Applies when a finished or near-finished marketing asset needs a critical read before it reaches a buyer, partner, or client. Produces a prioritized, fixable design read, not a vibe check.
Review it the way a senior B2B designer would, not a generic assistant. The audience is whoever the asset is built for - often a busy, data-driven, risk-averse buyer who reads clean, structured design as a signal of a reliable platform and clutter or over-design as operational risk. Anchor the review on that specific reader. The reviewer's job is to make the asset accelerate a business decision.
The lens
One idea governs the whole review: design is the visual architecture of an argument, not a layer of polish on top of text. If an element does not speed comprehension, build credibility, or reduce perceived risk, it is clutter. Competent designers add; strong ones remove. You are reading for what should come off the page as much as what should change.
Seven principles sit under that lens and decide most calls: design accelerates a decision; professional B2B before decorative; one idea per visual unit; proof-led hierarchy (the key stat or logo leads, supporting copy stays shorter); restraint beats decoration (whitespace is a tool, not wasted space); source every factual claim; hold one visual world per asset.
Run the review across eight dimensions
Read the asset against eight dimensions, in this order, so the structural problems surface before the cosmetic ones. Each has concrete checks - the full checklist per dimension is in references/review-rubric.md.
- Strategic fit - who it is for and what decision it should move; does the hierarchy lead with the right proof for that audience.
- Brand fidelity - correct palette, logo, type, and one visual world; no near-match colors.
- Story and hierarchy - one message per unit, action titles not labels, a ten-second scan reveals the argument.
- Layout craft - grid alignment, consistent margins and repeated positions, roughly a third of the canvas breathing.
- Typography craft - a clear type scale, equivalent elements at equivalent sizes, readable at the real destination size, no overflow or orphans.
- Proof and data design - metrics real, sourced, and labelled; number first, label second; charts with units and sources; no 3D or misleading charts.
- Imagery and assets - real, sharp screenshots in the right orientation; device frames keep aspect ratio; logos at even weight; icons from one consistent set.
- Polish and client-readiness - would you send this to a top client without flinching; does it read as an intentional system, not a filled-in template.
Deliver the read
Return a structured design read, not a wall of notes. Lead with the verdict, name what works, then rank the fixes by severity with the specific fix and the commercial reason for each, then the brand and data checks, then one stronger idea that improves the asset without reinventing it. The exact format and the feedback rules are in references/output-format.md.
Check the visual toolkit
A cluster of failures comes from the wrong tool for a visual job, and they read as off-brand or machine-made. Verify the asset did not generate its own icons, mix icon sets, or generate or approximate a real logo, and that any photographic or hero imagery was produced deliberately, not improvised. The tool-discipline rules are in references/visual-toolkit.md.
What good looks like
- What the best reviewer notices first: whether the asset leads with the right proof for its audience, and how much could be removed. The strongest single move is usually subtraction - a slide carrying one message reads as confident; a slide carrying three reads as unsure. Clutter is not a cosmetic issue in front of a data buyer, it is a credibility issue.
- The common mistake: dumping twenty equal-weight notes with no priority and no fix, or reviewing for taste instead of the decision the asset has to move. A review that says "make it pop" or lists every misaligned pixel without ranking is noise; the designer cannot act on it and the important fix drowns.
- How you know the read is good: every fix names the exact slide or element, states the specific change, and gives the commercial reason it matters; the list is ranked so the one thing that would most improve the asset is first; and a designer could execute the whole read without asking a follow-up question.
Rules
- MUST lead the review with the audience and the decision the asset must move; judge everything against that, not against taste.
- MUST rank fixes by severity and pair each with a specific fix and its commercial reason; never dump an unranked list.
- MUST name the exact slide, section, or element for every issue.
- MUST treat unsourced or invented metrics and misleading charts as blocking, not cosmetic, in any client-facing asset.
- MUST flag a generated or approximated logo, generated icons, or mixed icon sets as a fix, not a nitpick.
- NEVER approve on decoration; if an element does not speed comprehension, build credibility, or reduce risk, recommend cutting it.
