Agent skill

Med Business

by asgard-ai-platform in asgard-ai-platform/skills

A skill your agent uses when writing financial news — earnings, IPO/M&A, regulatory changes, industry trends — from transcripts, filings, or investor materials.

MITAuto-check passedWriting & Content

Install Med Business

skills CLI
$ npx skills add asgard-ai-platform/skills --skill med-business -a claude-code

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

GitHub CLI
$ gh skill install asgard-ai-platform/skills med-business --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/asgard-ai-platform/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/med-business .claude/skills/med-business && 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
med-business
GitHub stars
242
Token cost
~4.7k tokens
SKILL.md length
2,030 words
Files
9 (incl. references)
Skills in repo
207
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing financial news — earnings, IPO/M&A, regulatory changes, industry trends — from transcripts, filings, or investor materials.

  • Works in 5 steps: Defer general workflow to… → Classify the business-story sub-type → Source vetting & financial credibility → …
  • Writing financial news — earnings
  • SKILL.md covers Overview, When to Use, Methodology and Output Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Med Business is an agent skill from asgard-ai-platform/skills. Use when writing financial news — earnings, IPO/M&A, regulatory changes, industry trends — from transcripts, filings, or investor materials. Activates business-beat workflow: financial-figure provenance, analyst-stake disclosure, securities-law risk, and number stewardship. Triggers on '寫一篇財報季報導', '分析這份財報', '整理 IPO 新聞', 'turn earnings call into a piece', 'write up M&A announcement'. Defers general craft to med-news-reporter. Do NOT use for press releases (pr-press-release), investment advice…

Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `examples/sample_input.md`, `examples/sample_output.md` and `references/ethics_and_law.md`).

It sits in Writing & Content, covering Copywriting and Essays and academic help. The repository describes itself as: 301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Platform. The licence is MIT.

When your agent uses it

  • Writing financial news — earnings
  • Regulatory changes
  • Industry trends — from transcripts
  • Investor materials

Example prompts

  • “寫一篇財報季報導”
  • “分析這份財報”
  • “整理 IPO 新聞”
  • “/med-business”

Workflow steps

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

  1. Defer general workflow to med-news-reporter
  2. Classify the business-story sub-type
  3. Source vetting & financial credibility
  4. Business-specific risk check
  5. Number Provenance Audit (business-specific addition)

What it can do on your machine

Read from SKILL.md and the folder at commit 4e7f4f8. 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 (its code samples are markdown).

    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

Med Business loads about 4.7k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 2,030 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~139
When it runs · the whole SKILL.md, loaded when a task matches
~4.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

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 asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 2,030 words, ~4,687 tokens.

Download SKILL.mdSave it as .claude/skills/med-business/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
med-business
description
Use when writing financial news — earnings, IPO/M&A, regulatory changes, industry trends — from transcripts, filings, or investor materials. Activates business-beat workflow: financial-figure provenance, analyst-stake disclosure, securities-law risk, and number stewardship. Triggers on '寫一篇財報季報導', '分析這份財報', '整理 IPO 新聞', 'turn earnings call into a piece', 'write up M&A announcement'. Defers general craft to med-news-reporter. Do NOT use for press releases (pr-press-release), investment advice (fin-investment-thesis), or marketing (mkt-*).
metadata.category
WP-50 大眾傳播
metadata.tags
news, journalism, business-news, finance-news, earnings, financial-reporting

Business & Finance News Reporting

This skill specializes med-news-reporter for the business beat. Read med-news-reporter first for the general 6-step workflow (type selection, material audit, fact-check, balance, ethics, literacy). This file adds business-beat-specific discipline on top.

Overview

Distilled from financial-journalism curricula at NCCU 新聞系、NTU 新聞研究所、Columbia Journalism Review (Business Desk), Medill (Business Journalism), CUNY Newmark, Reuters Institute. Covers the four main business-news sub-types: earnings / IPO-M&A / regulatory-policy / industry-trend reporting. Core mandate: every financial figure must trace to base period, scope (consolidated vs standalone; domestic vs group), source (CFO statement / 公開資訊觀測站 / analyst estimate), and confidence level (audited vs preliminary vs forecast). The non-obvious failure is when the literal number is correct but the missing context lets readers compare apples-to-oranges.

