演(Scenario Deduction)
情景触发条件资产含义
基准情景......
备选情景......
证伪信号......
7. 关键跟踪变量(Variables to Watch)

3–6 observable indicators for the next update cycle.

8. 方向性参考(Non-Advisory Implication)

Explain directional exposure and risk. No ticker calls, no buy/sell recommendations.

9. 数据来源

Inherited sources from daily-finance + any new verified sources, one per line.

10. 免责声明

本文仅供参考,不构成投资建议。


File Output

Save to:

markdown/finance-core-analysis-YYYY-MM-DD.md
  • Use the same report date as the input daily-finance file
  • Create markdown/ directory if missing
  • UTF-8 encoding
  • Output a complete publishable article, not notes
  • Fallback: If write fails, output full markdown in chat

Writing Style

  • Strong title, short paragraphs, numbered sections
  • Sharp but rational tone — serious analysis, not hype
  • Mechanisms explained in plain Chinese
  • Use contrast: "不是A,而是B"
  • No empty emotional phrases, no unexplained jargon
  • Publishable as-is on 公众号

Goal

Answer four questions every reader should leave with:

  1. What changed — the key fact
  2. Why it changed — the mechanism
  3. How facts connect to asset pricing — the transmission
  4. What would prove this wrong — the falsification signal

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/skills_for_claude_web/finance-core-analysis of digoal/blog.

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Finance Core Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Finance Core Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Finance Core Analysis this skilldigoal/blog8.6k—~1.4kAutomated safety check: PassGPL-2.0
Consulting Analysisbytedance/deer-flow84k4 repos~8.4kAutomated safety check: PassMIT
Startup Validatorailabs-393/ai-labs-claude-skills4541 repos~2.8kAutomated safety check: PassMIT
Competitive Analysis BriefNateBJones-Projects/OB14.7k—~1.1kAutomated safety check: PassCustom licence
Market AnalysisYicunAI/Pnlclaw-community197—~364Automated safety check: PassAGPL-3.0
Hehe Governance Capital Allocationhexiaofeier/hehe-industry-research-skill-pack304—~1.5kAutomated safety check: PassMIT

Similar skills

  • Consulting Analysis

    bytedance/deer-flow

    A skill your agent uses when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial…

    84k GitHub starsUsed in 4 repos~8.4k tokens
    Marketing & SEOAuto-check passed
  • Startup Validator

    ailabs-393/ai-labs-claude-skills

    Comprehensive startup idea validation and market analysis tool.

    454 GitHub starsUsed in 1 repo~2.8k tokens
    Marketing & SEOAuto-check passed
  • Competitive Analysis Brief

    NateBJones-Projects/OB1

    Turns a competitor set into a decision-ready brief: profiles, pricing and packaging comparisons, a positioning map, a SWOT and recommended moves for operators and founders.

    4.7k GitHub stars~1.1k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Market Analysis

    YicunAI/Pnlclaw-community

    Analyzes current market state and short-term trends using ticker, candle, and narrative context

    197 GitHub stars~364 tokensUpdated 6 mo ago
    Marketing & SEOAuto-check passed
  • Hehe Governance Capital Allocation

    hexiaofeier/hehe-industry-research-skill-pack

    盒子原创行业研究 Skill 组合中的治理与资本配置专项。判断公司的实际控制权与决策机制、管理层和股东激励、少数股东保护、关联交易及资本配置历史质量。用于“分析公司治理或实际控制人”“评估股权激励、关联交易、并购、融资、分红、回购或资本开支”等问题。

    304 GitHub stars~1.5k tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed
  • Research

    Gerstep/cybos

    Company due diligence, technology deep-dives, market analysis, and topic exploration for cyber•Fund investment decisions, content creation, and personal projects.

    104 GitHub stars~945 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated today
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Finance Core Analysis

What does Finance Core Analysis do?

Generate stage-2 deep financial mechanism analysis markdown from a daily-finance brief plus current web verification. Finance Core Analysis is an agent skill from digoal/blog. Generate stage-2 deep financial mechanism analysis markdown from a daily-finance brief plus current web verification.

When should I use Finance Core Analysis?

Finance Core Analysis fits situations like: the user wants deeper macro/market analysis beyond daily news; asks for 核心分析、深度分析、机制分析、为什么市场这样走、帮我分析一下背后逻辑; the user references a daily-finance output and wants the second step of the pipeline before writing a 公众号爆款文章.

How do I install Finance Core Analysis in Claude Code?

Run `npx skills add digoal/blog --skill finance-core-analysis -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/finance-core-analysis in digoal/blog) into .claude/skills/finance-core-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Finance Core Analysis in Codex?

Run `npx skills add digoal/blog --skill finance-core-analysis -a codex`. Or copy the skill folder (skills/skills_for_claude_web/finance-core-analysis in digoal/blog) into .agents/skills/finance-core-analysis in your project. Codex loads it when a task matches its description.

Can I use Finance Core Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill finance-core-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/finance-core-analysis, .gemini/skills/finance-core-analysis, .github/skills/finance-core-analysis and .opencode/skills/finance-core-analysis in your project.

What does Finance Core Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Finance Core Analysis is instructions for the agent only.

Does Finance Core Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Finance Core Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Finance Core Analysis use?

Finance Core Analysis is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Finance Core Analysis use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Finance Core Analysis?

Skills that share tags, products or a category with Finance Core Analysis: Consulting Analysis (bytedance/deer-flow, 84k stars), Startup Validator (ailabs-393/ai-labs-claude-skills, 454 stars), Competitive Analysis Brief (NateBJones-Projects/OB1, 4.7k stars) and Market Analysis (YicunAI/Pnlclaw-community, 197 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Finance Core Analysis?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,586 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.