agentleFS
Faaz17Faaz17/Agents-and-Skills/skills/research-writing/aviation-data-sources/SKILL.md

aviation-data-sources

Skill1 starsChanged 2 months agoMITView on GitHub

Where to find and how to verify data for the MGT4897 DXB report — Dubai Airports newsroom releases, the DWC expansion page, ICAO and IATA statistics, ACI airport rankings and ASQ, UAE government statistics, and the academic journals that carry airport operations and air transport demand research. Includes the source-quality hierarchy, the data-log protocol, and the rules against fabricated figures. Use when sourcing any number, fact, or journal reference.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never invent a figure, a source, a URL, a date, or a DOI: If a number cannot be traced to a real, named, dated source, write [UNVERIFIED — …

    line 10
  2. Distinctive:

    Search terms that work: *airport passenger demand forecasting*.

    line 93
  3. Very specific:

    Every figure enters 02-Analysis/data-log.md before it enters a draft.

    line 108
  4. Distinctive:

    Prefer the primary source: If a news article reports a Dubai Airports figure, cite Dubai Airports

    line 134
  5. Distinctive:

    Every figure should either drive a decision or be cut.

    line 155
  6. Distinctive:

    No cost, revenue or operational-constraint data was provided, so the location and capacity recommendations rest on published information …

    line 171

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Data sourcing and verification — aviation and DXB

The rule that outranks the rest

Never invent a figure, a source, a URL, a date, or a DOI. If a number cannot be traced to a real, named, dated source, write [UNVERIFIED — needs source] and leave it visible in the draft. A visible gap is a task; a fabricated number in a Turnitin submission is academic misconduct.

This applies to passenger counts, capacity figures, market shares, cost estimates, runway counts, distances, dates, and every percentage. It applies equally to "approximately" and "around" — a vague fake is still a fake.

Source-quality hierarchy

Work down. Stop at the highest tier that has the number.

  1. Dubai Airports' own disclosures — the newsroom, annual traffic releases, the DWC expansion page, Dubai Airports corporate publications. For DXB figures this is the primary source and the brief itself points to it
  2. Peer-reviewed journal articles — the only tier that satisfies the five-journal requirement
  3. International aviation bodies — ICAO, IATA, ACI. Official, methodologically documented
  4. UAE government and statutory bodies — GCAA, Dubai Statistics Centre, UAE Federal Competitiveness and Statistics Centre, Dubai Media Office, Dubai's 2040 Urban Master Plan
  5. Airline disclosures — Emirates Group annual report, flydubai. Relevant because DXB's traffic is hub-dependent
  6. Consultancy and industry research — McKinsey, PwC, Deloitte, Oliver Wyman, ACI economics reports. Credible but promotional; read the methodology note
  7. Quality business press — Reuters, FT, Bloomberg, Gulf News, The National, Arabian Business, Aviation Week. For events and dates, not headline statistics

Never cite: blogs, SEO listicles, "top 10 airports" content-marketing pages, Wikipedia (follow its sources instead), AI-generated summaries, or undated pages.

The three sources the brief names

The brief explicitly encourages these. Using them is free marks for diligence.

SourceURLWhat it gives
ICAO Air Transport Monthly Monitorhttps://www.icao.int/air-traffic-monitorGlobal traffic trends, passenger growth, forecasts. Benchmarks DXB against world and Middle East growth rates
Dubai World Central expansion pagehttps://dubaiairports.ae/corporate/our-story/dwc-dubai-world-centralThe USD 35bn Phase II programme, capacity targets, timeline, strategic rationale. Essential for task 4
Dubai Airports Newsroomhttps://media.dubaiairports.aeAnnual traffic press releases back to 2013, quarterly updates, operational milestones

Verify the brief's own data against the newsroom releases. The brief attributes its tables to "Dubai Airports, 2026". Confirming a sample of years against the original releases, and reporting that you did, demonstrates exactly the verification the rubric rewards under task 8. If a figure differs, report the discrepancy rather than silently picking one — that is analysis.

Note the brief's figures for 2024 (92,300,000) and 2025 (95,200,000) are round to the hundred thousand while earlier years are exact. That suggests rounded or provisional reporting for the recent years. Worth a sentence in the limitations.

Aviation data beyond the brief

NeedSource
World's busiest airports by international passengersACI World annual traffic rankings
Airport service quality benchmarkingACI Airport Service Quality (ASQ) programme
Global and regional traffic forecastsIATA passenger forecasts; ICAO long-term traffic forecasts; Boeing and Airbus commercial market outlooks
Air transport economic contributionATAG Aviation: Benefits Beyond Borders; IATA economics briefings
Emirates hub traffic and fleetEmirates Group Annual Report
Airport capacity and slot coordination methodologyIATA Worldwide Airport Slot Guidelines; EUROCONTROL for methodology precedent
UAE aviation regulationUAE General Civil Aviation Authority (GCAA)
Dubai population and economic contextDubai Statistics Centre; Dubai 2040 Urban Master Plan
Aviation emissions and net zeroIATA net zero commitments; UAE Net Zero 2050 strategic initiative

Academic literature — where the five journal articles come from

The requirement is a minimum of five high-quality journal articles. Search:

Google Scholar · ScienceDirect · Emerald Insight · Taylor & Francis · Wiley · JSTOR · the Middlesex library discovery service.

