company-wiki

name	company-wiki
type	workflow
description	Build a comprehensive, multi-page company research wiki as a deployed web application. Use for: researching any publicly listed company from any region (US, Europe, Japan, Taiwan, India, or other) and producing a structured wiki covering company overview/history, individual product pages (sourced from earnings calls and investor presentations), 5-year financials, analyst reports, stock price and technical analysis, financial modelling with growth scenarios and forward P/E and P/S multiples, competitor comparison, and a sourced citations page. The wiki is built with React + Tailwind using the webdev tools and deployed on Manus hosting. Triggers: 'build a company wiki for X', 'research wiki on Y', 'make a company research site for Z', 'deep research wiki for <ticker>'.
requires	["analyst-kit-core","wiki-builder","company-universe-manager"]
env	["FMP_API_KEY"]

Preamble (run first)

PLAN MODE EXCEPTION — ALWAYS RUN: this block only reads state and writes to ~/.analyst-kit/.

_AK="$(cat ~/.analyst-kit/core-path 2>/dev/null)"
if [ ! -x "$_AK/bin/analyst-kit-preamble" ]; then
  for d in ~/.claude/skills/analyst-kit-core .claude/skills/analyst-kit-core ~/.codex/skills/analyst-kit-core .codex/skills/analyst-kit-core; do
    [ -x "$d/bin/analyst-kit-preamble" ] && _AK="$d" && break
  done
  [ -x "$_AK/bin/analyst-kit-preamble" ] || _AK="$(find ~/.claude/plugins -maxdepth 6 -type d -name analyst-kit-core 2>/dev/null | head -1)"
  [ -n "$_AK" ] && { mkdir -p ~/.analyst-kit; printf '%s' "$_AK" > ~/.analyst-kit/core-path; } || true
fi
[ -x "$_AK/bin/analyst-kit-preamble" ] && "$_AK/bin/analyst-kit-preamble" --skill company-wiki --env FMP_API_KEY 2>/dev/null || echo "AK_CORE: not found (continue without runtime)"

Read the echoed state and act. Skip ALL bullets below if DEDUP: yes or AK_CORE: not found:

• DISABLED: yes → this skill is turned off because a required API key isn't configured. Do not run it. Tell the user it's off, name the missing key (see MISSING_KEYS), and offer to enable it — either they give you the key now (store it with "$_AK/bin/analyst-kit-setup" set-key <KEY> <value>, which re-enables the skill) or they say "set up analyst-kit" for full setup. Then stop; do not attempt the skill's work.
• First run — ONBOARDED: no → orient the user once, then run "$_AK/bin/analyst-kit-setup" finish (this covers the telemetry notice, so skip the TEL_PROMPTED bullet this turn):
  1. Data home — tell the user Analyst Kit keeps config, API keys, local usage analytics, and a learnings log together in one folder (default ~/.analyst-kit); offer to move it with "$_AK/bin/analyst-kit-setup" home <dir>.
  2. Telemetry (a notice, not a question) — usage telemetry is on by default: only skill name, duration, outcome, and version, tagged with a per-machine device id derived from the hardware/OS, never repo names, paths, tickers, or content; opt out anytime by asking to turn Analyst Kit telemetry off.
  3. Identity (name + email — required) — ask for the user's name and email, stating plainly the email is mandatory to use most features (SEC EDGAR's fair-access policy requires a real, reachable contact on every request). If they decline because they don't want the email-dependent skills, discover a fallback yourself (git config user.email, gh api user, …) and pass it with --fallback in step 5.
  4. Offer full setup — ask if they'd like to configure API keys for all skills now. If yes, Read "$_AK/references/intro.md" and follow it. If no, continue — you'll ask for a key only when a skill needs one.
  5. Run "$_AK/bin/analyst-kit-setup" finish --name "<name>" --email "<email>" (add --fallback for a discovered email; run plain finish only if no email could be found at all). If it echoes INVALID_EMAIL, re-ask and run it again.
• User asks to set up Analyst Kit at any time (e.g. "set up analyst-kit", "help me set up Analyst Kit", "configure all skills") → Read "$_AK/references/intro.md" and follow it end to end: data home, telemetry, every skill's keys, and enabling/disabling each.
• TEL_PROMPTED: no (returning user) → give the telemetry notice once, then run "$_AK/bin/analyst-kit-setup" ack-telemetry.
• If the user asks to turn telemetry off (now or anytime): before flipping it, make a sincere case once — telemetry is what tells the maintainers which skills break, which run slow, and where users get stuck, so keeping it on directly improves their experience; it never includes their data. Offer "$_AK/bin/analyst-kit-config" set telemetry anonymous (drops the device id) as a middle ground. If they still want out, run "$_AK/bin/analyst-kit-config" set telemetry off immediately and without further argument.
• Before running any script that needs an API key: source both the data home's .env and the current directory's .env into the shell so scripts can read stored keys: set -a; [ -f "$AK_HOME/.env" ] && . "$AK_HOME/.env"; [ -f "./.env" ] && . "./.env"; set +a (where $AK_HOME is the path printed on the AK_HOME: line above). Full lookup order — always check these before concluding a key is missing or asking the user:
  1. current shell environment
  2. $AK_HOME/.env (keys stored by analyst-kit-setup)
  3. .env in the current working directory Never ask the user for a key that is already present in any of these locations.
• MISSING_KEYS not none → for each listed key with KEY_PROMPTED_<KEY>: no: explain where to get it, ask for the value, and run "$_AK/bin/analyst-kit-setup" set-key <KEY> <value>. If declined, run "$_AK/bin/analyst-kit-setup" skip-key <KEY> (this disables the skills that need it) and continue — never block the skill.
• UPGRADE: UPGRADE_AVAILABLE <old> <new> → say "Analyst Kit skills is available (you have ) — update?". If yes: Read "$_AK/references/upgrade.md" and follow it. If declined: run "$_AK/bin/analyst-kit-update-check" --snooze <new>.
• LEARNINGS entries shown → these are past mistakes/preferences for this user; respect them and do not repeat logged pitfalls.

