manage-app

Use when the user wants to manage or troubleshoot tooling, remotes, sync, build, deploy, logs, CI/CD, or operational workflows for an existing Twenty app.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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 body is an efficient, highly actionable operational runbook: concrete yarn commands, explicit confirmation/version/isolation checkpoints for risky operations, and well-signaled one-level-deep references for background and detail. It assumes Claude's competence and avoids padding.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven throughout, with domain-specific asides (e.g. 'A remote is a Twenty server...') rather than generic concepts Claude already knows; every section earns its tokens.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands with concrete flags throughout, e.g. 'yarn twenty remote:add --url ... --api-key $TWENTY_API_KEY --as production' and 'TWENTY_API_URL=http://localhost:2021 yarn test'.	3 / 3
Workflow Clarity	Risky operations carry explicit validation/confirmation checkpoints — confirming the app directory first, asking before production deploys/syncs/uninstalls, checking a strictly higher semver before redeploy, and isolating integration tests on a separate test instance — with error-recovery guidance in Troubleshooting.	3 / 3
Progressive Disclosure	SKILL.md acts as a well-organized overview with clearly signaled, one-level-deep references ('read `../../references/manage-app/cli-and-sync.md`', 'how-apps-work.md', 'tests.md') for deeper detail, keeping the inline body focused on immediate operational commands.	3 / 3
	Total	12 / 12 Passed

Description

100%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.

A concise, well-scoped description that names concrete operational actions, includes an explicit 'Use when' trigger, and stays clearly distinct from sibling Twenty skills. It avoids fluff and verbosity entirely.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete operational actions — 'manage or troubleshoot tooling, remotes, sync, build, deploy, logs, CI/CD' — rather than vague language, matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (manage/troubleshoot operational workflows for a Twenty app) and when via an explicit 'Use when the user wants to...' trigger clause.	3 / 3
Trigger Term Quality	Uses natural terms users would actually say ('deploy', 'sync', 'logs', 'CI/CD', 'remotes', 'troubleshoot'), giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'an existing Twenty app' with operational-only triggers (sync/build/deploy/logs/CI/CD), carving a clear niche unlikely to fire for scaffolding or entity-development skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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: twentyhq/twenty
Path: packages/twenty-codex-plugin/skills/manage-app/SKILL.md
Commit: bb4e427

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.