Publish Artifact To Sites Agent Skill

Publish a validated Data Analytics report or dashboard artifact through Sites.

Context cost
1.1k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 4.2 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Publish a validated Data Analytics report or dashboard artifact through Sites. Use automatically for durable artifacts in any positively identified Work Mode when the full Sites lifecycle is callable, or in ChatGPT Desktop outside Work Mode only after an explicit Sites request or acceptance of the optional post-handoff sharing offer.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

analytics

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md4.2 kB · preview
--- name: publish-artifact-to-sites ---
6# Publish Artifact To Sites
7
8Use this skill after the report or dashboard workflow produces a complete canonical manifest and bounded snapshot and validate_artifact succeeds. It publishes the Data Analytics reader runtime as a Sites-hosted snapshot; it does not add live source connections to the Site.
9
10## Routing Contract
11
12- In any positively identified Work Mode, a durable report or dashboard request selects Sites automatically when the full Sites building and hosting lifecycle is callable. Do not ask for another delivery choice or publish confirmation.
13- In ChatGPT Desktop outside Work Mode, use this skill only after the user explicitly requests Sites or explicitly accepts the optional coworker-sharing offer made after a successful final MCP artifact handoff. A report or dashboard request alone does not authorize publishing there.
14- If the full Sites lifecycle is not callable in Work Mode, use the self-contained HTML fallback selected by the owning report or dashboard workflow.
15
16## Workflow
17
181. Confirm that $sites-building and $sites-hosting are both callable for the full Sites create, checkpoint, and deployment lifecycle.
192. Invoke $sites-building to create or reopen one worker-starter checkout per logical report or dashboard. For a new Site, select the worker starter (--starter worker). Reuse that Site for later versions.
203. Read the Site's current access policy with the Sites connector. Treat a workspace Site as verifiably owner-only only when it is custom, has exactly one allowed_account_user_id, its sole allowed_users entry has the same account-user id and a non-empty email, and it has no allowed groups. If the user asked to widen reader access, defer that access change until after the package is exported so the verified creator seed is not lost. Do not infer a creator from an already-shared reader allowlist.
214. Call export_artifact_package with the validated payload, the Sites project id in the compatibility field site_creator_project_id, and the returned checkout path as output_dir. When the current workspace policy is verifiably owner-only, pass its sole resolved email as site_editor_email; the exporter hashes it before writing source. Otherwise omit the field so an existing editor seed or explicit disabled state is preserved. Pass site_editor_email: null only when the user explicitly asks to disable presentation editing. After export succeeds, apply any reader-access change the user explicitly requested, then checkpoint and deploy with the same approval boundary.
225. Verify that every returned source/schema/hosting path is inside the checkout, and separately verify that the hosting metadata contains the resolved project id. Presentation editing requires the logical D1 binding DB; do not replace another binding name. A read-only export may omit database_schema_path.
236. Checkpoint the checkout through $sites-building, then invoke $sites-hosting to poll the deployment to a terminal state.
247. Return the Sites URL and artifact snapshot timestamp, and state that the published data is a snapshot rather than a live connection. When presentation editing is enabled, state that only the seeded creator can edit title/text/layout, delete blocks, or launch refresh and export handoffs; saved presentation overrides remain in Sites rather than syncing back to ChatGPT Desktop.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md615 words
Files1
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈100
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
950
on trigger
The instruction body, read only when the skill fires.
0.53%
of a 200k window
Ten skills this size would take about 5% of the window before you open a file.
050k100k150k200k context window

1.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 4.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md4.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Publish Artifact To Sites · 1.1k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/publish-artifact-to-sites/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/publish-artifact-to-sites" ] && { [ ! -e .claude/skills/publish-artifact-to-sites ] || { mv .claude/skills/publish-artifact-to-sites "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/publish-artifact-to-sites" .claude/skills/ && echo "Installed .claude/skills/publish-artifact-to-sites"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ahang1598/publish-artifact-to-sites

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/publish-artifact-to-sites/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/publish-artifact-to-sites/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/publish-artifact-to-sites" ] && { [ ! -e ~/.claude/skills/publish-artifact-to-sites ] || { mv ~/.claude/skills/publish-artifact-to-sites "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/publish-artifact-to-sites" ~/.claude/skills/ && echo "Installed ~/.claude/skills/publish-artifact-to-sites" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/publish-artifact-to-sites/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceahang1598/publish-artifact-to-sites

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill