port-page
Probe source and target stacks/conventions, write a port plan, then faithfully port a page with function, style, and responsive parity.
Skill by Alfred-Lau
Chalk Labs
Need help deploying port-page?
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/alfred-lau-port-page
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: writing
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/port-page
What's inside
- Skill name
port-page- Description
- Probe source and target stacks/conventions, write a port plan, then faithfully port a page with function, style, and responsive parity.
- License
- MIT
- Instructions
- 78 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- parity-checklist.md
- plan-template.md
- probe.md
SKILL.md (first lines)
# Port Page **Faithful port** of one page from a source project into a target project. Source owns *what the page does and how it should feel*; target owns *how it is built*. Not a redesign. Not a blind copy-paste. Probe → plan → port → parity. ## Inputs Lock these before probing (ask once if missing): | Input | Examples | | --- | --- | | **Source** | path in another repo, monorepo package, or live URL + route | | **Target** | repo root (default: cwd) + destination route / page slug | | **Scope** | one page (default). Multi-page → one page per invocation | ## Process ### 1. Probe both sides Load [probe.md](./probe.md). Probe **source** and **target** independently, then diff. Capture at minimum: - Tech stack (framework, language, package manager, styling system, routing) - Code conventions (file layout, components, naming, state/data patterns, lint/format) - Design system signals (tokens, primitives, breakpoints, motion) - The source page's sections, interactions, and responsive behaviour **Completion criterion:** both probes filled; gaps and conflicts listed — no code written yet. ### 2. Write the port plan Create `docs/site/ports/<slug>.md` from [plan-template.md](./plan-template.md) (create `ports/` if needed). If the target has no site-docs layout, write under `.scratch/ports/<slug>.md` instead. The plan must name: - Stack/convention mapping (source construct → target idiom) - Section inventory (nothing invented, nothing dropped without an explicit defer) - Style mapping (source visual → target tokens/primitives; token additions called out) - Responsive mapping (source stacking intent → target breakpoints / verification viewports) - Risks and accepted deltas (things that cannot reach full parity) Confirm with the user only when a risk would change page job, drop an interaction, or introduce a second styling system. **Completion criterion:** an agent could port without inventing sections or guessing stack choices. ### 3. Faithful port Implement in the **target** only: - Prefer existing target routes, layouts, and primitives - Map every planned section and interaction - Extend target tokens when a needed value is missing — do not hardcode source hex/fonts into the target - Obey target `docs/agents/design-rules.md` / stack conventions when present - Preserve source **parity** intent: same jobs, same interactive outcomes, same visual hierarchy, same mobile stacking story Stop and update the port plan if reality diverges (new defer, new token, new risk). ### 4. Parity check Walk [parity-checklist.md](./parity-checklist.md). Run **`/responsive-pass`** against the plan's verification viewports (or target page-spec / `TOKENS.md` bands when those exist). **Completion criterion:** every parity item is pass, explicit defer, or open blocker; responsive failures are concrete; target build/lint for touched files succeeds when tooling exists. ### 5. Close Summarise: files changed, token additions, accepted deltas, open blockers. Recommend next: - Target follows Site Skills main flow → `/visual-qa` (or `/page-spec` first if no page-spec yet and they want the contract persisted) - More pages remain → another `/port-page` for the next slug - Unclear → `/ask-site`
From Alfred-Lau/skills, MIT.
More from Alfred-Lau/skills
- 0.547score
perf-pass
Alfred-Lau
Performance smoke pass for a page — LCP/CLS risks on fonts, images, critical path.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
responsive-pass
Alfred-Lau
Walk critical breakpoints for a page — no overflow, intact hero, readable CTA.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
design-critique
Alfred-Lau
Critique a design direction, mock, or live page against site composition hard rules and DIRECTION — before or beside code.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ui-prototype
Alfred-Lau
Build throwaway UI variants to answer one visual design question.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
a11y-pass
Alfred-Lau
Accessibility smoke pass for a page — focus order, contrast, semantics, alts.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
visual-direction
Alfred-Lau
Lock a one-composition visual thesis into DIRECTION.md — type, color, material, atmosphere, reference boundaries.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
conversion-audit
Alfred-Lau
Audit funnel friction — CTA clarity, trust, drop-off hypotheses — and produce smallest-change recommendations.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
implement-ui
Alfred-Lau
Faithfully restore a page-spec into UI code using tokens — no improvisational redesign.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
page-spec
Alfred-Lau
Turn IA and direction into a tracer page-spec with sections, copy slots, breakpoints, and acceptance checks.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
visual-qa
Alfred-Lau
Diff built UI against page-spec and direction; grade findings blocker / major / nit.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
information-arch
Alfred-Lau
Shape the sitemap and per-page jobs — hero budget and one job per section — into IA.md.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
instrument
Alfred-Lau
Write a tracking plan and land the events — named events, properties, funnel steps before growth work.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 5, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Alfred-Lau/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Alfred-Lau
- 0.547score
perf-pass
Alfred-Lau
Performance smoke pass for a page — LCP/CLS risks on fonts, images, critical path.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ui-prototype
Alfred-Lau
Build throwaway UI variants to answer one visual design question.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
responsive-pass
Alfred-Lau
Walk critical breakpoints for a page — no overflow, intact hero, readable CTA.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
a11y-pass
Alfred-Lau
Accessibility smoke pass for a page — focus order, contrast, semantics, alts.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
design-critique
Alfred-Lau
Critique a design direction, mock, or live page against site composition hard rules and DIRECTION — before or beside code.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
design-system
Alfred-Lau
Freeze tokens-first design primitives into TOKENS.md and align code CSS variables.
SkillBFreshness: B★ 1Claude 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 port-page 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
port-page skill. Agent Mart. https://agentmart.dev/skills/alfred-lau-port-page (last updated 2026-10-24)