IRON LAW: Numbers Need Stewardship

Every financial figure in the piece — revenue, EPS, growth rate, margin,
valuation multiple — must explicitly carry FOUR metadata tags: (a) BASE
PERIOD / FISCAL YEAR (e.g., "113年度合併報表"), (b) SCOPE (consolidated
vs individual; domestic vs group; operating vs including-financial gains),
(c) SOURCE (CFO statement / 公開資訊觀測站 / analyst consensus / research
report), and (d) CONFIDENCE (audited / preliminary / forward-looking).
Without all four, the figure is marked [待查證] or omitted. Default LLM
behavior is to drop context for "cleaner prose" or assume implied scope
— this suppresses that default by requiring explicit stewardship. The
reader cannot infer scope from a number alone; ambiguity is not efficiency.

Why this is non-obvious: a headline "Company posts record 5B EPS" is technically true (audited, consolidated, 2025 FY) but sounds miraculous without the context that it's 50% higher than last year due to a one-time merger gain, not operating performance. When readers hear "record EPS", they assume baseline comparable operating earnings — a fundamental mismatch. Stewardship audit catches this by forcing every number to carry its scope flags.

Rationalization Table — these justifications DO NOT override the Iron Law:

Claude might think...Why it's still a violation
"EPS growth was 30%, that's the key number, we don't need to explain consolidated vs individual"Scope ambiguity is the #1 source of misleading financial journalism. The reported-to-media EPS (often consolidated, including one-time items) differs from operating EPS. Both numbers are "true"; omitting the qualifier lets readers confuse them.
"The press release says 營收成長 15%, I'll use that without checking if it's year-over-year or 2-year stack"Base-period ambiguity is a gotcha. Always verify: Is 15% versus prior-year Q2 or full year? Is the comparison to 113年同期 or 累計? Mismatched bases are the #2 error.
"Analyst estimates are just opinions, not facts, so I can soften them as 'expected' instead of marking them as forecasts"Analyst consensus is market material — forecast signals must be clearly marked as such. When you write 'expected to grow', readers hear 'will grow'. Use 'X firm projects' / 'consensus estimate' to signal uncertainty.
"The company's 本益比 of 12 is reasonable, so I can describe it as 'fairly valued' "本益比 is a metric, not a judgment. "Fairly valued" requires comparison to peer multiple, historical average, or growth rate context. The bare number 12× is incomplete. Omit judgment or add comparison.
"I'll round the margin from 24.3% to 'about 24%' for readability"Rounding financial figures obscures precision. Use the reported number or mark as [estimated]. Readers trust journalists with numbers; small rounding is still fabrication.
"Market cap of 2.5T NT$ is big, readers don't need to know the share price and shares outstanding"Implied scope: are we talking market cap at close? Intra-day? Converted at what exchange rate if international? Stating the date and share price (+count) lets readers verify and understand concentration risk.

When to Use

Trigger conditions:

  • User supplies financial material — 財報新聞、法說會逐字稿、公開說明書、投資人簡報、SEC EDGAR filing、IPO 招股書、重大訊息、併購公告 — and asks for a news piece.
  • User asks for "財報季報導" / "IPO 新聞" / "併購分析" / "監理解讀" / "產業趨勢報導" / "earnings story" / "M&A coverage" / "regulatory impact piece".
  • User paraphrases: "把這份財報做成新聞", "法說會怎麼寫", "SEC filing 有什麼亮點", "整理成市場分析", "寫一篇產業動向".

Input signals:

  • Named companies, financial metrics (revenue, EPS, margin, P/E, ROA, EBITDA), fiscal periods, accounting bases.
  • Earnings transcripts, investor presentations, regulatory filings, 公開資訊觀測站 announcements, analyst reports.
  • Direct quotes from CFO, investor-relations staff, analysts, regulators.

When NOT to use:

  • Company press release in the company's own voice → use pr-press-release.
  • Investment thesis or buy/sell recommendation → use fin-investment-thesis.
  • Marketing copy promoting a stock / fund / investment product → use mkt-*.
  • General economic news without company-specific angle → use med-news-reporter (not this beat).