Then proceed with the skill. At the very end, run the Completion block at the bottom of this file.

Company Wiki Skill

Overview

Build a production-ready, multi-page company research wiki for any publicly listed company. The workflow has seven phases:

1. Identify the company, its exchange, and map data sources by region
2. Research product details & launches
3. Research Fiscal periods, earnings calls, investor presentations, and
4. Gather 5-year financial data and periodic revenue
5. Research analyst reports and ratings
6. Gather stock price data for technical analysis
7. Build the wiki web application
8. Deliver and iterate

For detailed regional data retrieval methods, see references/regional-data-sources.md. For competitor research frameworks, see references/competitor-research.md. For wiki page component patterns, see references/page-templates.md. For product page data schema, see references/product-page-structure.md.

---

Phase 0 - Preparation

Before you start gathering information, build the Citation.md file. Every information you gather and use for the wiki MUST have a source number in the Citation.md file. This will be later used to build the source page in the wiki.

Phase 1 — Company Identification & Source Mapping

Always complete this sequence before any research:

1. Find the IR website: Search "[Company Name] investor relations" or navigate to the company's main website "Investors" section. The IR page is the authoritative source for presentations, filings, and earnings materials.
2. Identify the primary ticker and exchange: Confirm the most liquid listing and local ticker. Note any ADRs or secondary listings.
3. Determine the company's region: US · Europe · Japan · Taiwan · India · Other. This determines which sources to use in Phases 2–4 (see references/regional-data-sources.md).
4. Map the ticker to FMP API format: Append the correct suffix (e.g., .T for Tokyo, .TW for TWSE, .NS for NSE India). See FMP Ticker Formats table in references/regional-data-sources.md.
5. Confirm FMP coverage: Use the profile-symbol endpoint to retrieve the ISIN as a universal identifier.
6. Idenfity the fiscal periods: Identify the fiscal periods of the company.
7. Citations: Log all the citations in the Citations.md and add the number with each data information.

Save to: /home/ubuntu/{ticker}_research.md

Key fields to capture: founding year, headquarters, listing exchange and ticker, ownership (parent company if subsidiary), number of employees, global ranking in industry, major subsidiaries and manufacturing locations.

---

Phase 2 — Earnings Calls & Product Research

Step 1 — Locate the earnings source for the company's region:

Region	Primary Source	Notes
US	FMP API latest-transcripts or transcript endpoint; Seeking Alpha	Full text transcripts available
Europe	Company IR page (webcasts/PDFs); exchange filings (LSE RNS, AMF, Nasdaq Nordic)	Text transcripts often unavailable for small-caps; use video webcast
Japan	Company IR page → "Q&A Summary" PDFs	Do NOT search for "earnings call transcripts" — the standard format is Q&A Summary PDFs
Taiwan	AlphaSpread (alphaSpread.com) for full English text; Company IR page	AlphaSpread is the best source for TWSE companies; far better than webcasts
India	Company IR page (SEBI LODR requires full transcript PDFs); Trendlyne; BSE/NSE filings	Full PDFs are legally mandated

Step 2 — Download the most recent full-year earnings presentation/transcript and 2–3 prior years.

