CtrlK
BlogDocsLog inGet started
Tessl Logo

build-chatgpt-app

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, actionable, and well-disclosed skill body with a strong sequenced workflow and real reference files; its main weakness is content redundancy across overlapping sections that could be tightened.

Suggestions

Consolidate the archetype classification so it lives in one place (step 0) and have the earlier "Classify The App Before Choosing Code" section point to it rather than restating the bullet list.

Merge the standalone "Default Starting-Point Order" with steps 2a/2b to avoid repeating the official-example / ext-apps / fallback ordering twice.

Drop the duplicate per-file reference pointers at the end ("## References") since each is already signaled inline, or keep only the inline mentions and retain the References block as the single consolidated index.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's knowledge (no explanations of MCP/widgets), but it is redundant: archetype classification is described both in "Classify The App Before Choosing Code" and step 0, the starting-point order is restated across "Default Starting-Point Order" and steps 2a/2b, and reference pointers appear both inline and again in the References list.

2 / 3

Actionability

Names concrete, usable surfaces — exact MIME type ("text/html;profile=mcp-app"), bridge events ("ui/notifications/tool-result"), window.openai methods, tool annotations, commands ("ngrok http <port>"), and a real executable scaffold script — providing specific actionable guidance for an instruction-heavy skill.

3 / 3

Workflow Clarity

A clearly sequenced 0–9 build workflow with explicit validation checkpoints (step 5a minimum working repo contract, step 6 validation ladder with low-cost-then-runtime ordering and "say what you did not run") and checklists, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

SKILL.md is an overview pointing to seven reference files plus one scaffold script, all verified to exist, one level deep and clearly signaled both inline ("Read references/...") and in a dedicated References section, with detailed rubrics/patterns offloaded to those files.

3 / 3

Total

11

/

12

Passed

Description

100%

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 specific, well-triggered description that clearly states both capabilities and use conditions in a domain-specific niche, with no first/second-person voice to penalize. It is strong across all four dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Build, scaffold, refactor, and troubleshoot", "design tools, register UI resources, wire the MCP Apps bridge", "apply Apps SDK metadata or CSP or domain settings", "produce a docs-aligned project scaffold" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ("Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications...") and when ("Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge...") with an explicit Use-when trigger clause.

3 / 3

Trigger Term Quality

Covers natural domain terms a user would say ("ChatGPT Apps SDK", "MCP server and widget UI", "project scaffold", "CSP", "domain settings") rather than abstract jargon, satisfying the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The tightly scoped niche — ChatGPT Apps SDK apps combining an MCP server and widget UI, wired through the MCP Apps bridge — has distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation16 / 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.