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.

71

Quality

86%

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%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 well-structured, docs-first workflow with a sequenced build process, explicit validation ladder, and excellent progressive disclosure into real, conditionally-signaled reference files. The main gaps are mild redundancy in reference pointers and the absence of any inline code snippet for the most common scaffold case.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and assumes Claude's competence — it never explains what MCP or a widget is. Minor inefficiencies remain: each reference file is pointed to both inline ('Read references/... when ...') and again in the final References section, and a few bullets are wordy, so it is 'efficient with minor trimming possible' rather than fully lean.

4 / 5

Actionability

Concrete, executable guidance throughout: exact doc paths ('apps-sdk/build/mcp-server'), a real script ('scripts/scaffold_node_ext_apps.mjs'), specific APIs ('window.openai.callTool(...)'), the MIME type 'text/html;profile=mcp-app', the ngrok command, and the exact Settings path for Developer Mode. Falls short of the top anchor only because there is no copy-paste-ready code snippet in the body itself for the most common scaffold case — code lives in the script and references.

4 / 5

Workflow Clarity

A clearly sequenced workflow (steps 0–9) with explicit validation checkpoints: a lowest-cost-first validation ladder, 'If doc search times out... fetch the canonical Apps SDK pages directly and continue', 'If you are only delivering a scaffold... say exactly what you did not run', and a minimum working repo contract checked before considering work done — including explicit what-was-and-was-not-run reporting.

5 / 5

Progressive Disclosure

The body is an overview that pushes detail into 7 one-level-deep reference files plus 1 script, all of which exist on disk. Each is clearly signaled inline with a 'Read references/X.md when...' condition plus a consolidated References section, making navigation easy. No nested references or inlined bulk content.

5 / 5

Total

18

/

20

Passed

Description

88%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 is strong: it states concrete capabilities in third person, includes an explicit 'Use when...' trigger clause, and carves out a distinct niche. Trigger-term coverage is good but misses a few natural synonyms, keeping it just short of top marks on two dimensions.

Suggestions

Add common user phrasings as triggers, e.g. 'ChatGPT app', 'ChatGPT connector', 'Apps SDK submission', or 'ext-apps', to broaden natural keyword coverage.

Clarify the boundary with adjacent skills (e.g. generic MCP server scaffolding or the openai-docs skill) so the description triggers only for ChatGPT Apps SDK-specific work.

DimensionReasoningScore

Specificity

Lists multiple specific 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' — with comprehensive coverage of the skill's scope.

5 / 5

Completeness

Explicitly answers both what ('Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI') and when ('Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge...'), matching the top anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('ChatGPT Apps SDK', 'MCP server', 'widget UI', 'scaffold', 'refactor', 'troubleshoot', 'CSP') that users would plausibly say. A few natural variations are missing (e.g. 'ChatGPT app', 'connector', 'app submission', 'ext-apps'), so it sits between the 'good coverage' and 'comprehensive synonyms' anchors.

4 / 5

Distinctiveness Conflict Risk

A clear niche (ChatGPT Apps SDK apps with MCP server + widget) with distinct triggers, but there is minor overlap risk with generic MCP-server or 'build a ChatGPT connector' requests and with the referenced openai-docs skill, placing it just below the minimal-conflict anchor.

4 / 5

Total

18

/

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.