Agent skill

Finance Explosive Article

by digoal in digoal/blog

Generate stage-3 high-impact 德哥风格 公众号 financial articles from daily-finance and finance-core-analysis outputs plus current web verification.

GPL-2.0Auto-check passed

Install Finance Explosive Article

skills CLI
$ npx skills add digoal/blog --skill finance-explosive-article -a claude-code

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

GitHub CLI
$ gh skill install digoal/blog finance-explosive-article --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-explosive-article .claude/skills/finance-explosive-article && 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-explosive-article
GitHub stars
8.6k
Token cost
~1.6k tokens
SKILL.md length
667 words
Files
1
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Generate stage-3 high-impact 德哥风格 公众号 financial articles from daily-finance and finance-core-analysis outputs plus current web verification.

  • Works in 4 steps: Read Inputs → Verify Key Data → Apply 德哥风格 → …
  • The user wants a 公众号爆款文章
  • SKILL.md covers Overview, Step 1: Read Inputs, Step 2: Verify Key Data and Step 3: Apply 德哥风格, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Finance Explosive Article is an agent skill from digoal/blog. Generate stage-3 high-impact 德哥风格 公众号 financial articles from daily-finance and finance-core-analysis outputs plus current web verification. Use this skill whenever the user wants a 公众号爆款文章, final financial commentary, "帮我写成文章"、"整理成爆款"、"德哥风格"、"公众号推文"、"写一篇深度文章"、"把分析写成文章发布", or the third and final step of the pipeline. Even if the user only says "帮我把今天的分析整理一下发出去", use this skill. This is stage 3 of: daily-finance → finance-core-analysis → finance-explosive-article.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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 a 公众号爆款文章
  • Final financial commentary
  • 帮我写成文章、整理成爆款、德哥风格、公众号推文、写一篇深度文章、把分析写成文章发布
  • The third and final step of the pipeline

Example prompts

  • “帮我写成文章”
  • “写一篇深度文章”
  • “把分析写成文章发布”
  • “/finance-explosive-article”

Workflow steps

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

  1. Read Inputs
  2. Verify Key Data
  3. Apply 德哥风格
  4. Validate Before Writing

What it can do on your machine

Read from SKILL.md and the folder at commit 69fb793. 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 Explosive Article loads about 1.6k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 667 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~123
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 69fb793, republished under its GPL-2.0 licence (© digoal). 667 words, ~1,558 tokens.

Download SKILL.mdSave it as .claude/skills/finance-explosive-article/SKILL.md (or your agent's skills folder).
name
finance-explosive-article
description
Generate stage-3 high-impact 德哥风格 公众号 financial articles from daily-finance and finance-core-analysis outputs plus current web verification. Use this skill whenever the user wants a 公众号爆款文章, final financial commentary, "帮我写成文章"、"整理成爆款"、"德哥风格"、"公众号推文"、"写一篇深度文章"、"把分析写成文章发布", or the third and final step of the pipeline. Even if the user only says "帮我把今天的分析整理一下发出去", use this skill. This is stage 3 of: daily-finance → finance-core-analysis → finance-explosive-article.

德哥风格金融爆款文章

Overview

Generate a high-impact, publishable financial article in 德哥风格 for 公众号.

Pipeline position:

daily-finance → finance-core-analysis → finance-explosive-article
  • Stage 1 supplies facts and verified sources
  • Stage 2 supplies mechanisms, scenarios, and key variables
  • Stage 3 (this skill) transforms them into a sharp, viral-ready article

The goal is NOT to summarize news. The goal is to:

  • Explain what is really happening beneath the surface
  • Identify the underlying drivers
  • Deliver sharp, data-backed insight
  • Make readers say: "原来是这样"

Step 1: Read Inputs

Preferred: Read both upstream files:

  • markdown/daily-finance-YYYY-MM-DD.md
  • markdown/finance-core-analysis-YYYY-MM-DD.md

Fallback order:

SituationAction
Only daily-finance existsBuild mechanism yourself; mark uncertainty explicitly
Only finance-core-analysis existsUse its facts/sources; avoid unsupported news details
Date ambiguousAsk the user which date to use
User pasted content in chatUse that content directly

Step 2: Verify Key Data

Always access current external data before writing.