Methodology

Step 0: Defer general workflow to med-news-reporter

Read or have already loaded med-news-reporter for: material audit, fact-checking, source-strength tagging, balance principle, media-ethics check, media-literacy self-check. Do not re-implement those steps here. This file specializes Steps 1, 2, 3, and adds a business-specific Step 4 (Number Provenance Audit).

Step 1: Classify the business-story sub-type
Sub-typeSignalsSub-template focus
Earnings / quarterly resultsFiscal quarter/year, 財報季, revenue/EPS/margin metrics, guidance, CFO commentaryRevenue scope (consolidated?); one-time items segregation; YoY/QoQ base-period clarity; FX impact disclosure
IPO / M&AInitial public offering, merger, acquisition, spin-off, share buyback, capital raiseValuation methodology; deal structure (all-stock / cash / mixed); regulatory approval status; pro-forma scope
Regulatory / policy金管會公告、央行決議、證交法修訂、會計準則變更、監管罰款Regulatory text source; impact on multiple companies or industry-wide; timeline for enforcement
Industry trendMarket shifts, competitor moves, supply-chain changes, sector rotation, technology disruptionCompetitive positioning; addressable-market context; historical parallel (if claimed cyclical)

If material spans sub-types (e.g., an earnings call with M&A announcement), classify by the primary news driver.

Step 2: Source vetting & financial credibility

Every number must carry four metadata flags:

  1. Base period — "113 年度" / "113 年 Q2" / "累計 1-6 月" / "2026 財年" (date ambiguity kills credibility)
  2. Scope — 合併報表(consolidated) vs 個體/個別(individual); 國內(domestic) vs 國際(international); 持續營業(operating) vs including 停業部門; 經常(operating income) vs including 業外(non-operating/financial gains)
  3. Source — CFO statement (audited) / 公開資訊觀測站 preliminary / analyst consensus / research firm estimate / internal forecast
  4. Confidence — 已審定(audited) / 未審(unaudited) / 初步(preliminary) / 預估/展望(forward-looking, include risk disclaimer)

Source tier tagging (extends med-news-reporter's tiering with financial-specific tiers):

TierExamplesTreatment
Official disclosure公開資訊觀測站, SEC EDGAR, company-filed 年報/季報, CFO statementDirect citation; audited flag clearly marked
Investor-facing materialEarnings transcript, investor presentation, guidance, earnings call Q&ALabel as "company guidance" / "CFO stated"; distinguish from audit attestation
Research / analystSell-side reports, consensus estimates, analyst downgradesAlways disclose analyst's firm name, rating (buy/hold/sell), if stock held. State "consensus estimates" if multiple firms
Market dataPrice, trading volume, index levels, analyst-consensus tickersTimestamp (close vs intra-day), exchange-rate basis if international
Second-hand mediaNews relay, competitor claims about the targetRequires cross-check with primary source before using
Step 3: Business-specific risk check

Beyond med-news-reporter's general ethics check, add:

  1. 內線交易 / 市場操縱 (證交法 §155, §157-1):

    • 重大訊息 publication timing: 公開資訊觀測站 timestamp, not press-release timing. If material info disclosed before 公開資訊觀測站 publication, that is non-public — reporting it may expose risk.
    • Embargo rules: some companies embargo financial information until official release time; publishing early can expose the reporter to liability.
  2. 會計舞弊紅旗 — watch for:

    • Revenue recognition shifting (e.g., quarter-end channel-stuffing, sales to related parties, side agreements)
    • Margin compression with no explanation (could signal pricing power loss or cost hiding)
    • Huge accounts-receivable growth without revenue growth (cash-flow risk)
    • One-time items that repeat (no longer "one-time"; operating deterioration masked)
    • Related-party transaction spike (transfer pricing risk)
  3. 估值斷言需避免 — never write:

    • ❌ "The stock is fairly/overvalued at 12× P/E" (requires multiple-comparison context)
    • ❌ "Company is worth 100B" (absent valuation method disclosure)
    • ✅ "Stock trades at 12× P/E vs peer median 18×, suggesting discount or slower growth"
  4. 匯率影響揭露 — when international revenue/EPS is cited:

