extension-creator

Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an extension locally. Invoke with `/extension-creator` followed by an extension path and optional template name.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

The content is highly actionable with strong, explicitly-validated workflows and concrete executable commands, and it avoids explaining concepts Claude already knows. Its main weaknesses are repeated security/path guidance across sections (conciseness) and a monolithic single-file structure where reference material could be split into one-level-deep files (progressive disclosure).

Suggestions

Deduplicate the repeated security guidance (contextFileName path rejection, NODE_OPTIONS/PATH/LD_PRELOAD/DYLD_INSERT_LIBRARIES env-var warnings, and symlink/path-containment rules) into a single authoritative section referenced by the others, to tighten conciseness.

Extract the detailed Extension Shape field reference and the Local Test Flow into one-level-deep reference files (e.g. EXTENSION-SHAPE.md, LOCAL-TEST-FLOW.md) signposted from the main workflow, improving progressive disclosure for this long skill.

Move the Before Handoff checklist items into a short, scannable verification list with the longer justification text pushed to a reference, keeping the gate explicit without the surrounding prose.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence (no explaining of what extensions/npm are), but it repeats the same guidance across sections — e.g. contextFileName path rejection (lines 127-128 and 214-216), process-control env vars NODE_OPTIONS/PATH/LD_PRELOAD/DYLD_INSERT_LIBRARIES (lines 139 and 218), and symlink/path-containment rules across Before Handoff — so not every token earns its place as the score-3 anchor requires.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (qwen extensions new "$extension_path" "$template", npm install --ignore-scripts, node -e "JSON.parse(...)" validation) plus exact manifest-field rules, matching the score-3 anchor for concrete executable guidance with no pseudocode.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints and feedback loops — e.g. step 7 stop-and-report on command failure, the Before Handoff checklist as a verification gate, and build failure recovery in the Iterating flow — satisfying the score-3 anchor for clear sequence with explicit validation.	3 / 3
Progressive Disclosure	Well-organized into clear sections with headers, but it is a single ~344-line monolithic file with no external references despite clearly separable concerns (the Extension Shape field reference, the Local Test Flow) that could be split out; this matches the score-2 anchor of structure present but content that should be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, trigger-rich, and fully answers both what the skill does and when to use it, with a clear explicit Use-when clause and third-person voice throughout. It is well above the cap placed on descriptions missing a Use-when trigger and shows no over-claiming or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Create, scaffold, customize, validate, and locally test Qwen Code extensions" — matching the score-3 anchor for enumerating specific concrete actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what (create/scaffold/customize/validate/test extensions) and when via a clear "Use when the user wants..." clause, meeting the score-3 anchor for both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say — "new Qwen Code extension", "extension template", and a broad enumeration (QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, LSP servers, link and test) — satisfying the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Qwen Code extensions) with distinct, specific triggers unlikely to fire for unrelated skills, matching the score-3 clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: QwenLM/qwen-code
Path: packages/core/src/skills/bundled/extension-creator/SKILL.md
Commit: 8878264

Reviewed: 5 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.