CtrlK
BlogDocsLog inGet started
Tessl Logo

desktop-brand-builder

Generate a branded qwen-code desktop package from a minimal brandId and logo. Use when the user wants a custom, white-label, rebranded, ModelStudio/OpenWork/Qwen Code desktop client, installer, DMG/EXE/AppImage, or one-click brand build.

76

Quality

93%

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

92%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 focused, highly actionable build skill with executable commands, explicit validation, and failure handling. The bundled script is correctly referenced and present, and the body stays lean with minor trimmable justification.

DimensionReasoningScore

Conciseness

Mostly lean with well-organized sections and assumes Claude's competence; a few justifying clauses ('so user changes in the current worktree are not mutated') could be tightened but earn their place.

4 / 5

Actionability

Fully executable, copy-paste-ready bash commands, a concrete brand.json example, and explicit packaging/validation commands cover the common cases without pseudocode.

5 / 5

Workflow Clarity

Clear sequenced workflow (isolate build dir, clone, brand.json, install, run bundled script, package, validate) with explicit validation checkpoints (artifact existence, sha256, hdiutil verify) and a failure-handling feedback loop.

5 / 5

Progressive Disclosure

Well-structured overview with a single one-level-deep bundle reference (scripts/brand-create.ts) that exists and is clearly signaled as the source of truth; no nested references.

5 / 5

Total

19

/

20

Passed

Description

95%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, third-person description that concisely states the capability and gives rich, natural trigger phrasing with synonyms and artifact formats. Minor specificity headroom only because intermediate build steps are summarized rather than enumerated.

DimensionReasoningScore

Specificity

Lists several concrete actions and outputs (branded package, installer, DMG/EXE/AppImage) grounded in a specific brandId+logo input, with only minor coverage gaps around intermediate steps.

4 / 5

Completeness

Explicitly answers both 'what' (generate a branded desktop package from brandId and logo) and 'when' via a concrete 'Use when the user wants...' clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger vocabulary including synonyms (white-label, rebranded, one-click brand build), product names (ModelStudio/OpenWork/Qwen Code), and artifact formats (DMG/EXE/AppImage) a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (white-label/rebranded qwen-code desktop clients) with highly specific triggers, making conflict with unrelated skills minimal.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
QwenLM/qwen-code
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.