Unify every version string: skill frontmatter and preview block, package.json,
the four preview-examples samples, the eval direction note, the ROADMAP opener,
and the site badges/captions (which were still stamped v1.1/v1.3). The PR is
retitled to match and sits as a draft on the renamed v1.2 branch.
Hallmark stops targeting open-weight models and goes deep on the three
terminals where design work happens: Claude Code, Codex CLI, and OpenCode.
Same core everywhere (SKILL.md standard), plus a per-harness adapter each
harness loads before Step 0.
- references/harnesses/codex.md: $hallmark invocation, workspace-write
sandbox + network-off reality (picker server asks first, --static
fallback), no hooks/subagents (sequential variants + progressive reveal),
AGENTS.md as a Step 0 signal, batch-per-direction patches
- references/harnesses/opencode.md: /hallmark + skill-tool invocation,
allow/ask/deny permission model, parallel variants via its subagents,
formatter/LSP interplay, compatibility-path discovery
- references/models.md deleted; its harness-agnostic rules live on in both
adapters. SKILL.md dispatch now routes by harness, not by model family
- agents/openai.yaml: Codex interface + implicit-invocation policy
- scripts/install.mjs: detects installed harnesses and installs a lean
1.5MB payload (SKILL.md, references, scripts, agents, LICENSE - never
site/ or eval/) to ~/.claude/skills, ~/.agents/skills (+ refreshes the
stale legacy ~/.codex/skills copy), and leaves OpenCode to its
compatibility discovery; --dry-run / --remove / idempotent
- README: 'Open models' section replaced by 'One skill, three harnesses'
with the install matrix; ROADMAP and eval/README reframed (Tier B kept
as archive only); version 1.4.0
Ran the installer live: all three locations now serve 1.4.0 with the
adapters in place (the Codex location previously held a 27MB v1.0.0 copy).
Skill and package to 1.3.0; preview-example version strings to v1.3.0;
README variants section rewritten for v2 (progressive reveal, parallel +
sketch-default, thumbnails, compositional grafts, section-zoom, scoped
injection); ROADMAP marks the five v1.3 items shipped.
Replace the carousel's inconsistent scroll-videos with one CSS image hover-scroll
across all twelve cards. Each thumb is a tall full-page screenshot that pans top
to bottom on hover, with a per-card duration scaled to page height so they all
move at the same brisk, readable pace; captured Retina-sharp at 1400px wide.
Touch and reduced-motion get a static crop. Drop the Slow Pour card.
Bump the version to v1.1 on the landing (banner + footer), package.json, SKILL.md,
and the preview-block examples.
The skills CLI copies everything under the directory containing SKILL.md.
With SKILL.md at the repo root, installs were pulling in docs/, site/,
package.json, README, ROADMAP, vercel.json, LICENSE. Moving the skill
into skills/hallmark/ scopes the install to just SKILL.md + references/.
The CLI's priority search hits skills/ first, so `npx skills add
nutlope/hallmark` is unchanged. Updated README install paths,
package.json (entry/references/files), and the internal links that
crossed the new boundary.
The published install command in the README — npx skills add nutlope/hallmark — was failing for users because the skills CLI looks for SKILL.md at the repo root, not at skill/SKILL.md where Hallmark kept it. The clone succeeded but the CLI reported "No skills found." Manual cp was the only working install path.
Flattened the layout:
- skill/SKILL.md → SKILL.md
- skill/references/ → references/
- (skill/ directory removed; was empty after moves)
git mv preserved rename history for all 76+ files (SKILL.md + 28 reference files + 21 macrostructures + 46 components + 7 verb/genre subfolders).
Updated every cross-reference (36 occurrences across 9 files):
- README.md — 4 links (SKILL.md + references/ + the install snippet still reads the same)
- ROADMAP.md — 4 links to reference files
- package.json — "files" field + "skill" entry/references paths
- site/js/main.js — 3 source comments
- references/design-md.md — one broken link (was pointing skill/references/export-formats.md from inside references/ — now just export-formats.md as a sibling)
- site/_tests/verbs/study/notes.md, diagnosis.md and verbs/audit/audit-report.md, custom/README.md — test-artifact relative paths shortened by one segment (e.g. ../../../skill/SKILL.md → ../../../SKILL.md)
No skill content changes. After this lands, 'npx skills add nutlope/hallmark' should clone + install correctly without any manual cp fallback.
Section 03 ships as the five-skills showcase (Build · Study · Audit ·
Refine · Redesign), each row with its own structurally-distinct demo.
SKILL.md and references — new disciplines that hold across every verb:
· Pre-emit self-critique on six axes (Philosophy · Hierarchy · Execution
· Specificity · Restraint · Variety) — anything <3 triggers revision
· Honest copy — no fabricated metrics, real numbers or labelled
placeholder, never invent "+47% conversion"
· Locked tokens — no mid-render colour or font-family improvisation
· Re-drawn UI chrome forbidden — never hand-build fake browser bars,
phone frames, code-block windows, IDE chrome
· Clickable text never wraps to two lines on shrink
Slop test grows from 55 to 60 gates (gates 56–60). Pre-emit critique
block sits above the gate sweep. anti-patterns.md gains five new named
entries; responsive.md gains "Clickable text — never wraps" with the
4-step fix order.
Site:
· Studio photographic hero — empty 3x3 placeholder grid replaced with
a 3x2 showcase of six real Hallmark output thumbnails (Static Hour,
NAJM, Tally hero, Nexus, Tracejam, Tally process)
· Studio — strip "· selected work" suffix from section labels
(::after rule removed) and from hero eyebrow COPY
· FAQ section dropped from landing page · CSS removed · Install
renumbered 07 → 06, footer reveal index 7 → 6
· Section 03 Row I (Build) demo swaps Tide → Static Hour
· README — concise intro paragraph, hero showcase swapped to four
new outputs (Static Hour, NAJM, Tally hero, Nexus)
Version bumped to 1.0.0 across package.json, SKILL.md, banner, footer,
JS captions, and the artifact stamp string.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Anti-AI-slop design skill for Claude Code, Cursor, and Codex,
plus a self-demonstrating landing page powered by Together AI.
- 4 verbs: default / audit / refine / redesign
- 10 reference files including microinteractions and structure
- 12 themes with structural fingerprints
- Two test specimens: bakery (editorial) and cmdk (technical)
- 20-question slop test covering visual, structural, and microinteraction tells
Youssef