Journals that carry directly relevant work:

ThemeJournals
Air transport management and airport operationsJournal of Air Transport Management; Transport Policy; Research in Transportation Economics
Air travel demand forecastingJournal of Air Transport Management; Transportation Research Part A; International Journal of Forecasting
Airport capacity, congestion and slotsTransportation Research Part A / Part E; Transportation Science
Airport service qualityJournal of Air Transport Management; Total Quality Management & Business Excellence; Managing Service Quality
Facility location and multi-criteria decision methodsInternational Journal of Production Economics; European Journal of Operational Research; Omega
Operations and quality management generallyInternational Journal of Operations & Production Management; Journal of Operations Management; Production and Operations Management

Search terms that work: airport passenger demand forecasting; air traffic forecasting error; airport capacity expansion decision; multi-airport system transition; airport service quality SERVQUAL; hub airport relocation; weighted factor location model.

Capture the DOI at the moment you find the paper. Retrofitting DOIs the night before submission is miserable and is where fabrications creep in.

Relevant precedent worth searching for: other hub relocations — Hong Kong Kai Tak to Chek Lap Kok, Denver Stapleton to DIA, Istanbul Atatürk to Istanbul Airport, Berlin Brandenburg, Bangkok Don Mueang to Suvarnabhumi. These give the "at least two industry-relevant examples" task 2 demands, and citing a real transition that overran or under-delivered is far stronger than a generic statement about forecast error.

The data-log protocol

Every figure enters 02-Analysis/data-log.md before it enters a draft.

FieldMeaning
IDD001, D002 … — reference it in draft comments
ClaimWhat the number asserts, in one line
ValueFigure with unit
PeriodThe period the figure describes, not the publication year
SourceFull Harvard reference
LocationPage, table, or section within the source
URLStable direct link
AccessedDate retrieved
Confidenceverified / secondary / estimate / unverified
So whatWhy it matters to the COO's decision
  • verified — read it in the primary source myself
  • secondary — a source I read attributed it to someone else; note both
  • estimate — derived or calculated; show the arithmetic
  • unverified — placeholder only; must not survive to submission

Figures the forecasting engine computes are estimate with the arithmetic shown by the script and the workbook. That is legitimate and must be labelled as calculated output, not presented as observed data.

Verification discipline

  • Prefer the primary source. If a news article reports a Dubai Airports figure, cite Dubai Airports
  • Check the period. A 2026 publication often reports 2025 data
  • Check the definition. "Passengers" can mean total, international only, or arrivals-plus-departures counted once or twice. DXB's "world's busiest international airport" title rests on international passengers specifically — conflating that with total passengers is a mistake an aviation-literate marker will spot immediately
  • Check the geography. DXB ≠ DWC ≠ Dubai's airport system ≠ UAE
  • Check the units. Movements vs flights vs departures; millions vs absolute
  • Triangulate anything load-bearing. Where sources disagree, report the range and explain the divergence — that is analysis, and it earns marks

Using data well — what earns marks

Weak: "DXB handled 95.2 million passengers in 2025 (Dubai Airports, 2026)."

Strong: "At 95.2 million passengers against a 115 million design capacity, DXB is running at roughly 83% utilisation (Dubai Airports, 2026). On the pre-COVID growth basis that headroom is exhausted by 20xx — inside the lead time for any terminal project the COO could commission today."

Every figure should either drive a decision or be cut.

Limitations to acknowledge in the conclusion

Task 7 awards marks for this explicitly. Real limitations here:

  • 13 annual observations for passengers, 9 for movements — a small sample for extrapolation to 2036
  • A structural break (2020–2022) sits in the middle of the passenger series
  • Annual data conceals seasonality, and airport operations are acutely seasonal; peak-day and peak-hour capacity, not annual totals, is what actually binds
  • The 2024 and 2025 figures are rounded, suggesting provisional reporting
  • The brief's data stops at 2025; no 2026 partial-year data is incorporated
  • The associative model extrapolates beyond the observed movement range (max 454,800)
  • Passengers per movement is treated as stable, when it depends on aircraft gauge and load factor, both of which shift over a decade
  • No cost, revenue or operational-constraint data was provided, so the location and capacity recommendations rest on published information and stated assumptions rather than internal data

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.