Audit: QRS - Tazarotene for Skin Rejuvenation

Audit conducted on 14/09/2026 10:40 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	84
Failed	0
N/A	9
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.	🟢	Every span traces to ER text: at-a-glance to Conclusion, protocol cells to Therapeutic Protocol, time cells to the Practical Considerations “Time to effect” bullet, tiers to Expected Benefits / Potential Risks & Side Effects, gates to Key Interactions & Contraindications, markers and cadence to Monitoring Protocol & Defining Success.
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_4_target retains the ER’s “No established target”; time_1_sub retains “not yet plateaued”.
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 is carried as an absolute bar in both the at-a-glance (“use in pregnancy is ruled out”) and stop_items, matching ER lines 246–248 and 308.
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.	🟢	No content from Benefit-Modifying Factors, Risk-Modifying Factors, or Risk Mitigation Strategies appears in the gates or risk tiers.
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.	🟢	No PMIDs, URLs, NCT IDs, or expert names present. All named drugs in caution_items are taken from the same ER interaction bullets.
1.6	The QRS does not introduce new attributions.	🟢	No attributions anywhere in the sheet.

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.	🟢	Phrasing mirrors the ER’s measured, non-promotional register.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Benefit and risk tiers are stated flatly; the protocol panel gives concrete, actionable figures.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is presented as facts and conditions, not instructions.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	Contraindications and interactions are noun phrases naming conditions, not directives.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No “recommended”, “should”, or “advised” anywhere in the document.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns present.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms are confined to ER-verbatim biomarker and benefit labels required by items 4.2/4.3; the at-a-glance is jargon-free.
2.8	Information is presented in a concise and very compact manner	🟢	All tier items are single lines of semicolon-separated key facts; gate items carry no rationale.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by scan for “you”/”your”.
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.	🟢	Monitoring cadence, biomarker targets, and titration framing assume a reader who will execute a protocol.
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.	🟢	Daily evening application, sun protection, and a weekly local-reaction score are presented without hedging about burden.
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.	🟢	Content assumes prescription access, lab testing, and graded self-assessment.
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.	🟢	The at-a-glance states the irritation trade-off plainly rather than discouraging use.
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.
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)”; “oral” / “administered orally” not “taken by mouth” / “given by mouth”; “injection” not “shot”; “adverse event” not “bad reaction”). This holds on EVERY surface, including the QRS lede — the stricter plain-language bar (see 2.7) does not license lay phrasing for route of administration.	🟢	The lede names the formulation and route formally (“prescription vitamin A cream applied to the face each evening”); no colloquial route terms occur.

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 fixed headings verified verbatim at lines 446, 490, 534, 567, 580, 600, 624, 628–630, 703 and in the tier <strong> labels.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 38 distinct template variables present (marker_#* expanded to 5 rows, qualitative_item# to 5 items); the three <span website="..."> hooks also retained at lines 423, 426, 440.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Diff of lines 16–410 against the template shows the head, full style block, and override stylesheet link byte-identical; footer disclaimer unchanged.

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 ER section mapped into the QRS is empty. The empty Medium risk tier is governed by item 13.5, which mandates display:none rather than empty-state phrasing.
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.	🟢	action_1/2/3_label reproduce the ER bold labels “Standard regimen”, “Best time of day”, “Short-contact approach” verbatim; monitoring marker names reproduce the ER biomarker-table labels verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Protocol and marker labels are ER-verbatim. Time-to-effect cell labels are structurally required by section 11 and are drawn from the single ER “Time to effect” bullet.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Scan returns no emoji code points; the ER’s ⭕️ and ⚠️ markers on benefit/risk headings were stripped.
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.	🟢	Every section is condensed against its ER source: 14 protocol bullets → 3 cells, 8 benefit headings → 4 tier lines, 7 risk headings → 3 tier lines, gate items stripped to label plus qualifiers, monitoring “why” and qualitative trailing clauses trimmed. Total visible text is 625 words.

---

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 template’s own “blank template” comment follows at line 16.
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 “—” at line 3, closing “—” at line 13.
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 before <html>; no duplicate rendering.
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: "00:03" is quoted, correctly, because it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: tazarotene_skin_2026-0914-0820_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: qrs_prompt_version: 26.9.11, 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: 2026-0914-1032.
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” is a single word with no version.
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, no context-window or other qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the actual file 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 nine keys including git_user and git_issue.

