Audit: QRS - Topical Retinol for Skin Rejuvenation

Audit conducted on 13/08/2026 14:53 using AI4L / Opus 5

Iterations

Summary

Items Count
Total 93
Passed 83
Failed 0
N/A 10
Pass Rate 100.00%
  • Total = Passed + Failed + N/A
  • Pass Rate = Passed / (Passed + Failed) × 100
  • N/A items are excluded from the pass rate calculation

1. General Rules

# Description Result Comments
1.1 Every claim, magnitude, label, recommendation, and statement in the QRS is literally supported by content in the source ER. 🟢 Spot-checked every populated span against the ER: protocol values (ER 303, 307, 309, 315), time-to-effect (ER 341, 162, 166), tier lists (ER 148–192, 209–253), gates (ER 267–286), monitoring table (ER 365–372) and cadence (ER 363).
1.2 Where the ER uses cautious phrasing (“not formally studied”, “None documented in human trials to date”, “theoretical concern”, “data are limited”), the QRS uses the same phrasing. 🟢 marker_5_target retains “No established target for retinol users”; speculative tiers are carried as “Speculative” in both Benefits and Risks.
1.3 The QRS never strengthens an ER claim (e.g., “not formally studied” → “not required”) or softens one (e.g., “do not use during pregnancy” → “use with caution during pregnancy”). 🟢 Pregnancy stays in Contraindications (line 542), matching the ER’s “Populations who should avoid” list; oral isotretinoin remains an absolute contraindication rather than a caution.
1.4 The QRS does not relabel an ER fact under a different decision category. A “Benefit-Modifying Factor” from ER section is not surfaced as a “Caution”; a “Risk-Modifying Factor” is not surfaced as a “Side Effect”; etc. 🟢 Contraindications come only from the ER “Populations who should avoid” block, Key Interactions only from the ER interaction bullets; no Benefit- or Risk-Modifying Factor content appears anywhere on the sheet.
1.5 PubMed IDs, study citations, expert names, clinical trial identifiers (NCT*), and brand names appear in the QRS only if they appear in the source ER for the same fact. 🟢 Source scan returns no PubMed links, no “et al.”, no NCT identifiers and no brand names.
1.6 The QRS does not introduce new attributions. 🟢 No named investigators, institutions or organisations appear in any populated span.

2. Focus, Tone & Audience

# Description Result Comments
2.1 The QRS follows the tone of the ER, which is determined by the ER’s own language, phrasing, and framing. 🟢 Measured, non-promotional register; British spellings (“colour”, “remodelling”, “photodegradation”) carried over from the ER.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Numeric anchors (concentrations, week markers, biomarker ranges) sit alongside plain-language framing in At-A-Glance and Qualitative Assessment.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 Content is presented as labelled facts (“Standard regimen”, “Concentration ceiling”) rather than instructions issued to a patient.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 No prescriptive verbs; the Protocol panel reports the standard regimen and the Monitoring cadence reports review timing without directing anyone.
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 The ER’s “Practitioners typically start…” and “Ongoing review is best set at…” are rendered as declarative data (lines 447–450, 673), not as recommendations.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance 🟢 No second-person pronouns anywhere in the source.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon 🟢 Technical terms are limited to ER-verbatim benefit, risk and biomarker names required by items 12.x, 13.x and 14.x.
2.8 Information is presented in a concise and very compact manner 🟢 Every populated span is a single short phrase or one- to two-clause sentence.
2.9 It DOES NOT address the reader directly 🟢 Confirmed by the same second-person scan; the Qualitative Assessment items are phrased as observations, not instructions.
2.10 The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review. 🟢 The sheet assumes willingness to run baseline serum retinol, fasting retinyl esters, ALT and DXA-derived T-score.
2.11 The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort. 🟢 The staged twelve-week titration schedule and the standardised-photography efficacy endpoint both assume sustained effort.
2.12 The document is NOT written for the general population, who are unwilling to employ lifestyle and behavioral changes or follow protocols that may be inconvenient, costly, or require effort. 🟢 Biomarker targets are functional ranges, not conventional laboratory cut-offs, which is not general-population framing.
2.13 Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience. 🟢 Aggregate vitamin A exposure is surfaced as a Medium risk and as three separate gate items, reflecting an audience already taking supplements.
2.14 The document’s own voice frames usage in longevity terms, not “anti-aging” (e.g., “anti-aging clinics”, “anti-aging community”, “anti-aging medicine”). Proper names that contain “anti-aging” (e.g., “American Academy of Anti-Aging Medicine”) are quoted verbatim. 🟢 The string “anti-aging” does not occur in the file; the framing term is “Skin Rejuvenation”.
2.15 The document’s own voice uses formal clinical and scientific terminology, not colloquial or consumer-grade language (e.g., “oral medication” not “pill(s)”; “injection” not “shot”; “adverse event” not “bad reaction”). Direct quotes from sources are exempt. 🟢 “Retinoid dermatitis”, “transepidermal water loss”, “mottled hyperpigmentation” and “re-epithelialisation”-level register throughout; At-A-Glance plain language is mandated separately by item 7.4.

