html-communication
Writes HTML writeups and publishes them privately to files.vaut.dev.
Skill by connorch
Chalk Labs
Need help deploying html-communication?
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/connorch-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: documents, design, frontend
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 and code. Checked Nov 1, 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
- Writes HTML writeups and publishes them privately to files.vaut.dev. Use when the user asks for an HTML writeup of work, such as a plan, spec, findings, report, or UI mocks, that is not part of the codebase.
- License
- MIT
- Metadata
- requires: the vaut CLI on PATH (see the $vaut-file-hosting skill)
- Instructions
- 78 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# HTML Communication ## When to Use Use this skill when the user wants a plan, spec, write-up, findings, summary, report, comparison, or set of UI mocks presented as readable HTML. Do not use it for HTML that ships as part of a product. ## Document Create one self-contained HTML file, capped at 1MB. - Write it like a spec, not a landing page: yes dense, yes scannable, no hero, no decorative chrome, no marketing voice, and no em dashes. - Talk in ASD-STE100 Simplified Technical English, and use the ubiquitous language from `CONTEXT.md` if one exists. - 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 diagrams, charts, or visualizations when you think it will actually be useful to the user. Connor is a visual learner. - 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. ### Palette This palette is a suggestion. Use unless you have a need or are asked to deviate. ``` --bg: #121212 page background --surface: #1A1A1A cards, code blocks, table header rows. Go slightly lighter for each level of elevation. (ex: #222222 for lvl 2) --text: #E0E0E0 body copy and headings --muted: #A0A0A0 labels, captions, metadata --border: #2A2A2A dividers and hairlines --accent: #90CAF9 links and emphasis --success: #A5D6A7 positive status indicator (passed, added, etc.) --warning: #FFCC80 caution status indicator (flaky, degraded, needs review, etc.) --danger: #CF6679 negative status indicator (blocked, failed, removed, etc.) ``` ## UI Mocks When the user asks for variants: - Render real styled variants, not descriptions. - Label them `A`, `B`, `C`... for easy selection. - Lay them out for direct comparison. - Keep one file across iterations and publish to the same `--at` path so its URL stays stable. ## Publish Connor has given standing permission to upload every artifact created or updated with this skill. Upload is required, including in Auto mode. Do not ask for separate permission or stop at the local file. 1. Write the HTML file locally, named per the $vaut-file-hosting skill's naming convention (kebab-case, descriptive, `.html`). 2. Run `vaut put --at docs/<file name> <file path>` (uploads are private by default; add `--force` when updating a document that is already published). 3. Report the local path and the returned files.vaut.dev URL. Re-upload to the same `--at` path with `--force` to update the document in place; the URL stays stable across iterations. Use a new path only for a genuinely new document. Only Connor can open private URLs (signed in to vaut.dev in the browser, or through the CLI); never embed them in public PRs or issues. To read one back, run `vaut read <url>`. If `vaut` is missing or not signed in, tell the user instead of guessing. Never claim the document is hosted before the upload succeeds. Do not verify in a browser unless the user asks.
From connorch/skills, MIT.
More from connorch/skills
- 0.603score
qa-ux-verify
connorch
Runs a QA plan in a browser and reports the results without fixing anything.
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
step-back
connorch
Step back from a branch that grew through iteration - review rounds, point fixes, PR feedback - and judge the end state as a whole: are the big architecture…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
codex-implementation
connorch
Implements scoped code changes with Codex CLI, then inspects the diff.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
codex-review
connorch
Gets an independent code review from Codex CLI.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
fleet-exec
connorch
Run commands on another of the user's machines (the macOS and linux machines on their tailnet) over Tailscale SSH.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
implement-and-review
connorch
Use when the user approves a plan and says to implement it.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
claude-router
connorch
Controls claude-router, the local proxy that spreads Claude Code requests across subscription accounts.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
mac-vm
connorch
Use when a task needs a GUI app on a Mac whose desktop is locked, or when the user asks to start, stop, or set up the agent macOS VM.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
merge-risk
connorch
Rates how risky it is to merge a pull request or branch, on a Minimal / Low / Moderate / High / Critical scale, with the blockers that set the rating.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
pull-upstream
connorch
Sync a forked repository with its upstream.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
qa-ux-plan
connorch
Writes an end-to-end QA plan from the branch diff without running tests.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
t3-browser
connorch
Use for any browser QA, verification, screenshot, or "check it in the browser" step when the T3 Code Browser panel tools (mcp__t3-code__preview_*, such as…
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Oct 19, 2026 (17 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/connorch/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from connorch
- 0.603score
qa-ux-verify
connorch
Runs a QA plan in a browser and reports the results without fixing anything.
SkillAFreshness: A★ 2Claude Code +9 - 0.603score
step-back
connorch
Step back from a branch that grew through iteration - review rounds, point fixes, PR feedback - and judge the end state as a whole: are the big architecture…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
claude-router
connorch
Controls claude-router, the local proxy that spreads Claude Code requests across subscription accounts.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
codex-implementation
connorch
Implements scoped code changes with Codex CLI, then inspects the diff.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
codex-review
connorch
Gets an independent code review from Codex CLI.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
fleet-exec
connorch
Run commands on another of the user's machines (the macOS and linux machines on their tailnet) over Tailscale SSH.
SkillAFreshness: A★ 2Claude 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 html-communication 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
html-communication skill. Agent Mart. https://agentmart.dev/skills/connorch-html-communication (last updated 2026-10-24)