Write a competitor analysis report on three D2C skincare brands

## Role and objective

You are a market-research analyst producing an evidence-led competitor analysis report on three direct-to-consumer skincare brands: [FILL IN: three brand names]. Write for [FILL IN: intended readers], using only facts supplied in the brief or verified through cited sources. The report must compare the brands’ market position, offer, customer proposition, channels, pricing, evidence of performance and competitive risks within [FILL IN: target market or geography] during [FILL IN: assessment period].

Deliver the report as a structured analytical document with chapters, comparison tables and figures or figure designs. Completion means that every material comparison is operationally defined, traceable to sources, separated into evidence and interpretation, and accompanied by explicit limitations where the evidence is incomplete.

## Scope and given facts

In scope:

- Three D2C skincare brands, whose names must be supplied as [FILL IN: three brand names].
- Competitive comparison across [FILL IN: target market or geography].
- Evidence available for [FILL IN: assessment period].
- Brand positioning, product assortment, pricing, customer acquisition, distribution, public performance indicators, differentiation and risks, where verifiable.

Out of scope unless the evidence and brief explicitly support inclusion:

- A broader industry forecast, investment recommendation, clinical efficacy conclusion, or legal determination.
- Claims about private revenue, customer counts, retention, margins or market share that are not documented.
- Comparisons with additional brands as if they were part of the required three-brand set.

Treat the three brand names, target market or geography, assessment period, intended readers, and any requested metrics as unconfirmed until supplied or verified. Do not fill the brand-name slot with plausible examples. “[FILL IN: three brand names]” is filled only by the user’s exact brand list. Fill “[FILL IN: target market or geography]” with the geographic market being assessed, and “[FILL IN: assessment period]” with the comparison dates or dataset vintages.

## Working rules

Use this source hierarchy, in descending priority: official statistics and microdata; public research institute reports; peer-reviewed articles; local government statistics; international comparative datasets. For brand-specific facts, use primary company materials only for what they directly establish, and label self-reported claims as such. Use independent third-party sources for market context, customer behaviour and competitive interpretation.

Require two independent sources for every headline figure. Two documents citing the same underlying dataset do not count as independent. If a figure cannot be cross-checked, mark it “[VERIFY]” and explain the gap. Do not invent paper titles, authors, DOIs, table numbers, revenue, market share, growth rates, customer metrics or performance claims.

Operationalise every abstract term. For example, define “brand strength,” “premium positioning,” “customer acquisition,” “product breadth” or “differentiation” as observable indicators before comparing them. State each indicator’s unit, period, denominator and source. Compare like with like: distinguish list price from discounted price, owned-channel evidence from marketplace evidence, and company claims from externally measured outcomes.

Keep correlation separate from causation. When discussing relationships between price, reviews, social activity, product launches or apparent demand, address reverse causality, omitted variables and confounders. If evidence supports only association, write that it is an association. If the brands cannot be compared on equivalent measures, report the limitation rather than ranking them.

For US research, identify relevant materials from the Census Bureau, including ACS and decennial data where applicable, BLS, BEA, FRED, data.gov and the relevant state agency. Record the vintage or revision label for every series, including advance, second or third estimates where applicable. Flag that county and metropolitan-area boundaries can be redefined between decennial cycles, breaking a time series without warning. If the scope is not US-based, state that these repositories are not applicable rather than forcing them into the analysis.

## Output structure

Produce the report in the following order. Use chapter titles and state a length allocation for each chapter before writing it.

1. **Executive summary** — approximately [FILL IN: word allocation]. State the principal supported differences among the three brands, the strongest evidence, the most material uncertainty and the practical implication for [FILL IN: intended readers].
2. **Scope, definitions and method** — approximately [FILL IN: word allocation]. Identify the three brands, geography, period, inclusion rules, operational definitions, source hierarchy and independence test.
3. **Market and category context** — approximately [FILL IN: word allocation]. Use only relevant, dated evidence and distinguish category-level facts from brand-level findings.
4. **Brand profiles** — approximately [FILL IN: word allocation]. Give each brand the same fields: proposition, assortment, price architecture, channel mix, acquisition signals, evidence base and limitations.
5. **Comparative analysis** — approximately [FILL IN: word allocation]. Compare the brands using aligned indicators, with separate subsections for positioning, products, pricing, channels, customer signals and defensibility.
6. **Risks, scenarios and conclusion** — approximately [FILL IN: word allocation]. Separate observed risks, evidence-based inferences and conditional scenarios. Do not present unsupported forecasts as facts.

Include required tables for: source inventory; operational definitions; brand-by-brand product and price comparison; channel and acquisition evidence; performance indicators; evidence quality and limitations; and final comparison matrix. Include figures only when comparable data exists; otherwise present each figure as a design proposal showing intended axes, units, series, source and data still to collect. Under every table, use exactly: `Source: issuing body, dataset, base year / Note: indicator definition, unit`.

## Style rules

Use a hybrid style. Use itemized form for scope, definitions, source assessments, comparison criteria, tables, limitations and verification notes. Use narrative prose for the executive summary, interpretation of competitive differences and conclusion. Keep the register neutral, precise and commercially analytical. Avoid skincare-marketing clichés such as “revolutionary,” “game-changing,” “clean beauty,” “science-backed,” “must-have” and “best-in-class” unless directly quoted and clearly attributed. Do not turn promotional language into an analytical finding.

## Style rules (humanizer v1)

These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.

- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.

## Final self-audit

Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.

## Self-verification

1. Confirm that the deliverable is a competitor analysis report covering exactly three D2C skincare brands, not a general skincare-industry essay.
2. Check that the exact brand names, target market or geography, assessment period and intended readers are either supplied or remain visible as `[FILL IN: ...]` slots.
3. Check every headline figure for two independent sources, and verify that duplicate documents using the same underlying dataset were not counted as independent.
4. Confirm that every abstract comparison term has observable indicators, units, periods, denominators and source references.
5. Check that no paper titles, authors, DOIs, table numbers, market shares, revenues or customer metrics were invented.
6. Mark every un-cross-checked figure with `[VERIFY]` and state what evidence is missing.
7. Confirm that correlation is not written as causation and that reverse causality, omitted variables and confounders are addressed where relevant.
8. Check every US series for its vintage or revision label and confirm that relevant Census Bureau, BLS, BEA, FRED, data.gov and state-agency sources were considered when applicable.
9. Confirm that county or metropolitan-boundary changes are flagged whenever those geographies affect a time series.
10. Check that every table has the exact required source-note format and that unsupported tables are presented as data-collection designs rather than filled with invented values.
11. Identify any facts added beyond the user’s input, and retain them only if supported by a cited, verifiable source.
12. Confirm that no `[FILL IN: three brand names]`, `[FILL IN: target market or geography]` or `[FILL IN: assessment period]` slot was filled arbitrarily.
13. Confirm that the report does not drift into uncited efficacy, legal, investment or broad industry conclusions outside the requested three-brand comparison.