e2e-testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response payloads. Trigger on mentions of E2E testing, headless testing, MCP tool testing, or reproducing issues.

Quality

93%

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

93%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-structured, executable guide that keeps the body lean while pushing detailed MCP and mock-server setup into verified one-level-deep references. The only gap is a missing explicit verification checkpoint in the primary headless workflow.

Suggestions

Add an explicit verification step to the headless-mode workflow (e.g. check the result message's exit status / usage block or assert a known field with jq) so the main flow has a feedback checkpoint like the interactive and mock sections do.

Consider an explicit "expected output" snippet for the headless json example so Claude can confirm a successful run versus a silent failure.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — it explains only non-obvious gotchas (--auth-type vs --model, QWEN_RUNTIME_DIR scope, the "esc to cancel" poll, respond_in_schema) and every explanatory block earns its place rather than padding about basic concepts.	5 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (build/bundle, QWEN_RUNTIME_DIR, tmux send-keys, jq filters, --openai-logging-dir) with concrete examples covering the common headless, interactive, and API-inspection cases.	5 / 5
Workflow Clarity	Clear Setup → Run modes → Inspecting → Harnesses → Tips sequence with diagnostic checkpoints (poll-until-done, verify-server-loaded, verify-mock-hit), but the primary headless flow lacks an explicit output/exit verification step, leaving it just short of the feedback-loop richness of a 5.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to real, verified files (references/mcp-testing.md, references/mock-openai-server.md, scripts/*), and the detailed setup content is appropriately split out rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

92%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, specific description that covers what the skill does and when to use it with concrete trigger phrases and third-person voice. The only soft spot is trigger-term breadth, which is good but not exhaustive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full surface — "running end-to-end tests", "headless mode", "MCP server testing", "API traffic inspection", "reproduce user-reported bugs end-to-end", "inspect raw API request/response payloads" — giving comprehensive coverage rather than the minor gaps of a 4.	5 / 5
Completeness	Explicitly answers both what ("Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection") and when ("Use this skill whenever you need to verify CLI behavior...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Trigger on mentions of E2E testing, headless testing, MCP tool testing, or reproducing issues" gives good natural-term coverage with synonyms, but stops short of the comprehensive term list (e.g. variations/extensions) that would merit a 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a narrow niche (Qwen Code CLI E2E testing) with distinct, specific triggers, so it is unlikely to fire for the wrong skill.	5 / 5
	Total	19 / 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: .qwen/skills/e2e-testing/SKILL.md
Commit: 054eabb

Reviewed: 1 day 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.