    • Always state currency basis. If reporting "EPS $2.50 USD", note if converted at spot or fixed rate.
    • When Y-o-Y comparisons span periods with different FX rates, disclose FX headwind/tailwind separately from operating impact.
  5. 重大訊息揭露合規:

    • 公開資訊觀測站 公告 = 官方發布 — use as primary source.
    • 公司新聞稿 ≠ 公開資訊觀測站 公告 — they can have different timestamps and scopes.
    • Report based on 公開資訊觀測站 timestamp + regulatory-filing scope, not company PR spin.
Step 4: Number Provenance Audit (business-specific addition)

For every financial figure in the draft:

  1. Trace to source material — find the exact line in the earnings transcript, filing, or 公開資訊觀測站 announcement.
  2. Tag base period — write the fiscal year/quarter in parentheses: "營收 100 億 (113年度)", not just "營收 100 億".
  3. Declare scope — if the figure is consolidated, write it; if it's guidance, mark "展望". If unusual (e.g., pro-forma), say so.
  4. Check for one-time items — if EPS or margin is boosted by a gain, segregate: "Operating EPS $1.20, including $0.30 one-time merger gain".
  5. Validate comparisons — if claiming "grew 15%", verify: versus what base year/quarter? Same period last year or trailing-twelve-months? Same scope?

Show full SKILL.md (770 more words)Show less

Output Format

Use the med-news-reporter base format, with these business-beat additions to the meta footer:

markdown
[Headline / sub-headline / body paragraphs per med-news-reporter]

---

**稿件類型**: 財報季報導 / IPO新聞 / 併購分析 / 監理解讀 / 產業趨勢
**字數**: approx. XXX
**消息來源層級**: 公開資訊觀測站 N / 財報/法說會 N / 分析師 N / 媒體轉述 N
**財務數字稽核**:
- 基期 (fiscal year/quarter) 完整性: ✅ / ⚠️ (列出未標的數字)
- 範圍 (consolidated/individual, operating/including one-time) 清晰: ✅ / ⚠️ (列出未指明的)
- 來源與可信度 (audited/preliminary/forecast) 標記: ✅ / ⚠️ (列出未確認的)
- 匯率基準 (if applicable): ✅ / N/A / ⚠️
- 一次性項目隔離: ✅ / N/A / ⚠️ (如有列出影響幅度)
**分析師利益揭露**: ✅ (列出所有分析師所屬機構 + 評級) / N/A / ⚠️
**會計舞弊紅旗檢查**: ✅ / ⚠️ (列出可疑項目)
**估值斷言**: ✅ (無不當斷言) / ⚠️ (列出待補充比較基準的)
**證交法合規檢查**:
- 重大訊息揭露時點 (公開資訊觀測站 vs 新聞稿時差): ✅ / ⚠️
- 內線交易風險: ✅ / ⚠️ (列出可疑之處)
**待查證事項**: ...
**倫理 / 識讀檢核摘要**: 〔交給 med-news-reporter 的 Step 4-5 footer〕

Examples

Good Example

Scenario: User supplies (a) 103 Tech Corp 113年度年報 & 法說會逐字稿 (audited consolidated statement); (b) 公開資訊觀測站 重大訊息 (published 2026-04-15 12:30); (c) two sell-side analyst reports (one "buy" rated, one "neutral", both from top-3 brokers, with latest price targets); (d) peer comparison from Bloomberg (P/E multiples of 5 competitors). Request: ~1,000-word earnings story analyzing the year, growth drivers, and valuation context.

Analysis:

  1. Step 1: classified as earnings reporting (annual results with guidance implications) → focus on revenue scope, margin one-time segregation, YoY base-period clarity.
  2. Step 2: Source vetting — 年報 is audited (Tier 1, 已審定); 法說會逐字稿 is investor-facing (Tier 1, 來自公司); analyst reports are Tier 2 (include firm name + rating); Bloomberg is market data (Tier 1, 時間戳記重要).
  3. Step 3: Risk check — examine revenue for related-party sales spike; check if guidance has side agreements or channel-stuffing patterns; look for margin compression signals.
  4. Step 4 (Number Audit):
    • "營收 500 億" → write "113年度合併營收 500 億元,同期 112年度 450 億,年成長 11.1%"
    • "EPS 2.50 元" → write "基本每股盈餘 2.50 元 (113年度,已審定);其中包括業外投資收益 0.30 元"
    • "預估今年成長 8%" → write "公司展望 114 年營收成長 8% (保守估計,面臨匯率與原料成本變數)"
    • Peer comparison: "本益比 15× vs 同業平均 18× … 反映市場對成長率的差異評估"
  5. Output footer标示数字完整性 ✅, 分析师利益揭露 (两名分析师名字+评级+机构), 无会计舞弊信号 ✅, 估值对标完备 ✅.

