CtrlK
BlogDocsLog inGet started
Tessl Logo

create-app

Use when the user wants to create or scaffold a new Twenty app

66

Quality

80%

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 ./packages/twenty-codex-plugin/skills/create-app/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

The content is well-structured, actionable, and follows a clear sequenced workflow with confirmation and recovery checkpoints. Its main weakness is token efficiency, where some explanatory passages repeat the instance-vs-Docker point unnecessarily.

Suggestions

Collapse the "Why A Twenty Instance Is Needed" section and the Docker-fallback prose so the instance/Docker tradeoff is stated once; move deeper conceptual background entirely to how-apps-work.md.

Make reference paths consistent (one uses ../../references/..., the other references/...) so navigation resolves predictably within the bundle.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but the "Why A Twenty Instance Is Needed" section and the repeated Docker-fallback explanation restate the same instance/Docker tradeoff several times and could be tightened.

2 / 3

Actionability

It provides copy-paste-ready commands (npx create-twenty-app@latest with --url and the package-name variant), an explicit list of supported create-time options, and a concrete Docker download link, giving fully executable guidance.

3 / 3

Workflow Clarity

The flow is clearly sequenced (explain instance → choose instance → confirm purpose → scaffold → after-scaffold), with a pre-scaffold confirmation checkpoint and a Docker-fallback error-recovery loop that reroutes to --url.

3 / 3

Progressive Disclosure

The SKILL.md acts as an overview that signals one-level-deep references (../../references/concepts/how-apps-work.md, references/design/front-component-ui.md) and sibling skills, with content well split into clearly headed sections.

3 / 3

Total

11

/

12

Passed

Description

75%Weight 40%Scale 1-3

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 clear and trigger-driven with an explicit "Use when" clause and a distinct niche, but it is thin on action variety and natural-language variations. Broadening the verbs and trigger terms would raise it from good to comprehensive.

Suggestions

Add concrete action verbs beyond create/scaffold (e.g., "scaffold, bootstrap, or set up a new Twenty app") to lift specificity and trigger coverage.

Mirror the body's natural trigger phrasings ("build a Twenty app", "start a new Twenty plugin/integration") into the description so users' exact words are matched.

DimensionReasoningScore

Specificity

"create or scaffold a new Twenty app" names a clear domain and two near-synonym actions, but does not list multiple distinct concrete actions, matching the anchor that names domain and some actions without being comprehensive.

2 / 3

Completeness

The phrase "Use when the user wants to create or scaffold a new Twenty app" supplies both the what (create/scaffold a Twenty app) and an explicit "Use when..." trigger clause, satisfying both required elements.

3 / 3

Trigger Term Quality

"create", "scaffold", and "new Twenty app" are natural terms a user would say, but the description omits common variations (build, bootstrap, set up) that the body itself lists as triggers, so coverage is incomplete.

2 / 3

Distinctiveness Conflict Risk

The trigger is anchored to a clear niche (new Twenty app, from scratch), making it unlikely to fire for sibling skills like develop-app or manage-app that handle existing apps.

3 / 3

Total

10

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
twentyhq/twenty
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.