CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

publish-artifact-to-sites

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.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, well-sequenced runbook: routing rules, a seven-step workflow with explicit verification steps and named parameters, and honest failure handling with a retry-then-fallback loop plus instructions not to misreport a failed publish. The only gap is the absence of any literal command or invocation example, which keeps actionability just short of fully copy-paste ready.

DimensionReasoningScore

Conciseness

The ~30-line body contains no concept explanations or padding — even boundary statements like "it does not add live source connections to the Site" carry operational weight, and every sentence delivers routing, parameter, or verification detail. This matches the 'lean and efficient; assumes Claude's competence; every token earns its place' anchor, and there is no over-explanatory passage that could be trimmed to justify a 4.

5 / 5

Actionability

Guidance is concrete throughout: "Invoke `$sites-building`", "select the worker starter (`--starter worker`)", "Call `export_artifact_package` with ... `site_creator_project_id`", and "the logical D1 binding `DB`", with explicit pass/omit/null semantics for `site_editor_email`. It falls short of the 5 anchor because no literal copy-paste command or invocation example is shown (e.g. an actual `$sites-building` call), but it is well above 3 since the steps are executable as written with only minor gaps.

4 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit validation checkpoints ("Verify that every returned source/schema/hosting path is inside the checkout", "poll the deployment to a terminal state") and a defined error-recovery loop ("after one targeted retry ... switch to the owning workflow's self-contained HTML mode, state the failed stage"). Both verification and retry/recovery are explicit rather than implicit, matching the 5 anchor rather than the 4.

5 / 5

Progressive Disclosure

The skill is under 50 lines, self-contained with no external file references, and organized into clear sections (Routing Contract, Workflow, Fallbacks And Failures) with no nested or buried references. Per the rubric's simple-skill allowance this earns a 5; nothing is misfiled or inlined that belongs in a separate file.

5 / 5

Total

19

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description precisely names its niche and explicitly answers both what and when, with unusually specific routing conditions. Its weaknesses are naming only one capability (publishing) and leaning on internal jargon ("Work Mode", "callable", "post-handoff sharing offer") in the trigger clause, which narrows natural user-spoken trigger coverage.

DimensionReasoningScore

Specificity

"Publish a validated Data Analytics report or dashboard artifact through Sites" names the domain precisely and gives one concrete action, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because it does not list several distinct actions (export, checkpoint, deploy, verify are body-only), and not a 2 because the single action is concrete rather than generic.

3 / 5

Completeness

The what is answered clearly ("Publish a validated Data Analytics report or dashboard artifact through Sites") and the when is answered explicitly with concrete conditions ("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..."). The when could not reasonably be more explicit, so the 4 anchor ('when could be more explicit or specific') does not apply.

5 / 5

Trigger Term Quality

Natural terms a user would say are present — "Publish", "Sites", "report or dashboard" — giving good keyword coverage, but common synonyms like "share", "host", or "deploy" are missing and much of the trigger clause is internal jargon ("positively identified Work Mode", "the optional post-handoff sharing offer"). This fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive-synonym 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"through Sites" carves out a clear niche — publishing Data Analytics report/dashboard artifacts to Sites — with the distinctive anchor term repeated and explicit routing conditions that disambiguate it from generic sharing or fallback HTML publishing. This matches 'clear niche with distinct triggers; minimal conflict risk' rather than the 4 anchor's minor overlap risk.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

openai/plugins

Path

plugins/data-analytics/skills/publish-artifact-to-sites/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.