plan-design-review
Review a product or feature plan from a design perspective before implementation.
Skill by sdntsng
Chalk Labs
Need help deploying plan-design-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sdntsng-plan-design-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/plan-design-review
What's inside
- Skill name
plan-design-review- Description
- Review a product or feature plan from a design perspective before implementation. Use when a plan needs clearer UX decisions, better interaction-state coverage, stronger hierarchy, more intentional responsiveness, or protection against generic AI-generated design choices.
- License
- MIT
- Instructions
- 41 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Plan Design Review Use this skill before implementation when the design is still in the plan, not yet in the UI. ## Workflow 1. Read the plan or feature brief. 2. Identify missing design decisions. - screen hierarchy - primary actions - loading, error, empty, and success states - mobile and desktop behavior - accessibility expectations 3. Check whether the plan is specific enough to implement without improvising weak UI. 4. Improve the plan. - add missing state coverage - sharpen information hierarchy - remove generic or lazy design language - define the important interactions explicitly 5. End with a design-ready verdict. ## What this skill should catch - "clean modern UI" with no actual design choices - missing empty, error, or loading states - no responsive intent beyond stacking things on mobile - unclear content hierarchy - generic card-grid thinking where the product needs more intent - plans that assume polish will happen later ## Output expectations Return: - design quality summary of the plan - missing decisions - recommended changes - revised design guidance ready for implementation ## Guardrails - Do not implement the UI here. - The goal is a better plan, not a design essay. - Be specific enough that an engineer or designer could build from it without guessing.
From sdntsng/codex-gstack, MIT.
More from sdntsng/codex-gstack
- 0.409score
browser-dogfood
sdntsng
Run real browser-based product testing with Codex browser tools.
SkillDFreshness: DClaude Code +9 - 0.409score
codex-gstack-upgrade
sdntsng
Upgrade or refresh a local codex-gstack installation when the skill pack has changed upstream.
SkillDFreshness: DClaude Code +9 - 0.409score
design-consultation
sdntsng
Define upfront product design direction before implementation.
SkillDFreshness: DClaude Code +9 - 0.409score
design-review-live
sdntsng
Audit a live or implemented UI for visual quality, UX clarity, and product feel.
SkillDFreshness: DClaude Code +9 - 0.409score
doc-sync-after-change
sdntsng
Update project documentation after code changes using the actual diff as the source of truth.
SkillDFreshness: DClaude Code +9 - 0.409score
office-hours
sdntsng
Reframe a product or startup idea before implementation.
SkillDFreshness: DClaude Code +9 - 0.409score
plan-ceo-review
sdntsng
Review a product plan from a founder or CEO perspective.
SkillDFreshness: DClaude Code +9 - 0.409score
plan-eng-review
sdntsng
Turn an idea or product plan into a buildable technical plan.
SkillDFreshness: DClaude Code +9 - 0.409score
pr-preflight-review
sdntsng
Review the current branch before push or PR creation.
SkillDFreshness: DClaude Code +9 - 0.409score
project-retro
sdntsng
Summarize recent execution and derive practical next-step improvements from commits, diffs, and recent work patterns.
SkillDFreshness: DClaude Code +9 - 0.409score
setup-browser-cookies
sdntsng
Prepare browser-based QA against authenticated pages by reusing an existing logged-in browser session or importing cookies into the testing context.
SkillDFreshness: DClaude Code +9 - 0.409score
ship
sdntsng
Prepare a branch for release or handoff with disciplined final checks.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 19, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sdntsng/codex-gstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sdntsng
- 0.409score
codex-gstack-upgrade
sdntsng
Upgrade or refresh a local codex-gstack installation when the skill pack has changed upstream.
SkillDFreshness: DClaude Code +9 - 0.409score
design-consultation
sdntsng
Define upfront product design direction before implementation.
SkillDFreshness: DClaude Code +9 - 0.409score
design-review-live
sdntsng
Audit a live or implemented UI for visual quality, UX clarity, and product feel.
SkillDFreshness: DClaude Code +9 - 0.409score
doc-sync-after-change
sdntsng
Update project documentation after code changes using the actual diff as the source of truth.
SkillDFreshness: DClaude Code +9 - 0.409score
office-hours
sdntsng
Reframe a product or startup idea before implementation.
SkillDFreshness: DClaude Code +9 - 0.409score
browser-dogfood
sdntsng
Run real browser-based product testing with Codex browser tools.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get plan-design-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
plan-design-review skill. Agent Mart. https://agentmart.dev/skills/sdntsng-plan-design-review (last updated 2026-10-24)