CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qc-helper

Answer any question about Qwen Code usage, features, configuration, and troubleshooting by referencing the official user documentation. Also helps users view or modify their settings.json. Invoke with `/qc-helper` followed by a question, e.g. `/qc-helper how do I configure MCP servers?` or `/qc-helper change approval mode to yolo`.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/core/src/skills/bundled/qc-helper/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-architected lookup skill with a genuinely useful topic index and two clear, checkpointed workflows. Its weaknesses are duplicated configuration content inlined in SKILL.md, a missing post-edit validation step, and a documentation tree that is referenced but not present in this bundle.

Suggestions

Ship the 'docs/' directory with the skill — the entire workflow depends on ~60 referenced paths that do not exist in the bundle, making the skill unusable as delivered.

Trim the 'Configuration Quick Reference' section to a few pointer lines into 'docs/configuration/settings.md' instead of duplicating locations, priority, and key categories inline.

Add a post-edit validation step to the configuration workflow, e.g. re-read the modified file with 'read_file' and confirm the JSON parses before reminding the user to restart.

DimensionReasoningScore

Conciseness

The documentation index itself is lean and earns its tokens, but the ~30-line 'Configuration Quick Reference' section (file locations, priority order, format details, key categories) duplicates content already maintained in 'docs/configuration/settings.md', and the 'load only the docs that are relevant' guidance appears twice (lines 27 and 152). This fits 'mostly efficient but could be tightened' rather than the minor-trimmable-inefficiency of a 4.

3 / 5

Actionability

Concrete, executable guidance throughout: exact doc paths, named tools ('read_file', 'edit_file'), explicit file paths ('~/.qwen/settings.json', '.qwen/settings.json'), and a verbatim restart reminder to deliver after every config change. Not a 5 because there is no worked example of the actual read_file/edit_file call with the joined base-directory path, and the JSONC example guidance has no sample snippet.

4 / 5

Workflow Clarity

Both workflows are clearly sequenced with real checkpoints: ask which config level if unspecified, read the current settings file before editing, and a mandatory post-change restart reminder. It falls short of 5 because there is no explicit validation step after edit_file (e.g., re-reading the file or checking JSON validity), which matters since malformed JSON would break Qwen Code on restart.

4 / 5

Progressive Disclosure

The body is structured as a clean overview with a well-organized, one-level-deep index of ~60 doc paths — exactly the right shape — but the referenced 'docs/' tree is entirely absent from the bundle (only SKILL.md, config.json, and rubrics/ exist), so every reference is dangling and navigation cannot be exercised. Scored against the actual bundle structure, this lands mid-scale: excellent structure on paper, broken in practice.

3 / 5

Total

14

/

20

Passed

Description

78%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, well-scoped description with concrete capability areas, natural example invocations, and minimal conflict risk. Its main weakness is that the 'when to use' guidance lives only in invocation-syntax examples rather than an explicit 'Use when...' trigger clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about Qwen Code usage, configuration, features, or errors, or wants to change a Qwen Code setting.'

Include a few more natural trigger variations users would say, such as 'set up', 'fix', 'install', or 'error messages', alongside the existing terms.

DimensionReasoningScore

Specificity

The description names the domain ('Qwen Code') and lists several specific capability areas — 'usage, features, configuration, and troubleshooting', 'view or modify their settings.json' — plus concrete example invocations. It falls short of a 5 because the actions are stated at the area level rather than as multiple discrete concrete actions, and beyond a 3 because it covers more than 1-2 concrete actions with minor gaps.

4 / 5

Completeness

The 'what' is clear (answer Qwen Code questions by referencing official documentation; help modify settings.json), and the 'when' is addressed through explicit invoke examples ('/qc-helper how do I configure MCP servers?'), which qualifies as equivalent explicit trigger guidance so the cap of 3 does not apply. Not a 5 because there is no explicit 'Use when...' clause stating the conditions for use; the trigger conditions must be inferred from the invocation syntax examples.

4 / 5

Trigger Term Quality

Good keyword coverage: 'Qwen Code', 'configuration', 'troubleshooting', 'settings.json', 'MCP servers', 'approval mode', 'yolo', and two naturally phrased example questions users would actually say. Not a 5 because common variations like 'set up', 'fix', 'error', or 'install' are missing alongside the listed terms.

4 / 5

Distinctiveness Conflict Risk

The skill is scoped to a clear niche — answering questions about Qwen Code specifically — with distinct triggers like 'Qwen Code', 'MCP servers', and 'approval mode to yolo' that would not naturally fire for other skills. Minimal conflict risk.

5 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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/qc-helper/SKILL.md

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.