Result: 读者可独立验证每个数字的基期、范围、来源;可区分运营增长 vs 一次性收益;可理解分析师评级背后的利益关系。

Bad Example

Scenario: Same input material. Writer produces a "rosy" story by (a) stating "103 Tech posts record 500B revenue" without mentioning it's consolidated and includes a one-time acquisition; (b) claiming "EPS 2.50 is strong growth" without checking it includes a 0.30 one-time item (actual operating EPS only 2.20); (c) citing one analyst's "buy" rating as justification that stock is "undervalued" without disclosing the analyst owns 5% of the firm and has conflicts; (d) stating "P/E of 15 is attractive" without peer comparison; (e) omitting the 4-day gap between 公開資訊觀測站 publication and company press release.

What went wrong:

  • (a) & (b): Scope ambiguity and one-time masking. Both the 500B and 2.50 EPS are literally true, but reader confuses operating performance with windfall gains. Iron Law violation: missing stewardship metadata.
  • (c): Analyst conflict undisclosed. If the analyst's firm holds stock, that holding shapes the rating; reader needs to know. Same if the analyst is compensated by deal fees.
  • (d): Valuation without context. "Attractive" requires comparison. 15× versus 18× peer average tells one story; versus 12× historical average tells another.
  • (e): Timing gap ignored. If company disclosed in 公開資訊觀測站 on day X and press release on day X+4, and the reporter relied on the press release without noting the official disclosure timestamp, readers misunderstand what counts as "material" information.

Net effect: Story reads fluent and "positive", but every number is decontextualized. Readers cannot independently assess the company's actual operating performance vs. one-time boosts, or evaluate analyst credibility. This is the failure mode the Stewardship Audit exists to catch.


Gotchas

  • 「同期」「同比」「年增」的基期容易混 — 「113年度營收同比成長 10%」vs 「113年第2季同比成長」— 前者是 vs 112年度全年,後者是 vs 112年 Q2。永遠寫清楚對比期間,不要假設讀者能推斷。混淆基期是財經新聞最常見的欺騙(刻意或無意)。
  • 「合併」「個體」帳目數字不可混用 — 某些公司個體淨利 50 億,合併報表淨利 80 億(因子公司貢獻)。若文中既引個體又引合併而未說明,讀者會混淆。始終聲明你用的是哪一份,尤其跨段落引數字時。
  • 分析師評級「都有利益關係」,必須揭露 — 「某投行上調目標價」時,務必寫出 (a) 該投行是否為公司的財務顧問/主承銷商 / 融資提供者(證券法上須揭露), (b) 該投行是否持股(利益衝突). 「研究獨立」不代表無衝突;讀者有權知道投行的經濟利益。
  • 「預期」「預估」「展望」是法律概念 — 若寫「公司預期今年營收 100 億」,該預期必須來自官方指引(年報、法說會、公開聲明),不能是你的推測或分析師猜測。「展望」與「宣布」的法律後果不同(展望有 safe harbor, 宣布無)。
  • 匯率換算的基準易生誤解 — 「美國子公司營收 $100M USD」若未說明是月底匯率、月均、還是歷史成本,國際讀者無法驗算。跨幣別報導時永遠附匯率日期與匯率數字,让讀者能追蹤 FX impact。
  • 「本益比」「股價淨值比」無脈絡就無意義 — 12× P/E 在成長股集中的產業是便宜,在成熟產業是昂貴。寫倍數前,必須給對標(「同業平均 18×」或「公司 5 年平均 15×」),否則讀者無法判斷。避免使用「合理」「偏高」這類無基礎的斷言。
  • 一次性項目重複出現代表隱瞞常態營運衰退 — 若財報連 3 季都有「一次性」收益/損失,這不再是「一次性」,而是常態。當你看到重複的「一次性」旗標,這是會計舞弊紅旗,應列入稿件待查項目。