3. Template Integrity

# Description Result Comments
3.1 The following labels and headings on the QRS are fixed and not modified: Card and section headings: “Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”; Gate headings: “Contraindications”, “Key Interactions”; Tier labels: “High”, “Medium”, “Low”, “Speculative”; Table column headers in Monitoring: “Marker”, “Target”, “Why” 🟢 All present and unmodified: lines 440, 477, 519, 574, 593, 679 (cards), 539, 553 (gates), 522–531 and 577–586 (tiers), 597–599 (table headers).
3.2 All “” from the [qrs_template] are present in the the QRS. 🟢 58 data-qrs-var spans present, covering the full variable set the checklist addresses (header ×4, at_a_glance, action_1–3 ×3, time_1–3 ×3, four benefit tiers, stop/caution, four risk tiers, marker_1–6 ×3, monitoring_cadence, qualitative_item_1–6).
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 The three non-variable spans (website=”evidence_review”, website=”audit”, website=”full_review”) remain untouched at lines 423, 426 and 434.

4. Formatting

# Description Result Comments
4.1 When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied” N/A No source ER section feeding the QRS is empty; every benefit tier, risk tier, gate list, protocol, monitoring and qualitative source block is populated.
4.2 Where the ER presents a bulleted item as “Label: content”, the QRS uses the ER’s bold label verbatim as the cell or row label. 🟢 “Standard regimen”, “Best time of day” and “Concentration ceiling” match ER lines 303, 307 and 315 verbatim; the nine Key Interactions labels match ER lines 267–276.
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Benefit and risk names match the ER headings word for word; biomarker names match the ER table’s Biomarker column exactly.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. 🟢 Source scan returns no emoji code points; the ER’s 🟩/🟥/🟨 tier markers and the ⚠️ Conflicted flags were correctly dropped.
4.5 The QRS is designed to render on one A4 page. Any section that has more content in the ER than fits the per-section budget is condensed by the LLM, not extended onto a second page. 🟢 Single .sheet container with the template’s A4 @page rule intact; content was condensed rather than extended (e.g., marker_5_target trimmed from the ER’s longer phrasing, parenthetical glosses dropped from the gate items).

5. Metadata

# Description Result Comments
5.1 The metadata is placed inside a single HTML comment that is the first element after “<!doctype html>” and before any other comment, head, or body content. 🟢 Lines 2–14: the comment opens on line 2, immediately after the doctype on line 1, and precedes every other comment and the head.
5.2 Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. Text before the opening “—” is permitted but is not parsed as YAML. 🟢 Opening “—” on line 3, closing “—” on line 13; the descriptive text on line 2 sits before the opening delimiter.
5.3 The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet. 🟢 Enclosed in an HTML comment and not duplicated in the header, footer or any card.
5.4 All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting. 🟢 Only duration: "00:02" is quoted, and it contains a colon; all other values are bare and untrimmed of nothing.
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 Line 4: er_filename: topical_retinol_skin_2026-0813-1321_Opus_ER.md.
5.6 Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]” 🟢 Line 5 states 26.7.02, matching the QRS.md version badge.
5.7 Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430) 🟢 Line 6: qrs_creation_date: 2026-0813-1442.
5.8 The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]” 🟢 Line 7: qrs_creator_ai_nickname: Opus.
5.9 The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT) 🟢 “Opus” — single word, no version or qualifier.
5.10 The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]” 🟢 Line 8: qrs_creator_ai_fullname: Opus 5.
5.11 The full name of the AI consists of the [qrs_creator_ai_nickname] and the model version number and no additional qualifier (e.g., Opus 4.6, Sonnet 3.2, Grok 4.5, Gemini 3.1, ChatGPT 5.4) 🟢 “Opus 5” — nickname plus version number, no context-window or tier qualifier.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 Line 9 matches the file’s own name on disk.
5.13 All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting. 🟢 Re-verified across all ten keys; no stray whitespace and no unnecessary quoting.

