CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

share

Share a runnable prototype using the user's preferred deployment tool.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/product-design/skills/share/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A compact, well-structured instruction skill: the fragile Sites handoff is protected by explicit build/test/artifact validation, guardrails are clear, and cross-skill references are well signaled. The only notable flaws are a duplicated fallback instruction and the absence of an error-recovery path when pre-deploy validation fails.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence ("Run `npm run build` and `npm run test:sites`"), with no explanations of known concepts. One verbatim duplication — "If the selected tool is not available, say that clearly and ask whether to use another target" appears as both Workflow step 6 and a Rule — is the only trimmable content, keeping it below the "every token earns its place" anchor.

4 / 5

Actionability

Concrete commands and file checks are present ("Run `npm run build` and `npm run test:sites`", "Confirm `dist/client/index.html`, `dist/server/index.js`... exist") plus an exact question to ask the user. The core deployment step itself ("Run the deployment when possible") delegates mechanics to other tools, a minor gap versus fully copy-paste-ready guidance.

4 / 5

Workflow Clarity

Nine clearly sequenced steps with an explicit pre-handoff validation checkpoint (build, test, confirm four artifact files exist before handing to `sites-hosting`) and guardrail Rules. It lacks an error-recovery loop for what to do when that validation fails, so it does not reach the feedback-loop anchor.

4 / 5

Progressive Disclosure

The body is under 50 lines with well-organized sections (Critical Overrides, User Context, Workflow, Rules) and one-level-deep cross-references clearly signaled with `[$index]`, `[$critical-overrides]`, and `[$user-context]` syntax. Per the simple-skill scoring note, no external reference files are needed, so this fully meets the anchor.

5 / 5

Total

17

/

20

Passed

Description

53%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 communicates a clear, single-purpose capability in third person without fluff, but it is bare: it states only the core action with no when-to-use guidance and a thin set of trigger synonyms. This limits discoverability and routing confidence even though conflict risk is low.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to share or publish a finished prototype, get a shareable URL, or asks to deploy it to @Sites, @Vercel, or another host."

Enumerate the concrete actions the skill performs — verify the prototype build, deploy to the chosen target, and return a working shareable URL — to raise specificity.

Include natural trigger synonyms such as "publish", "put it online", and "shareable link" to match the phrasings users actually say.

DimensionReasoningScore

Specificity

"Share a runnable prototype using the user's preferred deployment tool" names the domain and one concrete action (share/deploy), matching the "1-2 concrete actions, not comprehensive" anchor. It omits the skill's other concrete behaviors (verify the build, return a working shareable URL), so it does not reach the several-specific-actions anchor.

3 / 5

Completeness

The "what" is clear (share/deploy a runnable prototype) but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is above anchor 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

It includes relevant natural terms — "Share", "prototype", "deployment tool" — that users would plausibly say, but misses common variations such as "publish", "put it online", "shareable link/URL", or "demo", fitting the some-keywords-but-missing-synonyms anchor rather than good coverage.

3 / 5

Distinctiveness Conflict Risk

"Share a runnable prototype" carves a distinct niche (prototype deployment for sharing) with only minor overlap risk against generic deployment/hosting or file-sharing skills. It is not a 5 because without trigger phrases, a request like "deploy this app" could still plausibly route here or to a general deployment skill.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/product-design/skills/share/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.