References

FilePurposeWhen to read
references/sources_and_beats.md財經線消息來源、機構、官方資料庫 (公開資訊觀測站、TWSE、金管會、央行、主計總處、SEC EDGAR、Bloomberg)Step 2 source vetting
references/glossary.md財務、會計、市場專業術語對照與定義 (GAAP/IFRS, EPS/ROE/EBITDA, 重大訊息, M&A, 量化寬鬆) 與常見誤用When unfamiliar terminology appears
references/ethics_and_law.md證交法 §155 操縱市場、§157-1 內線交易、利益衝突揭露、財報新聞時間敏感性、Analyst disclosureStep 3 risk check
references/financial_statements_reading.md三大表判讀:資產負債表/損益表/現金流量表警訊指標、會計舞弊紅旗、本益比與股價淨值比脈絡化Step 4 Number Audit
references/market_data_reading.md指數計算口徑、報酬率年化、技術指標限制、單日波動 vs 趨勢、匯率報導基準When citing market data / multi-period comparisons

Related skills:

  • med-news-reporter — general news workflow (this skill specializes it)
  • data-financial-analysis — deeper analysis of financial metrics & ratio modeling
  • stat-hypothesis-testing — for statistical rigor in trend claims
  • hum-source-criticism — source vetting frameworks for analyst credibility

Limitations

  • Does not detect accounting fraud algorithmically. This skill flags red-flag patterns (revenue timing, margin compression, related-party spikes); it does not perform forensic accounting or access internal controls audit. Fraud detection requires specialist expertise.
  • Does not perform live fact verification. This skill flags claims that need verification (e.g., "CEO says $2B revenue, check against filing"); it does not access SEC EDGAR, 公開資訊觀測站, or company databases in real time. Editor must verify or supply.
  • Valuation methods are not within scope. DCF, comparable-company, precedent-transaction analyses are covered in data-financial-analysis and fin-investment-thesis. This skill assumes valuation inputs are supplied and checks only the metadata (source, assumptions disclosed).
  • Jurisdictional scope: Legal references (證交法, 上市公司規範, GAAP vs IFRS) reflect Taiwan. For US (SEC rules, Reg FD, Sarbanes-Oxley), EU (IFRS, MAR), HK, PRC, or other jurisdictions, principles still apply but specific statutes and thresholds differ.
  • Not an earnings-call transcription service. If the user supplies an audio/video earnings call without a transcript, this skill does not transcribe it; user must provide transcript or use external transcription tool first.

© asgard-ai-platform, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in med-business of asgard-ai-platform/skills.

  • SKILL.md
  • .gitkeep
  • examples/sample_input.md
  • examples/sample_output.md
  • references/ethics_and_law.md
  • references/financial_statements_reading.md
  • references/glossary.md
  • references/market_data_reading.md
  • references/sources_and_beats.md

Open the folder on GitHubat commit 4e7f4f8

Compare with similar skills

Med Business 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.

Med Business compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Med Business this skillasgard-ai-platform/skills242—~4.7kAutomated safety check: PassMIT
Asd Ste100danyuchn/asd-ste100-skill4.3k—~4.1kAutomated safety check: PassMIT
AI Copywritermikiarlo3/ai-copywriter1.2k—~12kAutomated safety check: PassMIT
Brand Voice Guideluongnv89/claude-howto42k—~609Automated safety check: PassMIT
Ralph Copywritermuratcankoylan/ralph-wiggum-marketer778—~2.4kAutomated safety check: PassNone
Humanities Writing Companiontizzy916/humanities-writing-companion436—~3.4kAutomated safety check: PassCC-BY-NC-4.0

Similar skills

  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.3k GitHub stars~4.1k tokensUpdated 7 days ago
    Writing & ContentAuto-check passed
  • AI Copywriter

    mikiarlo3/ai-copywriter

    Write copy that converts and doesn't sound like a robot. An agent skill from mikiarlo3/ai-copywriter.