6. Page Title & Header

# Description Result Comments
6.1 [page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., &amp; for &) 🟢 Line 22: “Topical Retinol for Skin Rejuvenation - Quick Reference Sheet”; the canonical topic contains no characters requiring entity encoding.
6.2 [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., &amp; for &) 🟢 Line 417 matches ER frontmatter canonical_topic exactly.
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 Line 421: “08/13/2026”, the correct reformatting of 2026-0813-1442.
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname] 🟢 Line 425: “Opus 5”, identical to the frontmatter value.
6.5 No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. 🟢 The header holds only the title and the template subline; the ER’s “Also known as” list (Retinol, all-trans-retinol, Vitamin A1, Vitamin A Alcohol) was correctly omitted.

7. At-A-Glance Section

# Description Result Comments
7.1 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section 🟢 Line 433 compresses all three Conclusion paragraphs’ decision-relevant content: what it is, the benefit ranking, the dominant drawback, and the open pregnancy question.
7.2 [at_a_glance] is no longer than 60 words 🟢 56 words.
7.3 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 “convert, inefficiently … gentler … weaker” (ER 396); “softening of fine lines is the strongest” plus pigment and structure (ER 396); “redness, flaking … main reason people stop” (ER 398); pregnancy (ER 398).
7.4 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 Uses “vitamin A”, “prescription creams”, “fine lines”, “patchy colour”, “skin structure”, “redness and flaking” — no acronyms and no clinical-register vocabulary.
7.5 It DOES NOT cite specific trials (names, years, sample sizes, p-values) 🟢 No investigator names, years, cohort sizes or p-values appear.
7.6 It DOES NOT cite effect sizes, relative risks, or statistical results 🟢 The ER’s 44%, 84%, 1.64-point and odds-ratio figures are all absent.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 All seven items map one-to-one onto the ER “Populations who should avoid Topical Retinol” block (ER 278–286) inside that section.
8.2 [stop_items] represent the Contraindications from the ER 🟢 Lines 542–548 reproduce all seven ER entries in ER order, with no additions and no omissions.
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Seven discrete <li> elements inside the span at lines 541–549.
8.4 Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact. 🟢 No dashes introduce trailing clauses; no rationale, citation or study detail appears in any of the seven items.
8.5 Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely). 🟢 “particularly the first trimester”, “one month after the course ends”, “two to four weeks”, “Child-Pugh Class B or C” and “above 10% of total circulating vitamin A” are all retained; only the two plain-language glosses were trimmed, leaving the staging and threshold intact.
8.6 When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol. N/A The ER’s contraindication list uses no ranking notation inside parentheses.
8.7 The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no population, condition, or scenario for which the intervention should be avoided, deferred, or used only under specialist supervision. 🟢 The ER names seven such populations, and the section is correspondingly populated.
8.8 If the section is left empty, an HTML comment inside the [stop_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g. N/A The section is not empty.

9. Key Interactions

# Description Result Comments
9.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 All nine items map onto the ER interaction bullets at lines 267–276.
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 Nine of the ER’s ten interaction bullets appear; “Oral isotretinoin” is correctly excluded because it is an absolute contraindication already carried in [stop_items].
9.3 Individual [caution_items] are formatted as <li></li> 🟢 Nine discrete <li> elements inside the span at lines 555–565.
9.4 Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact. 🟢 Every ER bullet’s post-colon rationale (washout periods, sunscreen mitigation, morning/evening separation, the 3000 µg ceiling) is stripped; only the labels remain.
9.5 Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely). 🟢 All named example lists survive: tretinoin/tazarotene/adapalene; doxycycline/hydrochlorothiazide/amiodarone; hydrocortisone/triamcinolone/mometasone; glycolic/lactic/salicylic; L-ascorbic acid; and the five procedures, which the ER offset with an em-dash and the QRS normalised into parentheses.
9.6 When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol. N/A The ER’s interaction bullets use no ranking notation inside parentheses.
9.7 The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no interaction, additive effect, or exposure that changes how the intervention is used. 🟢 The ER names ten interactions, and the section is correspondingly populated.
9.8 If the section is left empty, an HTML comment inside the [caution_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g. N/A The section is not empty.

