skillstested.com
All skills / Deep comparison

hallmark vs kill-ai-slop vs visual-skills: three design skills, one real page

The three most-installed design skills for Claude Code claim adjacent territory: one generates taste, one hunts slop, one briefs image models. Instead of paraphrasing their READMEs, we pointed all three at the same real target — this site's own homepage — and let each do the job it claims, by its own rules. Including the part where two of them graded us.

Tested 2026-07-25

The three contenders

Metrichallmarkkill-ai-slopvisual-skills (image)
Reponutlope/hallmarkyetone/kill-ai-slopsmixs/visual-skills
Stars17,177 as of 2026-07-25738 as of 2026-07-25108 as of 2026-07-25
Commit testedaeb42fb88cd54475d8ce8
Installnpx skills add nutlope/hallmark -a claude-code -ynpx skills add yetone/kill-ai-slop -a claude-code -ynpx skills add smixs/visual-skills -a claude-code -y
Install time4.8s fresh session incl. CLI bootstrap; 2.5s on 07-23 warm run3.3s fresh session incl. CLI bootstrap; 2.8s on 07-23 warm run3.3s fresh session incl. CLI bootstrap; installs two skills (image + video)
Payload on disk0.94MB0.12MB0.44MB
Files installed106835
SKILL.md1 file(s), 558 lines, 9802 words — English1 file(s), 120 lines, 859 words — English2 file(s), 210 lines, 2099 words — English body, Russian reference tables
Audio assets bundledno (guidance only)no (guidance only)no (guidance only)

Three different theories of what a design skill even is. hallmark is a codified design judgment — four verbs, genre rules, a version-stamped system, and the heaviest instruction file we have ever measured. kill-ai-slop is recall machinery — a runnable scanner over a 33-tell taxonomy, with a mandatory human-confirm step before anything gets fixed. visual-skills is a compiler — it turns your intent into a model-specific prompt and refuses to let the agent improvise ("each model has its own physics").

The brief (same target for all three)

One real target — this site's own homepage — put through all three skills, each doing the job it claims: hallmark audits it (its 'audit' verb, punch list only), kill-ai-slop scans it (its bundled scanner, then the human-confirm step its workflow demands), and visual-skills writes the social-card image brief for it (its 'image' skill, mandatory reading order followed).

Auditing our own homepage is the honest version of this test: we publish the findings against ourselves, including the ones that sting.

Lens one — hallmark audits the page

Per its audit verb spec: named tell, severity, one-line fix, no edits. The punch list, verbatim from our session:

MAJOR Pure black, pure white
body background is pure #ffffff (ink is #191919, not pure black); per hallmark's own genre rules this is a tell for 'editorial' but allowed for 'modern-minimal' — and the page carries no stamp or design.md, so the audit spec cannot resolve which applies
MINOR Specimen fall-through risk
one system sans + one system mono, no display voice anywhere; deliberate zero-dependency choice, but hallmark's type-pairing rules read it as defaults
MINOR Variety drift
all 15 pages share one single-column macrostructure; hallmark's diversification rule flags it absent a design.md declaring the system
MINOR Eyebrow (kicker)
two kickers site-wide, both information-bearing (dates), not heading restatements — borderline by hallmark's own definition

0 critical · 1 major · 3 minor

The interesting failure is not on the page — it is in the spec. hallmark's severity rules are genre-scoped (a pure-white background is a tell for "editorial" but allowed for "modern-minimal"), and genre comes from a stamp or a design.md. Our page has neither, so the audit's only major finding hinges on a guess the spec never licenses. That gap went straight into our suggestions to the author, below.

Lens two — kill-ai-slop scans the page

Its scanner ran over the same homepage (plus our new comparison page) in seconds. Raw output, then the human-confirm step the skill itself insists on:

slop 09 decorative strikes & highlights2 raw hits
confirm: false positive — matched a:hover{text-decoration:underline}, which is the exact state the rule's own fix line recommends ('underline for links')
slop 10 kicker above every heading6 raw hits
confirm: partially fair — the kickers are dated info, not restatements; the compare-page one is the weakest and was kept deliberately
slop 33 tasteful-terminal (mono for code only)22 raw hits
confirm: philosophy clash — the site uses mono for measured numbers, badges and kickers as a data-log aesthetic; a deliberate system choice the regex cannot see

3 groups · 30 raw hits before human confirm

This is the recall-vs-precision trade in the open: thirty raw hits, of which roughly one survives confirmation. One rule literally matches the treatment its own fix line recommends; another flags the mono-for-data aesthetic this site chose on purpose. None of that makes the scanner useless — it makes the skill's own "confirm before you fix" workflow the load-bearing step, and it is the reason the two critics disagree about the same page.

Lens three — visual-skills briefs the image

visual-skills is the odd one out: it is not a critic and it never touches your page. Asked for this page's social-card image, it forces a reading order first (its own SKILL.md admits that shortcutting it "produced lazy, generic results"), routes the job to a model by table, and emits a structured brief:

OUTPUTGPT IMAGE 2
Settings
quality: high · 1200×630 (og:image)
Prompt (5-slot)
Scene: flat warm-white studio backdrop, no environment, no props. Subject: typographic social card for a software test log — headline 'Claude Code skills, actually tested' in a heavy grotesk, small wordmark 'skillstested.com' above it with a green checked square. Important Details: single accent green #106b34, ink near-black #191919, generous margins, flat color, no gradients, no shadows, tabular numerals if any digits appear. Use Case: og:image for a developer documentation site. Constraints: EXACT TEXT only as quoted — no extra words, no duplicate text, no watermark, no icons besides the one checked square, no gradients.
Routing
routing per its models.md table: brand typography + exact small text → GPT Image 2 over Nano Banana; syntax follows its 5-slot template with the anti-slop constraint slot filled

That is the entire deliverable — a prompt, not an image — and the discipline is the point: the model choice, the quality lever, and the constraints slot all came from rules we could trace to a specific reference file.

