desktop-brand-builder

Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.

Quality

88%

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

88%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 high-quality, actionable skill body with executable commands, a clear validated workflow, and robust failure handling. The main room for improvement is tightening minor redundancy and considering whether signing/validation detail could be split into a reference file.

Suggestions

Consolidate the repeated 'never re-run brand-create in the same clone / single-use script' warnings into one place to reduce redundancy in the conciseness dimension.

Consider moving the Signing and Updates detail into a separate reference file referenced from the main workflow to improve progressive disclosure.

Trim the explanatory aside about why root npm install is needed to a one-line note, since the command itself is self-evident.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes competence (copy-paste commands, terse input rules), with genuinely useful non-obvious notes like the wrong-arch Node-binary cross-compile hazard; minor redundancy in the repeated 'never re-run brand-create in the same clone' guidance keeps it just below lean.	4 / 5
Actionability	Provides copy-paste-ready, executable commands throughout (git clone, npm install, the bundled brand-create.mjs invocation with exact flags, tauri build, signer generate) plus a complete brand.json example covering the common build path.	5 / 5
Workflow Clarity	Clear sequence (clone -> brand.json -> install -> brand-create -> build -> validate) with explicit validation checkpoints (artifact exists, sha256, hdiutil verify) and feedback loops for error recovery (Failure Handling section, stop-on-clone-failure), satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Well-organized into clear navigable sections with one clearly-signaled bundled reference (scripts/brand-create.mjs, verified present) that is the source of truth; most content is appropriately inlined for a single cohesive build workflow, though the single file carries a lot of detail that could be further split.	4 / 5
	Total	18 / 20 Passed

Description

87%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 strong description that clearly states both what it does and when to use it, with concrete natural-language triggers and a distinct niche. It is slightly below top on specificity and trigger breadth because it describes essentially one packaging action with enumerated output formats.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo') and enumerates outputs ('installer, DMG/EXE/AppImage/deb'), but the core is one action with enumerated formats rather than multiple distinct actions, so it sits below the comprehensive-coverage anchor.	4 / 5
Completeness	Explicitly answers both what ('Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo') and when ('Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build'), matching the concrete-trigger-phrases anchor.	5 / 5
Trigger Term Quality	Includes natural synonyms users would say ('custom, white-label, or rebranded desktop client') plus format extensions ('DMG/EXE/AppImage/deb') and 'one-click brand build', giving good coverage; a few natural phrasings (e.g. 'rebrand the app', 'redesign') are not covered, so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche ('branded Qwen Code desktop package from the Tauri desktop shell ... on top of packages/desktop-shell') with distinct triggers, so overlap with other skills is minimal.	5 / 5
	Total	18 / 20 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: QwenLM/qwen-code
Path: packages/desktop-shell/.agents/skills/desktop-brand-builder/SKILL.md
Commit: a858dea

Reviewed: 4 hours 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.