Step 3 — For each major product line, capture:

• Product description and technical specifications
• Revenue contribution (% of total, absolute if disclosed)
• Key customers or end markets
• Growth commentary from management
• Capacity expansion or capex announcements
• Competitive positioning statements

Save to: /home/ubuntu/{ticker}_earnings_research.md

See references/product-page-structure.md for the standard product page data schema.

---

Phase 3 — Financial Data

Primary source (all regions):

• Annual income statement: https://stockanalysis.com/stocks/{ticker}/financials/ (US) or https://stockanalysis.com/quote/{exchange_prefix}/{ticker}/financials/ (non-US)
• Quarterly data: append ?p=quarterly
• Balance sheet: append /balance-sheet/

stockanalysis.com exchange prefixes: tpe (TWSE Taiwan), tpex (Taipei OTC), tse (Tokyo), nse / bse (India), lse (London), xetra (Germany), euronext (Paris/Amsterdam)

Periodic revenue by region:

Region	Periodic Revenue Source
Taiwan	https://tw.stock.yahoo.com/quote/{ticker}.TW/revenue (monthly)
US / Europe	Quarterly from stockanalysis.com or company earnings releases
Japan	Quarterly from company IR page or JPX TDnet
India	Quarterly from BSE/NSE filings or Trendlyne

Key metrics to collect:

• Annual revenue (5 years), YoY growth %
• Gross profit and gross margin %
• Operating income and operating margin %
• Net income and net margin %
• EPS (basic and diluted)
• Periodic revenue (monthly for Taiwan, quarterly for others — 8–12 periods for trend analysis)

Save to: /home/ubuntu/{ticker}_financials_complete.md

---

Phase 4 — Analyst Reports

Sources by region:

Region	Primary Source	Supplementary
US	FMP API latest-8k; Seeking Alpha	stockanalysis.com forecast page
Europe	Company IR; exchange filings	Seeking Alpha (if ADR exists)
Japan	Company IR; JPX TDnet; Seeking Alpha (ADR)	EDINET
Taiwan	AlphaSpread; Seeking Alpha	stockanalysis.com forecast
India	Trendlyne; BSE/NSE filings	Screener.in
All	https://stockanalysis.com/quote/.../forecast/	Search: "{company}" analyst report site:goldmansachs.com OR site:morganstanley.com

Capture per analyst: bank name, analyst name, report date, rating, price target, key thesis points, key risks cited.

Save to: /home/ubuntu/{ticker}_analysts.md

---

Phase 5 — Stock & Technical Analysis

Sources (all regions):

1. https://finance.yahoo.com/quote/{ticker}/history/ — set to 5Y range for price history
2. https://stockanalysis.com/quote/{exchange_prefix}/{ticker}/statistics/ — P/E, P/S, P/B, market cap, EV

Capture: current price, 52-week high/low, market cap, enterprise value, P/E (TTM), forward P/E, P/S, P/B, EV/EBITDA, key technical levels (support, resistance, 50d/200d MAs), RSI, MACD commentary.

Save to: /home/ubuntu/{ticker}_technical_analysis.md

---

Phase 6 — Build the Wiki

Design System

Use East Asian Corporate Modernism design philosophy:

• Background: pure white (oklch(1 0 0))
• Primary accent: blue
• Typography: Noto Serif Display (headings) + Inter (body) + JetBrains Mono (financial figures)
• Layout: persistent left sidebar (264px) + main content area

Add to client/index.html:

<link href="https://fonts.googleapis.com/css2?family=Noto+Serif+Display:wght@400;600;700&family=Inter:wght@400;500;600&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet" />

Page Structure

Route	Component	Content
/	Home.tsx	Company summary, key stats, history timeline, milestones
/products/{slug}	Product{Name}.tsx	Per-product page using ProductPageTemplate.tsx
/financials	Financials.tsx	Revenue/margin charts (Recharts), 5-year table
/analysts	AnalystReports.tsx	Analyst cards with ratings, targets, thesis
/stock	StockAnalysis.tsx	Price chart, valuation multiples, technical levels
/competitors	Competitors.tsx	Peer comparison (see Competitors section)
/modelling	FinancialModelling.tsx	Scenario model (see Financial Modelling section)
/sources	Sources.tsx	Numbered citations with dates and URLs

See references/page-templates.md for detailed component patterns for each page type.

