qwen-prompting

Qwen Prompting

Use this skill when qwen:qwen-rescue needs to ask Qwen Code for help.

Prompt Qwen like an operator, not a collaborator. Keep prompts compact and block-structured with XML tags. State the task, the output contract, the follow-through defaults, and the small set of extra constraints that matter.

Core rules:

• Prefer one clear task per Qwen run. Split unrelated asks into separate runs.
• Tell Qwen what done looks like. Do not assume it will infer the desired end state.
• Add explicit grounding and verification rules for any task where unsupported guesses would hurt quality.
• Prefer better prompt contracts over raising reasoning or adding long natural-language explanations.
• Use XML tags consistently so the prompt has stable internal structure.
• Qwen Code's default models (qwen3.5-plus, qwen3-max, qwen3-coder-plus) are strong at code edits and tool use but prefer explicit contracts. Spell out file boundaries, acceptance criteria, and stop conditions.

Default prompt recipe:

• <task>: the concrete job and the relevant repository or failure context.
• <structured_output_contract> or <compact_output_contract>: exact shape, ordering, and brevity requirements.
• <default_follow_through_policy>: what Qwen should do by default instead of asking routine questions.
• <verification_loop> or <completeness_contract>: required for debugging, implementation, or risky fixes.
• <grounding_rules> or <citation_rules>: required for review, research, or anything that could drift into unsupported claims.

When to add blocks:

• Coding or debugging: add completeness_contract, verification_loop, and missing_context_gating.
• Review or adversarial review: add grounding_rules, structured_output_contract, and dig_deeper_nudge.
• Research or recommendation tasks: add research_mode and citation_rules.
• Write-capable tasks: add action_safety so Qwen stays narrow and avoids unrelated refactors.

How to choose prompt shape:

• There is no dedicated review/adversarial-review command in v0.1 of this plugin. For review-style work, send a task prompt with a <task>Review ...</task> block plus a strict <structured_output_contract>.
• Use task when the task is diagnosis, planning, research, or implementation and you need to control the prompt directly.

Working rules:

• Prefer explicit prompt contracts over vague nudges.
• Use stable XML tag names.
• Do not raise reasoning or complexity first. Tighten the prompt and verification rules before escalating.
• Ask Qwen for brief, outcome-based progress updates only when the task is long-running or tool-heavy.
• Keep claims anchored to observed evidence. If something is a hypothesis, say so.

Prompt assembly checklist:

1. Define the exact task and scope in <task>.
2. Choose the smallest output contract that still makes the answer easy to use.
3. Decide whether Qwen should keep going by default or stop for missing high-risk details.
4. Add verification, grounding, and safety tags only where the task needs them.
5. Remove redundant instructions before sending the prompt.