CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qwen-code-claw

Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.qwen/skills/qwen-code-claw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is highly actionable with concrete, executable commands for installation, authentication, and every acpx workflow pattern, and the auth flow includes genuine validation checkpoints. Its weaknesses are the inlined full ACPX CLI reference, which both bloats the token budget and duplicates content the skill points to elsewhere, and the absence of validation guidance for non-interactive batch operations.

Suggestions

Move the ACPX command-syntax and global-options reference into a separate references file (e.g. references/acpx-cli.md) and keep only the handful of commands used in the workflows inline.

Add a validation step for batch/non-interactive runs, e.g. check acpx exit status or review --format json events before declaring success with --approve-all.

Trim the duplicated task enumeration in 'When to Use This Skill' that restates the frontmatter description nearly verbatim.

DimensionReasoningScore

Conciseness

The body is mostly lean, command-first prose, but it inlines a full ACPX command-syntax and global-options reference that the skill itself says is available via the acpx skill and an external CLI doc, which could be trimmed to the few commands actually used.

3 / 5

Actionability

Every section gives copy-paste-ready commands: install (npm install -g @qwen-code/qwen-code), auth checks and branches (qwen auth status, env var test), and concrete acpx invocations covering persistent, one-shot, parallel, and JSON-output cases with flags.

5 / 5

Workflow Clarity

The auth section has an explicit check-then-branch sequence (verify existing auth, test the env var, interrupt and prompt the user if absent) and acpx setup is numbered, but there is no validation guidance for batch runs under --approve-all, a minor checkpoint gap.

4 / 5

Progressive Disclosure

There are no bundle files and external docs are one-level pointers, but the skill inlines an entire ACPX CLI reference (command syntax, session management, global options) that clearly belongs in a separate reference file, matching the 'content that should be separate is inline' anchor.

3 / 5

Total

15

/

20

Passed

Description

62%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.

The description clearly names the tool and several concrete capabilities but lacks any 'Use when...' trigger guidance, and it closes with the vague catch-all "various programming tasks" that inflates overlap risk with other coding skills. Adding an explicit trigger clause and replacing the generic tail with specific task terms would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to delegate coding tasks to Qwen Code, run a second coding agent, or mentions Qwen."

Replace "various programming tasks" with the specific tasks already in the body (code review, testing, documentation generation) to reduce vagueness and conflict risk.

Add natural synonym phrases users would say ("fix bugs", "explain this codebase", "review this PR") to improve trigger term coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ("code understanding, project generation, features, bug fixes, refactoring") with only minor generic filler ("various programming tasks"), placing it above the 1-2-action anchor but below comprehensive coverage.

4 / 5

Completeness

The description has a clear 'what' (use Qwen Code as a Code Agent for listed tasks) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural user phrases like "bug fixes", "refactoring", and "code understanding" are present, but common variations users would actually say ("code review", "explain this code", "write tests", file/task synonyms) are missing.

4 / 5

Distinctiveness Conflict Risk

Naming the specific tool (Qwen Code) gives it a niche, but the trailing "various programming tasks" is broad enough to overlap with general coding-agent and code-review skills, so it is somewhat specific with residual conflict risk.

3 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

QwenLM/qwen-code

Path

.qwen/skills/qwen-code-claw/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.