Use web search / browser / MCP tools to:

  • Confirm upstream facts are still accurate
  • Re-check any number used in the title, opening, or core judgment
  • Update stale data when a reliable newer source exists

Do not add fresh claims only for dramatic effect. Every number must be source-traceable.

Source hierarchy:

  • Primary: Reuters, Bloomberg, FT, WSJ; 财新, 第一财经
  • Secondary (require backtracking): FT中文, WSJ中文, 新浪财经
  • Forbidden: 自媒体, 公众号, 未经核实社交媒体

Step 3: Apply 德哥风格

Three mandatory elements:

3a. First-Principles Mechanism

Never explain surface events. Explain the bottom-layer driver.

Every conclusion must trace to at least one:

  • 流动性 Liquidity
  • 利率 Interest rates
  • 风险偏好 Risk appetite
  • 资本流动 Capital flows
  • 政策方向 Policy direction
  • 资产负债表压力 Balance-sheet pressure
  • 激励约束 Incentive constraints
3b. Counterintuitive Reversal(必须有)

The article must contain a clear "不是A,是B" cognitive reversal that exposes a real mechanism mismatch — not wordplay.

Strong examples:

  • "这不是牛市回来了,而是流动性重新定价风险资产。"
  • "市场不是在买增长,而是在买利率下行的想象空间。"
  • "政策不是直接托底价格,而是在修复资产负债表预期。"

Banned phrases (replace with mechanisms):

  • ❌ "因为利好所以涨"
  • ❌ "市场情绪推动"
  • ❌ "资金炒作"
  • ❌ "政策刺激"
3c. Reusable Systemic Model(必须有)

Every article must leave the reader with one model they can reuse.

Standard causal chain:

触发事件 → 传导机制 → 资金行为 → 资产定价 → 风险约束 → 后续观察点

Name the model in plain Chinese when useful:

  • "流动性-风险偏好模型"
  • "美元利率-全球资金流模型"
  • "政策预期-资产负债表模型"

Step 4: Validate Before Writing

CheckRequirement
DataDates, units, directions correct? Actual vs expected labeled? Intraday vs close distinguished?
SourcesEvery key number traceable to upstream files or reliable external source?
Reversal logic"不是A,是B" supported by mechanism, not rhetoric?
Causal chainTrigger → mechanism → capital behavior → asset pricing → risk constraint → next signal?
PublicationTitle, opening, section rhythm, conclusion, sources, disclaimer all present?
Risk boundaryNo explicit buy/sell recommendation?

If a powerful sentence overstates the evidence, weaken the sentence — never weaken the facts.


Output Format(MANDATORY STRUCTURE)

Show full SKILL.md (271 more words)Show less
1. 爆点标题
  • Must create tension or contradiction
  • Must trigger curiosity
  • Prefer "不是A,是B" or "真正的X,不是Y"
  • ✅ "市场根本不是在涨,而是在赌一件事"
  • ✅ "所有人都在看政策,真正的变量却在资金价格"
  • ❌ Generic headlines without tension
2. 破题(Opening)
  • Start with a fact or anomaly
  • Immediately raise the core question
  • State the mistaken mainstream interpretation
  • Foreshadow the counterintuitive answer
3. 一句话反转(Core Judgment)

One direct sentence defining the article's central reversal:

这件事表面上是A,本质上是B。

Then explain why A is incomplete and B is the real pricing variable.

4. 核心逻辑(Core Analysis)

2–4 sections, each containing:

  • Mechanism explanation
  • Data or observable signals
  • Causal reasoning
  • Link back to the systemic model

Typical angles: Liquidity / Policy / Global capital flows / Sector rotation

5. 可复用模型(System Model)

Summarize the reusable model explicitly:

第一层:触发变量 — ...
第二层:传导机制 — ...
第三层:资产定价 — ...
第四层:验证信号 — ...
6. 关键判断(Key Insight)

Clearly state:

  • What the market is actually pricing
  • What most people misunderstand
  • Which variable matters most next
7. 推演(Scenario Analysis)
情景触发条件资产含义
基准情景......
备选情景......
证伪信号......
8. 方向性参考(Non-Advisory Implication)

Directional thinking only. No ticker calls, no buy/sell.

9. 收束(Closing)
  • Strong summary sentence
  • End with mechanism, not slogan
10. 数据来源

Short source list, one per line.