    1.2k GitHub stars~12k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Brand Voice Guide

    luongnv89/claude-howto

    Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when…

    42k GitHub stars~609 tokensUpdated today
    Writing & ContentAuto-check passed
  • Ralph Copywriter

    muratcankoylan/ralph-wiggum-marketer

    A skill your agent uses when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand…

    778 GitHub stars~2.4k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed
  • Humanities Writing Companion

    tizzy916/humanities-writing-companion

    Help with humanities scholarly writing: sharpen research questions, map supplied readings, plan and draft arguments, review chapters, preserve authorial voice, and respond to reviewers.

    436 GitHub stars~3.4k tokensUpdated 19 days ago
    Writing & ContentAuto-check passed
  • Xiaoma Durex Copywriter

    crawfordxx/xiaoma-durex-copywriter

    用杜蕾斯黄金期(2011-2017 环时互动)那套「双层语义 + 留白」的方法产出文案与海报。先识别用户意图并给 3-5 个方案供选,再出短文案(长文案可选)+ 五种比例配图。适用于借势热点、节日节气、产品卖点、课程/知识付费推广、自媒体标题与封面、品牌人格化运营。当用户说「写个文案」「借势热点」「节日海报」「想句…

    584 GitHub stars~1.8k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed

More from asgard-ai-platform/skills

All 207 skills in this repo
  • Algo Ecom Bm25

    asgard-ai-platform/skills

    Implement BM25 ranking function for e-commerce product search relevance scoring.

    242 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Mfg Cpk

    asgard-ai-platform/skills

    Calculate Cpk process capability index to assess whether a process meets specification requirements.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Price Elasticity

    asgard-ai-platform/skills

    Calculate price elasticity of demand to quantify how price changes affect sales volume.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Rank Bayesian

    asgard-ai-platform/skills

    Apply Bayesian averaging to rank items by combining observed ratings with prior expectations.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Rank Elo

    asgard-ai-platform/skills

    Implement Elo rating system to rank items or players from pairwise comparison outcomes.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Rank Wilson

    asgard-ai-platform/skills

    Calculate Wilson Score confidence intervals for ranking items by positive proportion with sample size correction.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Med Business

What does Med Business do?

A skill your agent uses when writing financial news — earnings, IPO/M&A, regulatory changes, industry trends — from transcripts, filings, or investor materials. Med Business is an agent skill from asgard-ai-platform/skills. Use when writing financial news — earnings, IPO/M&A, regulatory changes, industry trends — from transcripts, filings, or investor materials.

When should I use Med Business?

Med Business fits situations like: writing financial news — earnings; regulatory changes; industry trends — from transcripts; investor materials.

How do I install Med Business in Claude Code?

Run `npx skills add asgard-ai-platform/skills --skill med-business -a claude-code`. Or copy the skill folder (med-business in asgard-ai-platform/skills) into .claude/skills/med-business in your project. Claude Code loads it when a task matches its description.

How do I install Med Business in Codex?

Run `npx skills add asgard-ai-platform/skills --skill med-business -a codex`. Or copy the skill folder (med-business in asgard-ai-platform/skills) into .agents/skills/med-business in your project. Codex loads it when a task matches its description.

Can I use Med Business 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 asgard-ai-platform/skills --skill med-business -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/med-business, .gemini/skills/med-business, .github/skills/med-business and .opencode/skills/med-business in your project.

What does Med Business need to run?

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

Does Med Business 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 Med Business 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 Med Business use?

Med Business is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Med Business use?

About 4.7k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.

What are the alternatives to Med Business?

Skills that share tags, products or a category with Med Business: Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars), AI Copywriter (mikiarlo3/ai-copywriter, 1.2k stars), Brand Voice Guide (luongnv89/claude-howto, 42k stars) and Ralph Copywriter (muratcankoylan/ralph-wiggum-marketer, 778 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Med Business?

asgard-ai-platform (a GitHub organization) maintains it in asgard-ai-platform/skills, which has 242 GitHub stars. The repository holds 207 skills in this directory. The repository was last updated on June 6, 2026.

Source: asgard-ai-platform/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.