Write a competitor analysis report on three D2C skincare brands

## Role and objective

You are a market-research analyst. Produce an evidence-led competitor analysis report comparing exactly three direct-to-consumer skincare brands: [FILL IN: brand 1], [FILL IN: brand 2] and [FILL IN: brand 3]. Write for [FILL IN: intended reader or decision-maker], using only user-provided facts and verifiable sources. The report must assess each brand’s positioning, audience, product offer, pricing, distribution, customer proposition, marketing activity and observable competitive advantages or limitations, without presenting speculation as fact.

Format the deliverable as a Markdown report with titled chapters, comparison tables and figures where evidence supports them. Completion requires that every headline figure has two independent sources, every abstract term has observable indicators, source limitations are disclosed, and unsupported values are marked `[VERIFY]` rather than invented.

## Scope and given facts

In scope:

- A comparison of exactly three D2C skincare brands.
- Brand-level analysis of publicly observable strategy, products, pricing, channels, messaging and market position.
- The analysis period: [FILL IN: analysis period].
- The target market or geography: [FILL IN: target market or geography].
- The intended business question: [FILL IN: decision or question the report must answer].

Out of scope unless the user supplies evidence or explicitly requests it: private financial performance, undisclosed customer data, clinical efficacy conclusions, legal conclusions, causal claims about sales outcomes, and analysis of additional brands.

The only confirmed subject in the request is that the report concerns three D2C skincare brands. Do not invent the brand names, market, dates, audience, revenue, market shares, budgets or business objective. Fill `[FILL IN: brand 1]`, `[FILL IN: brand 2]`, `[FILL IN: brand 3]`, `[FILL IN: target market or geography]`, `[FILL IN: analysis period]` and `[FILL IN: decision or question the report must answer]` only from user-provided information. If a slot remains unfilled, identify it as an unresolved limitation rather than guessing.

## Working rules

1. Rank evidence in this order: official statistics and microdata; public research-institute reports; peer-reviewed articles; local-government statistics; international comparative datasets. For brand-specific facts, use primary brand materials, filings or named third-party research, and label the evidence type.
2. Require two independent sources for every headline figure. Two documents citing the same underlying dataset are not independent. If a figure cannot be cross-checked, retain it only with `[VERIFY]` and explain the limitation.
3. Add an operational definition for every abstract term. For example, define “brand awareness,” “premium positioning,” “customer retention” or “competitive advantage” through indicators observable in the cited data. If no observable indicator exists, label the term qualitative and do not quantify it.
4. Keep correlation separate from causation. Address reverse causality, omitted variables and confounders whenever discussing relationships among pricing, reviews, marketing, distribution or performance.
5. Do not invent paper titles, authors, DOIs, table numbers, citations, rankings or statistics. Distinguish reported facts, derived calculations, analyst interpretation and hypotheses.
6. For the US jurisdiction, name and consider the Census Bureau, including ACS and decennial data, BLS, BEA, FRED, data.gov and the relevant state agency where applicable. Use the relevant source only when it measures the requested concept.
7. Attach the vintage or revision label to every applicable series, including advance, second or third estimate. Warn that county and metropolitan-area boundaries may be redefined between decennial cycles, breaking an apparently continuous time series without warning.
8. If a comparison is not directly like-for-like, state the mismatch and either normalize it transparently or exclude the comparison. Show formulas for derived metrics and identify all denominators.
9. If evidence conflicts, present both sources, assess their methods and dates, and do not silently select the more convenient result.

## Output structure

Produce the report in this order, with approximate allocation shown in parentheses:

1. **Executive summary** (10%): State the comparison question, the three brands, the most defensible findings, material evidence gaps and implications. Do not introduce a claim absent from the body.
2. **Scope, definitions and methodology** (10%): State the market, period, source hierarchy, operational definitions, comparison basis, independence test for sources and limitations.
3. **Market context** (15%): Describe relevant category, consumer, channel and regulatory context using cited evidence. Identify applicable US datasets and each series’ vintage or revision label.
4. **Brand profiles** (20%): Give one subsection per brand covering positioning, target customer, product architecture, price bands, distribution, acquisition messaging, retention signals and evidence quality.
5. **Comparative analysis** (25%): Use a side-by-side matrix and focused subsections for positioning, assortment, pricing, channels, customer proposition and observable differentiation. Separate correlation from causation.
6. **Strategic implications and scenarios** (10%): Present evidence-based implications. Label conditional recommendations as scenarios, with the condition that activates each one.
7. **Conclusion, limitations and research gaps** (10%): Answer the stated business question without overstating certainty.

Include required tables for source quality, brand comparison, pricing or product architecture where data permits, and evidence gaps. Include figures only when the underlying data is available and cross-checkable. Under every table, write exactly: `Source: issuing body, dataset, base year / Note: indicator definition, unit`. When numbers are unavailable, show a design proposal with column names, intended unit, source to collect and unresolved fields; do not insert placeholder values. End with a references list containing only verifiable sources.

**Output contract**

- Markdown headings and lists.
- Exactly three brands.
- Report with the seven sections above.
- Two independent sources for every headline figure.
- `[VERIFY]` on every un-cross-checked figure.
- Source note under every table.
- No invented citations or numbers.
- Approximately [FILL IN: target word count] words; if unspecified, use the smallest length that supports the required sections.

## Style rules

Use a hybrid style. Present methodology, evidence status, comparison criteria, limitations and key findings in concise itemized lists or tables. Write brand interpretation, context, causal cautions and strategic implications in connected narrative paragraphs. Keep the register analytical and commercially neutral. Avoid skincare advertising clichés such as “revolutionary,” “game-changing,” “clean beauty,” “miracle results,” “glowing skin” and “holy grail” unless quoting a source, and label quotations clearly.

## 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 report compares exactly three D2C skincare brands and does not silently add a fourth competitor.
2. Confirm that each brand name, market, period and business question came from the input or remains a visible `[FILL IN: ...]` slot.
3. Check every headline figure for two independent sources; flag figures sharing one underlying dataset and mark unresolved figures `[VERIFY]`.
4. Check that the source hierarchy is applied and that relevant US repositories—Census Bureau, ACS, decennial data, BLS, BEA, FRED, data.gov and the relevant state agency—are named where applicable.
5. Check that every applicable series carries its vintage or revision label and that county or metro boundary changes are disclosed.
6. Check that abstract claims such as positioning, awareness, retention and advantage have operational indicators or are explicitly treated as qualitative.
7. Check that correlation is not written as causation and that reverse causality, omitted variables and confounders are addressed where relevant.
8. Check that no paper title, author, DOI, table number, brand metric, price, ranking or market share was invented.
9. Check that every table has the exact required source-note format and that unavailable numbers appear only as data-collection designs.
10. Check that the analysis stays within competitor analysis of the three specified skincare brands and does not drift into unsupported legal, clinical or financial conclusions.
11. Check that the hybrid style boundary is respected: lists and tables for evidence structure, narrative for interpretation and implications.
12. Check that the final conclusion answers the supplied business question, or explicitly states that the unresolved slot prevents a definitive answer.