html-communication
Use for plans, specs, write-ups, findings, summaries, reports or comparisons presented as readable HTML; use for UI mocks when the user explicitly asks to…
Skill by AmitRockBear
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/amitrockbear-html-communication
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, frontend, 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/html-communication
What's inside
- Skill name
html-communication- Description
- Use for plans, specs, write-ups, findings, summaries, reports or comparisons presented as readable HTML; use for UI mocks when the user explicitly asks to approve them before implementation. Do not use for HTML that ships as part of a product.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Guidelines for non UI Mocks Write for a reader with fresh context, using plain language and only sections relevant to the task. Use consistent names across prose, examples and diagrams. Explain consequences concretely, using real symbols and values where relevant. 1. Lead with the problem, outcome, one short end-to-end example and core decisions; put detailed file/schema accounting afterward. Distinguish agreed decisions, recommendations and open questions. 2. Explain changes with one concrete scenario and labeled Before/After diagrams. For complex flows, start with the visible effect and introduce one component at a time in small diagrams before explaining symbols, storage details and exceptions. When comparing approaches, illustrate each meaningful alternative. 3. For implementation plans, cover scope, relevant components and data contracts, implementation order, and a short Verification section with concrete actions and expected observable results. 4. When decisions change, reconcile all affected prose, diagrams, and values into one current plan. Keep every section consistent with the latest agreed design. Create one self-contained HTML file, capped at 512 KB. - Use a compact spec layout: a centered reading column, short sections, system fonts, and minimal CSS. Place Before/After diagrams side by side on wide screens and stack them on mobile. Use tables for comparisons. - Use palette: background `#1f1a24`, surfaces `#29232d`, text `#f9f8fb`, secondary text `#e7d0dd`, links/code `#d8c3ef`, and accent fills `#a3004c` with text `#fbd0e8`. Keep accents sparse. - Make it mobile-readable with a responsive viewport and no fixed-width layout. - Use semantic HTML, inline CSS, inline SVG, and HTTPS or data-URL images. - Use an inline classic script only when interactivity materially helps. Keep scripted pages useful without JavaScript; the sandbox blocks storage, fetch, workers, frames, forms, and popups. - In script-free files, give external links `target="_blank"` and `rel="noopener noreferrer"`. If any script exists, omit `target="_blank"`. Never include external or module scripts, inline event handlers, `javascript:` URLs, forms, frames, embeds, objects, applets, meta refresh, linked stylesheets, secrets, private URLs, or local filesystem paths. ## Guidelines for UI Mocks Apply these UI-mock guidelines when the user explicitly asks to approve the UI before implementation. Present the artifacts and wait for that approval. For other UI design decisions, test alternatives, choose from evidence, and continue within the authorized scope. The non-UI HTML guidelines above remain applicable to reports and other written deliverables. Design <component>. Generate multiple artifacts for the component, consider the following guidelines: - Render real styled variants, not descriptions. - Label them `A`, `B`, `C`... for easy selection. - Lay them out for direct comparison. - Use the repo's existing design system: prefer the shared components we already have and the configured Tailwind colors over new ones whenever they fit. Introduce something new only when what you are designing is genuinely unlike anything in the codebase, and say so. - Every prototype must render all the states the component actually has — empty, loading, error, success, disabled, and any significant edge cases — visible and labeled on the page. - Use the real copy for labels, buttons, empty states, and errors. - When known, consider feature requirements, target route or screen, and relevant existing components. - Note which parts reuse existing components and which are new.
From AmitRockBear/pstack-t3code-claudex-port, MIT.
More from AmitRockBear/pstack-t3code-claudex-port
- 0.561score
correct
AmitRockBear
On explicit /correct, find repeated repository mistakes and prevent them through architecture, types, lint or behavioral tests.
SkillAFreshness: AClaude Code +9 - 0.544score
create-verification-skill
AmitRockBear
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9 - 0.541score
interrogate
AmitRockBear
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: AClaude Code +9 - 0.541score
how
AmitRockBear
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9 - 0.541score
architect
AmitRockBear
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: AClaude Code +9 - 0.539score
benchmark-checklist
AmitRockBear
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: AClaude Code +9 - 0.538score
babysit
AmitRockBear
Use when the user asks to monitor, watch, subscribe or babysit a PR.
SkillAFreshness: AClaude Code +9 - 0.536score
arena
AmitRockBear
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: AClaude Code +9 - 0.535score
create-pr
AmitRockBear
Use when the user asks to file, open, or create a PR.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AmitRockBear
- 0.569score
use-codex
AmitRockBear
Use when the user asks to use Codex, GPT, Sol, Luna or Astra.
SkillAFreshness: AClaude Code +9 - 0.566score
typescript-best-practices
AmitRockBear
Use when reading or editing any .ts or .tsx file.
SkillAFreshness: AClaude Code +9 - 0.565score
use-cursor
AmitRockBear
Use when the user asks to run a model fable-5-1 or opus-5-5 through Cursor, Grok, including follow-ups to an existing Cursor task.
SkillAFreshness: AClaude Code +9 - 0.565score
verify-change
AmitRockBear
Use when verifying an implemented change or PR before handoff.
SkillAFreshness: AClaude Code +9 - 0.564score
use-claude
AmitRockBear
Use when the user asks Claude, Opus or Fable for a task, including follow-ups to an existing Claude task.
SkillAFreshness: AClaude Code +9 - 0.564score
write-skill
AmitRockBear
Use when creating, modifying or reviewing skills based on recurring corrections.
SkillAFreshness: AClaude Code +9
Cite this page
html-communication skill. Agent Mart. https://agentmart.dev/skills/amitrockbear-html-communication (last updated 2026-10-24)