Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
> **Step 0 — is the kit here?** This skill reads files from the kit. Check once:
> `ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING`
> On `KIT_MISSING` only the skill folders were installed, which is what
> `npx skills add` does. Say so plainly, point the user at
> `npx ux-ui-agent-skills init` or the plugin install, and stop. Do not guess the
> contents of a file you could not open.
Gate first, then prepare the release. Do nothing destructive without explicit
confirmation (no tag, no publish) — this command verifies and drafts only.
1. Quality gate (must be fully green before continuing):
- `node ${CLAUDE_SKILL_DIR}/../../../scripts/accuracy_report.mjs` — report the real N/N.
- `node ${CLAUDE_SKILL_DIR}/../../../scripts/verify_responsive.mjs examples` — no overflow at 280/320/414.
- `python3 ${CLAUDE_SKILL_DIR}/../../../scripts/check_no_emoji.py` — UI + taste + instruction surface.
If anything fails, stop and fix; do not proceed to the checklist.
2. Release checklist (per the project release rule):
- Update `README.md`: version badge, "current" line, and changelog entry.
…
The line at the top of this page pins the label git:20261006.5751441, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_2b5colvpe7hqclly
GET https://markdownregistry.com/api/v1/resolve?ref=plugin87/ux-ui-agent-skills/ship
GET https://markdownregistry.com/api/v1/blob/b0cdad9a1c9e379684b1ba60520d265f4b95578327899010c5b9a020e6600bab
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
plugin87/ux-ui-agent-skills · .claude/skills/a11y-audit/SKILL.md · Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity…
plugin87/ux-ui-agent-skills · .claude/skills/apply-aesthetic/SKILL.md · Apply a visual direction — an archetype (high-end agency, editorial minimal, brutalist, soft-SaaS, dark-tech) or one of…
plugin87/ux-ui-agent-skills · .claude/skills/critique/SKILL.md · Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates…
plugin87/ux-ui-agent-skills · .claude/skills/data-dashboard/SKILL.md · Build a dense, data-heavy screen - an analytics console or a trading terminal - with real charts drawn from tokens…
plugin87/ux-ui-agent-skills · .claude/skills/design-component/SKILL.md · Design a UI component spec to the house quality bar — anatomy, variants, sizes, the 8 states, token mapping, and…
plugin87/ux-ui-agent-skills · .claude/skills/design-doctrine/SKILL.md · The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the…
plugin87/ux-ui-agent-skills · .claude/skills/design-review/SKILL.md · Review or audit a design/UI across 6 weighted dimensions with Nielsen's 10 heuristics and a prioritized findings table…
plugin87/ux-ui-agent-skills · .claude/skills/design-screen/SKILL.md · Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this…
plugin87/ux-ui-agent-skills · .claude/skills/design-tokens/SKILL.md · Generate, extend, or audit design tokens in DTCG format with the 3-tier architecture (primitive → semantic →…
suboss87/fdeops · skills/ship/SKILL.md · Prepare or execute an authorized controlled release with verified checks, recovery and an operating owner. Use when a…
snowflake-labs/cocoplus · .cortex/skills/cocobrew/ship/SKILL.md · Enter the Ship phase of CocoBrew. Reads review.md approval, generates structured commit, creates semantic version tag…
tobihagemann/turbo · claude/skills/ship/SKILL.md · Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship"…
tobihagemann/turbo · codex/skills/ship/SKILL.md · Commit, push, and optionally create or update a PR for the current staged changes. Use when the user asks to "ship"…
luongnv89/skills · skills/ship/SKILL.md · Run a release end to end, autonomous by default: version bump everywhere, changelog, docs, landing page, tag, push…
ilang-ai/autocode · skills/ship/SKILL.md · S6 of see-it-ship-it: put it at a public URL. Secret scan first; static builds go to GitHub Pages at no cost (sign-up…
