CtrlK
BlogDocsLog inGet started
Tessl Logo

chatgpt-app-submission

Inspect a ChatGPT Apps MCP server codebase and generate chatgpt-app-submission.json with app info suggestions, tool hint justifications, test cases, and negative test cases, then report review-check findings and outputSchema warnings for submission review.

66

Quality

78%

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/openai-developers/skills/chatgpt-app-submission/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tightly written, highly actionable skill body: concrete output contracts, exact warning text, and explicit approval gates around source edits. The only weaknesses are mild repetition of the approval procedure across sections and the absence of a final JSON-validation step.

DimensionReasoningScore

Conciseness

The body is dense operational rules with no conceptual padding (it never explains what MCP or CSP is) and every section carries actionable constraints. Minor tightening is possible: the "ask the developer for approval before updating source" instruction is repeated across the Workflow, Hint Rules, and Tool Descriptor/CSP Rules sections. This places it just below the lean-and-efficient anchor of 5.

4 / 5

Actionability

Fully concrete and copy-paste ready: a complete example chatgpt-app-submission.json, the exact outputSchema warning text to print verbatim, exact test-case counts ("exactly five positive test cases and exactly three negative test cases"), an explicit category enum, and good/bad justification examples. Specific examples cover the common cases.

5 / 5

Workflow Clarity

A clear 8-step numbered sequence with explicit approval gates before any destructive source edit and full error-recovery paths ("If the developer does not approve... do not generate misleading JSON; report the mismatch and the blocked update"). The score is 4 rather than 5 because there is no final step validating the generated JSON against the submission schema, and 4 rather than 3 because checkpoints are present and explicit rather than implicit.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; the skill is self-contained with clear, well-ordered section headers (Workflow, Hint Rules, Output Contract, Test Case Rules, Reporting). The full 45-line JSON example and the category enum could eventually move to a reference file if the skill grows, which is the minor organization gap separating it from a 5.

4 / 5

Total

17

/

20

Passed

Description

75%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.

A highly specific, distinctive description that comprehensively enumerates the skill's concrete outputs. Its main weakness is the absence of any explicit "when to use" trigger clause, which both caps completeness at 3 and leaves natural trigger phrasings uncovered.

Suggestions

Append a trigger clause such as: "Use when a developer needs to submit a ChatGPT Apps MCP server and must generate or review chatgpt-app-submission.json."

Add natural trigger synonyms users would actually say, e.g. "submit an app", "publish a ChatGPT app", "App Store submission", "Apps SDK review".

Keep the existing deliverable enumeration but front-load the trigger context so the when-to-use guidance is explicit rather than implied by the domain.

DimensionReasoningScore

Specificity

Names the domain ("ChatGPT Apps MCP server codebase") and lists multiple concrete actions — inspect the codebase, generate "chatgpt-app-submission.json", app info suggestions, tool hint justifications, test cases, negative test cases, and report review-check findings and outputSchema warnings. Coverage is comprehensive with no gaps between the description and the skill's actual deliverables.

5 / 5

Completeness

Clearly answers "what" with concrete deliverables, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline. Not a 2 because the "what" is fully concrete, not vague.

3 / 5

Trigger Term Quality

Good natural keywords — "ChatGPT Apps", "MCP server", "submission", "chatgpt-app-submission.json", "submission review" — but a few natural phrases users would say are missing (e.g. "submit an app", "publish an app", "App Info"). Not a 3 because the present keywords are specific rather than generic.

4 / 5

Distinctiveness Conflict Risk

A clear niche (generating the ChatGPT Apps submission JSON) with distinct triggers tied to a specific file format and submission workflow; minimal risk of triggering for the wrong skill.

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
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.