Turn a feature idea or bug description into a GitHub issue, informed by relevant code and existing issues. It prepares an English draft with a Chinese translation, incorporates feedback, and submits it with labels after explicit approval.
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
Review the instructions the agent will receive before you install.
Take the user's idea or bug description, investigate the codebase for context, draft an issue for review, and submit once approved.
The user provides a brief description of a feature request or bug report via the skill argument.
Determine whether the request is a feature request or a bug report.
Search for relevant code, files, and existing behavior related to the request.
Build a thorough understanding of how the current system works. Note any related
existing issues found via gh issue list --search.
.github/ISSUE_TEMPLATE/feature_request.yml.github/ISSUE_TEMPLATE/bug_report.ymlUse the template's field labels and descriptions to structure the draft.
Write a markdown draft to .qwen/issues/draft-<slug>.md for the user to review.
Rules:
Write from the user's perspective — not as an implementation spec.
Keep language clear and concise; avoid internal implementation details.
Title stays in English only.
Bilingual body: English content first, Chinese translation at the end wrapped in a collapsible block:
<details>
<summary>中文</summary>
(Chinese translation here)
</details>
Present the draft. Iterate on feedback until the user is satisfied. Do not submit until the user explicitly approves.
When the user confirms, create the issue with gh issue create:
gh issue create --title "..." --body-file .qwen/issues/draft-<slug>.md
Apply labels based on type:
type/feature-request, status/needs-triagetype/bug, status/needs-triageReport the issue URL back to the user.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Write clear briefs for subagents and conversation forks, agents that inherit conversation history. Specify purpose, known findings, scope, and expected output while respecting each agent's existing role and separating research requests from implementation.
Compare a feature implemented in Qwen Code with Codex or Claude Code under the same scenario. Capture communication and terminal records, inspect tool definitions and outputs, and guide fixes toward matching observable behavior.
Reproduce a Codex or Claude Code feature in Qwen Code or another command-line agent. Capture requests, terminal output, and state changes, then use that evidence to implement focused behavior and add a verification path.
Review local uncommitted changes, verify findings, and repeat focused repairs until the review converges or a blocker remains. Also supports Qwen Code issue fixes and review responses within workflows run through GitHub Actions.
Apply the same operation across multiple files using parallel worker agents. The skill finds matching files, divides the work, and reports successes, failures, and skipped files, with a preview option before edits.
Prepare shared instructions for translating, rewriting, or extracting information from many independent files, then submit a plan through the DashScope Batch API. Processing runs asynchronously at half the realtime list price and delivers new files later.