The same page, three verdicts

Metrichallmarkkill-ai-slopvisual-skills (image)
Role on the same pageCritic with judgment (audit verb: tell / where / severity / fix, no edits)Critic with regexes (scanner output, then human confirm)Not a critic — produced the page's social-card brief
Raw output on our homepage0 critical · 1 major · 3 minor3 slop groups, 30 raw hits in seconds1 ready-to-use brief: GPT Image 2, quality high, 1200×630, 5-slot prompt
After the human-confirm step each skill demands1 major stands only if the page is 'editorial' genre — the audit spec has no rule for un-stamped pages, so severity hinges on a guess~1 hit survives; the other groups are deliberate design-system choices (mono for data) and one rule matching its own recommended fixn/a — output is the deliverable itself
Cost profileFull model pass + on-demand reference loads (9,802-word body)Seconds of node, zero model cost for recall; model cost only at confirm/fixOne model pass after a forced two-file read
Where it breaks downNo mechanical layer: regressions between audits cost a full re-auditNo judgment: philosophy clashes and self-matches ship as 'hits'Russian-first decision tables gate the core logic for EN users

A note on the star counts

SkillStar readings (GitHub UI/API, dated)
hallmark15,794 (2026-07-23) → 17,177 (2026-07-25)
kill-ai-slop683 (2026-07-22) → 708 (2026-07-23) → 738 (2026-07-25)
visual-skills (image)103 (2026-07-23) → 108 (2026-07-25)

All three moved up between our install tests and this comparison — no anomalies this time (unlike the video pair). Dated readings as always; we measure installs, not stars.

What we would fix upstream

Same protocol as our first deep comparison: evidence-backed suggestions, headed for each author's repo — links will land here once the issues are up.

To hallmark

1. Define genre resolution for un-stamped pages

The audit verb's severity rules are genre-scoped (pure-white paper: tell for editorial, allowed for modern-minimal), and genre comes from the page's stamp or design.md — but for a page with neither, the spec is silent. Our audit's only major finding flips severity depending on a guess the spec doesn't license.

2. Ship a mechanical recall layer

kill-ai-slop's scanner produced 30 dated, line-numbered hits in seconds at zero model cost; hallmark's audit needs a full model pass every time. A small scan script over the anti-pattern list's mechanical subset (transition-all, hover:scale-105, bg-clip-text) would catch regressions between audits cheaply.

3. Trim non-instruction content from the skill body

The 558-line SKILL.md every agent loads includes marketing lines ('Powered by Together AI') that carry no instruction; at 9,802 words this is the heaviest instruction file we have measured, and every non-directive line is paid for on every activation.

To kill-ai-slop

1. Fix rule 09 matching its own recommended fix

The rule's fix line says 'strike for edits, underline for links', yet the regex flags a:hover{text-decoration:underline} — the exact recommended link treatment. Reproduced on two pages of ours.

2. Add an exemption channel for declared design systems

Rule 33 (mono for code only) returned 22 hits on our deliberate data-log aesthetic — mono for measured numbers and badges. A config allow-list or a documented exemption comment would separate philosophy clashes from real hits without weakening recall.

3. Exclude test fixtures by default

Run without arguments, scan.mjs scans its own install directory and reports its test file's fixtures as live slop (hits for rules 01 and 02 from scan.test.mjs). Default-excluding *.test.* and the script's own directory would stop the self-match.

To visual-skills

1. Publish English mirrors of the decision tables

The routing logic that the skill hard-requires reading first (models.md model-selection tables) is written in Russian, as are the README usage examples — while the install path and skill descriptions target the English skills-CLI ecosystem. This is the single biggest adoption barrier we hit.

2. Document the one-line install

README only documents manual cp, but npx skills add smixs/visual-skills works and lands both skills (verified 07-23 and 07-25). One line in the README would align it with how the ecosystem actually installs.

3. Enforce the mandatory reading order mechanically

The skill's own body says shortcut prompting 'produced lazy, generic results' and relies on agent discipline to read models.md first; a checklist token the agent must echo (or a hash the output must cite) would turn the strongest design idea in this pack from a plea into a contract.

Verdict: which one, when

Building something new? hallmark, and nothing else comes close: it is the only one of the three that can generate a design, and its stamp system is the strongest anti-drift mechanism we have seen in any skill. Budget the context weight and declare a genre so its audit can actually grade you later.

Inheriting a vibe-coded mess? kill-ai-slop first — the scanner gives you a line-numbered map in seconds for free — but treat every hit as a question, not a sentence. Its own workflow says exactly that; the trouble starts when people skip the confirm step.

Need imagery for the page? visual-skills, with a Russian dictionary or a translator handy for the decision tables. It is the smallest, most disciplined skill of the three and the only one whose output you can paste straight into another tool.

All three together is the actual answer for a real project: hallmark to design, kill-ai-slop to police regressions mechanically, visual-skills to brief the artwork. They overlap on exactly one square — judging an existing page — and that is the square where they disagree, for reasons this page just showed you.

All three packages were previously install-tested on this site: the design skills roundup covers hallmark, kill-ai-slop and visual-skills individually, and kill-ai-slop has a dedicated test page. Method and environment disclosure: how we test.