10. Protocol

# Description Result Comments
10.1 The section is derived from the ER Protocol section 🟢 All three cells trace to the ER “Therapeutic Protocol” section (lines 303, 307, 309, 315).
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Starting concentration and titration schedule, timing/frequency, and the concentration ceiling are the three decision-bearing choices; the competing-approach and origins bullets are correctly not surfaced as actions.
10.3 If less that three distinct actionable implementation aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing. N/A The ER supplies well over three actionable aspects, and all three sets are used.
10.4 All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. 🟢 Nine populated spans at lines 444–472; “0.1–0.3% at night” (ER 303), “Night, single application” (ER 307/309) and “0.3%” (ER 315).

11. Time to Effect

# Description Result Comments
11.1 The three sets of [time] items cover the three most important time-to-effect aspects from the ER 🟢 Fine wrinkle reduction, mottled hyperpigmentation improvement and matrix remodelling — the three benefits for which the ER states a timeline.
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 Ordered High (Fine Wrinkle Reduction) then the two Medium benefits, matching the ER’s tiering at lines 148, 156 and 164.
11.3 If less that three distinct time-to-effect aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing. N/A Three distinct time-to-effect aspects are present in the ER and all three sets are used.
11.4 All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. 🟢 “12 weeks” and its sub from ER 341; “12–52 weeks” and its sub from ER 162; “4 weeks” and its sub from ER 166 and 341.
11.5 If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel N/A The ER supplies an explicit “Time to effect” bullet (line 341) plus per-benefit timelines, so the section is retained.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 All seven entries come from ER lines 148–192.
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 All four spans present and populated at lines 521–532.
12.3 Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact. 🟢 Each entry is the bare ER heading; the ER’s Magnitude paragraphs (1.64 points, 44%, 84%, 1.5-fold) are entirely absent.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 The ER’s benefit headings carry no parentheticals; the “⚠️ Conflicted” flag on Fine Wrinkle Reduction is correctly dropped per item 4.4.
12.5 If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. N/A All four tiers carry at least one ER benefit, so no span needed hiding.

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 All seven entries come from ER lines 209–253.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 All four spans present and populated at lines 576–587.
13.3 Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact. 🟢 Each entry is the bare ER heading; the 5% withdrawal rate, 4% absorption figure and the pregnancy odds ratios are all absent.
13.4 Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 The ER’s risk headings carry no parentheticals; the “⚠️ Conflicted” flag on First-Trimester Pregnancy Exposure is correctly dropped per item 4.4.
13.5 If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. N/A All four tiers carry at least one ER risk, so no span needed hiding.

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 The table reproduces the ER “Monitoring Protocol & Defining Success” biomarker table (ER 365–372).
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 All six ER rows present: Serum Retinol, Fasting Serum Retinyl Esters, ALT, Bone Mineral Density (T-score), Transepidermal Water Loss, Graded Crow’s-Foot Score — with targets and rationales matching the ER’s Optimal Functional Range and Why Measure It? columns.
14.3 [monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty. 🟢 Line 673 reproduces the ER’s week 2 / week 4 / week 12 / 6-month / 12-month schedule (ER 363).

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 All six items come from the ER’s “Qualitative markers worth tracking” list (ER 376–381).
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 Six ER markers, six QRS items, reproduced verbatim at lines 682–698: stinging/burning, visible flaking, morning tightness, makeup/sunscreen behaviour, subjective smoothness, sun sensitivity.

Issues 13/08/2026 14:53

Pass rate 100.00%. No issues found.

Issues 13/08/2026 14:47

  1. 2.5 / 2.6 / 2.9 — Imperative in protocol sub-cell: action_1_sub (line 450) ends with the bare imperative “reassess at twelve weeks”, which instructs the reader rather than presenting information; the ER states it descriptively as “reassessing at twelve weeks” (ER line 303).

Fixes 13/08/2026 14:47

  1. 2.5 / 2.6 / 2.9 — Imperative in protocol sub-cell: Changed action_1_sub from “then nightly as tolerated; reassess at twelve weeks.” to “then nightly as tolerated, with reassessment at twelve weeks.”, removing the direct instruction to the reader.