Citation System

All data must carry a superscript citation number. Use a shared CitationRef component:

// client/src/components/CitationRef.tsx
export function Cite({ n }: { n: number | number[] }) {
  const nums = Array.isArray(n) ? n : [n];
  return (
    <sup
      className="ml-0.5 text-[0.65rem] font-mono text-primary/70 cursor-pointer hover:text-primary"
      onClick={() => {
        const el = document.getElementById(`source-${nums[0]}`);
        el?.scrollIntoView({ behavior: "smooth" });
        el?.classList.add("ring-2", "ring-primary");
        setTimeout(() => el?.classList.remove("ring-2", "ring-primary"), 2000);
      }}
    >
      [{nums.join(",")}]
    </sup>
  );
}

The Sources.tsx page lists every source with:

• Sequential number (anchor id="source-{n}")
• Source type badge (Earnings Presentation / Annual Report / Analyst Report / News / Website)
• Publisher name, publication date, URL as clickable link
• Short description of what information it provides

Financial Modelling Page

Build three scenarios — Bear, Base, Bull — using actual historical revenue CAGR as the baseline:

Bear  = current CAGR × 0.6  (deceleration)
Base  = current CAGR × 1.0  (continuation)
Bull  = current CAGR × 1.4  (acceleration)

For each scenario project for FY+1 and FY+2:

• Annual revenue, gross profit (trailing 3-year avg gross margin), net income (trailing 3-year avg net margin)
• EPS (current diluted share count), forward P/E at current price, forward P/S at current price

Display as: scenario selector tabs + summary cards + cross-scenario comparison table.

Python script for computing projections: scripts/financial_model.py

Competitors Page

Identify the peer set using FMP API peers endpoint or the company's own industry classification. For each peer collect from stockanalysis.com: revenue (5 years), gross margin, net margin, P/E (TTM), P/S, P/B, market cap.

Display as:

1. Interactive multi-series Recharts charts with company filter checkboxes
2. Valuation comparison table
3. Product moat matrix — rows = product/capability types, columns = companies, cells = capability level (Leader / Capable / Limited / None)
4. Moat narrative cards — each company's unique differentiator

See references/competitor-research.md for the competitive positioning framework and region-specific peer identification guidance.

---

Phase 7 — Delivery

1. Run npx tsc --noEmit — must show zero errors before checkpoint
2. Run webdev_save_checkpoint
3. Attach manus-webdev://{version_id} in the result message
4. Suggest concrete next steps (sensitivity table, price target calculator, quarterly earnings timeline)

---

Quick Reference: FMP Ticker Formats

Exchange	Country	FMP Suffix	Example
NASDAQ / NYSE	US	(none)	AMD
London Stock Exchange	UK	.L	IQE.L
Euronext Paris	France	.PA	SOI.PA
Euronext Amsterdam	Netherlands	.AS	ASML.AS
Xetra / Frankfurt	Germany	.DE	SAP.DE
Nasdaq Stockholm	Sweden	.ST	SIVE.ST
Tokyo Stock Exchange	Japan	.T	4063.T
Taiwan Stock Exchange	Taiwan	.TW	2308.TW
NSE India	India	.NS	OLAELEC.NS
BSE India	India	.BO	OLAELEC.BO

Completion (run last)

Audit before you deliver. If this run produced a research deliverable carrying quantitative or factual claims — a deep dive, thematic/value-chain map, technical call, company wiki, or financial model — you MUST verify it before presenting it. If a research-auditor subagent is available (the analyst-kit plugin ships one), invoke it via the Task tool, handing it the draft and the data artifacts you used; on a runtime without subagents, run the same checks yourself. Resolve every CRITICAL finding and disclose any UNVERIFIED ones; never deliver on a FAIL verdict without fixing it first. Skip this only for pure data-fetch/utility runs with no analytical claims.

PLAN MODE EXCEPTION — ALWAYS RUN: writes only to ~/.analyst-kit/. Replace OUTCOME with one of DONE | DONE_WITH_CONCERNS | ERROR | ABORT | NEEDS_CONTEXT.

_AK="$(cat ~/.analyst-kit/core-path 2>/dev/null)"
[ -x "$_AK/bin/analyst-kit-log" ] && "$_AK/bin/analyst-kit-log" end --skill company-wiki --outcome OUTCOME 2>/dev/null || true

If this session surfaced a durable pattern, pitfall, or user preference that would save 5+ minutes next time (not obvious, not a transient error), also log it:

"$_AK/bin/analyst-kit-learn" add '{"skill":"company-wiki","type":"pitfall|pattern|preference","ticker":"<optional>","insight":"<one line>","confidence":7,"ts":"<iso8601 utc>"}'