11. 免责声明

本文仅供参考,不构成投资建议。


File Output

Save to:

markdown/finance-explosive-article-YYYY-MM-DD.md
  • Use the same report date as upstream files
  • Create markdown/ directory if missing
  • UTF-8 encoding
  • Final article only — no process notes
  • Fallback: If write fails, output full markdown in chat

Writing Style

  • Short paragraphs, clear rhythm
  • Sharp and direct — no fluff, no academic tone
  • Use contrast: "不是A,而是B"
  • Declarative sentences preferred
  • Use "说白了", "真正的问题是", "底层逻辑是" sparingly but decisively
  • Do not stack metaphors
  • Start with tension → land on mechanism → close with model

Goal

Produce an article that:

  1. Makes the reader say "原来是这样"
  2. Leaves behind one reusable model
  3. Can spread on social platforms
  4. Builds authority and trust through factual precision

© 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-explosive-article of digoal/blog.

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Finance Explosive Article 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 Explosive Article compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Finance Explosive Article this skilldigoal/blog8.6k—~1.6kAutomated safety check: PassGPL-2.0
Articlethedaviddias/Front-End-Checklist74k—~421Automated safety check: PassMIT
Financial Analystalirezarezvani/claude-skills28k1 repos~1.8kAutomated safety check: PassMIT
Startup Financial Modelingwshobson/agents40k—~1.9kAutomated safety check: PassMIT
Article Magazinenexu-io/open-design100k—~495Automated safety check: PassApache-2.0
Article Linksthedaviddias/Front-End-Checklist74k—~425Automated safety check: PassMIT

Similar skills

  • Article

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Implement valid Article structured data.

    74k GitHub stars~421 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Financial Analyst

    alirezarezvani/claude-skills

    Runs financial ratio analysis, DCF valuation, budget variance reports and rolling forecasts from statement data using four bundled Python scripts.

    28k GitHub starsUsed in 1 repo~1.8k tokens
    Business, Finance & HRAuto-check passed
  • Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.

    40k GitHub stars~1.9k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed
  • Article Magazine

    nexu-io/open-design

    Huashu / huashu-md-html-inspired magazine article layout for turning Markdown or notes into a polished long-form HTML essay.

    100k GitHub stars~495 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Article Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Optimize article link density.

    74k GitHub stars~425 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Article Writing

    affaan-m/ECC

    根据提供的示例或品牌指导,以独特的语气撰写文章、指南、博客帖子、教程、新闻简报等长篇内容。当用户需要超过一段的精致书面内容时使用,尤其是当语气一致性、结构和可信度至关重要时。

    275k GitHub starsUsed in 3 repos~295 tokens
    Writing & ContentAuto-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 10 days ago
    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 10 days ago
    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 10 days ago
    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 10 days ago
    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 10 days ago
    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 10 days ago
    Auto-check passed

Questions about Finance Explosive Article

What does Finance Explosive Article do?

Generate stage-3 high-impact 德哥风格 公众号 financial articles from daily-finance and finance-core-analysis outputs plus current web verification. Finance Explosive Article is an agent skill from digoal/blog. Generate stage-3 high-impact 德哥风格 公众号 financial articles from daily-finance and finance-core-analysis outputs plus current web verification.

When should I use Finance Explosive Article?

Finance Explosive Article fits situations like: the user wants a 公众号爆款文章; final financial commentary; 帮我写成文章、整理成爆款、德哥风格、公众号推文、写一篇深度文章、把分析写成文章发布; the third and final step of the pipeline.

How do I install Finance Explosive Article in Claude Code?

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

How do I install Finance Explosive Article in Codex?

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

Can I use Finance Explosive Article 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-explosive-article -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-explosive-article, .gemini/skills/finance-explosive-article, .github/skills/finance-explosive-article and .opencode/skills/finance-explosive-article in your project.

What does Finance Explosive Article need to run?

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

Does Finance Explosive Article 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 Explosive Article 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 Explosive Article use?

Finance Explosive Article 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 Explosive Article use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Explosive Article?

Skills that share tags, products or a category with Finance Explosive Article: Article (thedaviddias/Front-End-Checklist, 74k stars), Financial Analyst (alirezarezvani/claude-skills, 28k stars), Startup Financial Modeling (wshobson/agents, 40k stars) and Article Magazine (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Finance Explosive Article?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,587 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 28, 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.