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., & for &)	🟢	Line 22: “Tazarotene for Skin Rejuvenation - Quick Reference Sheet”; no characters require entity encoding.
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢	Line 417: “Tazarotene for Skin Rejuvenation”, matching ER frontmatter canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: 09/14/2026, correctly derived from 2026-0914-1032.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”.
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢	Header contains only title and the template subline; the ER’s “Also known as” line was not carried over.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Condenses ER lines 462–464: what it is, how it is applied, what changes, and the tolerability and pregnancy trade-off.
7.2	[at_a_glance] is no longer than 60 words	🟢	54 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to a distinct sentence of the ER Conclusion (lines 462 and 464) plus the pregnancy bar at line 308.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	Uses “brown mottling”, “rough texture”, “peeling, dryness, redness, burning”; no acronyms, no retinoid-class or receptor terminology.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	Refers only to “several large placebo-controlled trials” with no identifying detail.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No percentages, odds ratios, or P values present.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	Derived from the “Populations who should avoid Tazarotene” list at ER lines 306–313.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All six ER avoidance populations are present, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Six <li> elements at lines 570–575.
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.	🟢	The ER’s “Anyone with”/”Women who are” stems and the “(a condition in which sunlight triggers disease)” gloss are dropped; no dashes or trailing clauses remain.
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).	🟢	Retains “within the current cycle”, “within 14 days of starting”, “on or near the chest”, “until fully healed”, “above roughly two hours daily”, and “(lupus, inherited light-sensitivity syndrome)”.
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 uses no ranking notation in this section.
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 six such populations and the section is correctly 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	🟢	Derived from ER lines 290–304.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All eight ER interaction bullets present; no overlap with the six stop_items.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Eight <li> elements at lines 583–590.
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.	🟢	Each item is the ER bold label plus its parenthetical examples; the “Caution.” verdicts and all management sentences are stripped.
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).	🟢	Every ER example drug list is carried intact, e.g. “(doxycycline, minocycline, ciprofloxacin, hydrochlorothiazide, amiodarone)” and “(chemical peels, microdermabrasion, fractional laser resurfacing, waxing, electrolysis)”.
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 uses no ranking notation in this section.
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 eight interactions and the section is correctly 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 map to bullets in the ER Therapeutic Protocol section (lines 337, 341, 349).
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	“Standard regimen” (the approval-defining regimen), “Best time of day”, and “Short-contact approach” (the tolerability alternative) are the three most execution-relevant of the fourteen ER bullets.
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 fourteen protocol bullets; 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.	🟢	All nine spans populated; values (“0.1% cream nightly”, “Evening”, “20–30 min, then washed off”) and subs all trace to ER lines 337, 341, 349.

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	🟢	Covers all three timings the ER gives at line 396: week 2 separation, week 4 self-noticed change, and the 12–24 week / 52 week grade trajectory.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Set 1 carries the largest quantified benefit (wrinkling and pigment, 45-percentage-point treatment-success gap at ER line 154); the remaining two relate to endpoints the ER reports as direction-only.
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	The ER supplies three distinct time-to-effect aspects; 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.	🟢	All nine spans populated; “12–24 weeks”, “Week 4”, “Week 2” and their subs match ER lines 396, 164 and 368.
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 provides time-to-effect information, so the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All four tier lines reproduce the ER Expected Benefits H4 headings under their matching tier.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four present at lines 536, 543, 549, 555.
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 tier is a semicolon-separated list of ER benefit headings; all magnitude paragraphs, funding caveats, and mechanism text are omitted.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	The ER’s parenthetical glosses (e.g. “(flat brown spots left by sun exposure)”, “(the yellowed, thickened, leathery change…)”) do not appear.
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 benefit tiers carry items in the ER, so no span needs hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	Tier lines reproduce the ER risk H4 headings under their matching tier.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four present at lines 602, 605, 606, 613.
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.	🟢	“Local retinoid irritation” alone at High; frequency bands (29%, 27%, 21%, 14%), the 7.1% discontinuation figure, and all “Net reading” commentary are omitted.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	ER glosses such as “(skin peeling)”, “(redness)”, “(sunlight-triggered chemical burn)” are absent.
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.	🟢	The ER states “No risk reaches Medium” (line 236); line 605 is <span data-qrs-var="risks_medium" style="display: none"></span> with no empty-state text.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Derived from the ER Monitoring Protocol & Defining Success biomarker table at lines 426–432.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All five ER biomarkers present with their ER-verbatim names and optimal ranges (Negative; 70–100 mg/dL; 40–60 ng/mL; one-grade fall by week 24; 1 or below after week 4).
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 693 reproduces the ER cadence paragraph at line 424: weekly for 4 weeks, 12/24 weeks then 6-monthly, triglycerides and vitamin D at 6 months then annually.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Derived from the ER’s “Qualitative markers worth tracking” list at lines 436–440.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All five ER qualitative markers present at lines 706, 711, 717, 722, 727, with their trailing explanatory clauses trimmed.

Issues 14/09/2026 10:40

Pass rate 100.00%. No issues found.