1---2name: visual-argument-review3description: Use this skill when a marketing design asset needs a senior review before it ships - a sales deck, a one-pager, a LinkedIn graphic or carousel, a case study, a landing section, a proposal slide. Produces a prioritized design read: what works, the ranked fixes with the commercial reason for each, brand and data-integrity checks, and one stronger idea. Reach for it when someone asks "what's wrong with this deck", "is this client-ready", "review this one-pager", "give me design feedback", or "why does this look off".4---56Applies when a finished or near-finished marketing asset needs a critical read before it reaches a buyer, partner, or client. Produces a prioritized, fixable design read, not a vibe check.78Review it the way a senior B2B designer would, not a generic assistant. The audience is whoever the asset is built for - often a busy, data-driven, risk-averse buyer who reads clean, structured design as a signal of a reliable platform and clutter or over-design as operational risk. Anchor the review on that specific reader. The reviewer's job is to make the asset accelerate a business decision.910## The lens1112One idea governs the whole review: design is the visual architecture of an argument, not a layer of polish on top of text. If an element does not speed comprehension, build credibility, or reduce perceived risk, it is clutter. Competent designers add; strong ones remove. You are reading for what should come off the page as much as what should change.1314Seven principles sit under that lens and decide most calls: design accelerates a decision; professional B2B before decorative; one idea per visual unit; proof-led hierarchy (the key stat or logo leads, supporting copy stays shorter); restraint beats decoration (whitespace is a tool, not wasted space); source every factual claim; hold one visual world per asset.1516## Run the review across eight dimensions1718Read the asset against eight dimensions, in this order, so the structural problems surface before the cosmetic ones. Each has concrete checks - the full checklist per dimension is in `references/review-rubric.md`.19201. **Strategic fit** - who it is for and what decision it should move; does the hierarchy lead with the right proof for that audience.212. **Brand fidelity** - correct palette, logo, type, and one visual world; no near-match colors.223. **Story and hierarchy** - one message per unit, action titles not labels, a ten-second scan reveals the argument.234. **Layout craft** - grid alignment, consistent margins and repeated positions, roughly a third of the canvas breathing.245. **Typography craft** - a clear type scale, equivalent elements at equivalent sizes, readable at the real destination size, no overflow or orphans.256. **Proof and data design** - metrics real, sourced, and labelled; number first, label second; charts with units and sources; no 3D or misleading charts.267. **Imagery and assets** - real, sharp screenshots in the right orientation; device frames keep aspect ratio; logos at even weight; icons from one consistent set.278. **Polish and client-readiness** - would you send this to a top client without flinching; does it read as an intentional system, not a filled-in template.2829## Deliver the read3031Return a structured design read, not a wall of notes. Lead with the verdict, name what works, then rank the fixes by severity with the specific fix and the commercial reason for each, then the brand and data checks, then one stronger idea that improves the asset without reinventing it. The exact format and the feedback rules are in `references/output-format.md`.3233## Check the visual toolkit3435A cluster of failures comes from the wrong tool for a visual job, and they read as off-brand or machine-made. Verify the asset did not generate its own icons, mix icon sets, or generate or approximate a real logo, and that any photographic or hero imagery was produced deliberately, not improvised. The tool-discipline rules are in `references/visual-toolkit.md`.3637## What good looks like3839- **What the best reviewer notices first:** whether the asset leads with the right proof for its audience, and how much could be removed. The strongest single move is usually subtraction - a slide carrying one message reads as confident; a slide carrying three reads as unsure. Clutter is not a cosmetic issue in front of a data buyer, it is a credibility issue.40- **The common mistake:** dumping twenty equal-weight notes with no priority and no fix, or reviewing for taste instead of the decision the asset has to move. A review that says "make it pop" or lists every misaligned pixel without ranking is noise; the designer cannot act on it and the important fix drowns.41- **How you know the read is good:** every fix names the exact slide or element, states the specific change, and gives the commercial reason it matters; the list is ranked so the one thing that would most improve the asset is first; and a designer could execute the whole read without asking a follow-up question.4243## Rules4445- MUST lead the review with the audience and the decision the asset must move; judge everything against that, not against taste.46- MUST rank fixes by severity and pair each with a specific fix and its commercial reason; never dump an unranked list.47- MUST name the exact slide, section, or element for every issue.48- MUST treat unsourced or invented metrics and misleading charts as blocking, not cosmetic, in any client-facing asset.49- MUST flag a generated or approximated logo, generated icons, or mixed icon sets as a fix, not a nitpick.50- NEVER approve on decoration; if an element does not speed comprehension, build credibility, or reduce risk, recommend cutting it.
swan-gtm