一键导入
qwen-code-claw
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Design and specify banners for CKM projects across all platforms and formats. Activate when the user asks to create, design, or plan banners, social media covers, display ads, web heroes, or print materials. References references/banner-sizes-and-styles.md for the full size catalog and 22 art direction styles.
Identify, map, and optimize all conflicts within a Visual Story Planner StoryGraph. Always activate this skill when the user mentions: "conflict", "tension", "escalation", "antagonist dynamics", "analyze conflicts", "my story lacks tension", "how do conflicts connect", "conflict optimization", "subplot conflicts", or "is my conflict believable". Also use when the user asks why the story feels flat or stakes feel low — conflict analysis is almost always the answer. Produces a conflict map with type classification, escalation health score, interconnection diagram (as text), and specific improvement suggestions ranked by impact.
Expert story structure analysis using bl1nk-visual-mcp. Analyze story text, extract 3-act structure, characters, conflicts, relationships, and validate narrative structure. Activates for analyze story, story structure, story graph, validate story, character extraction, conflict analysis, narrative structure, story validation, three act structure.
Expert story visualization and export using bl1nk-visual-mcp. Export StoryGraph to Mermaid diagrams, Canvas JSON, Markdown, HTML dashboards, and MCP UI dashboards. Activates for export story, export mermaid, export canvas, story dashboard, story visualization, convert to mermaid, story markdown, story html.
Deep structural analysis of story graphs for Visual Story Planner projects. Use this skill whenever the user says "audit", "check structure", "analyze story structure", "is my story balanced", "review my plot", "structural report", or asks for feedback on three-act balance, pacing health, character arc completeness, or conflict escalation. Also activate when the user runs `validate_story_structure` and wants an explanation of results, or when story export output is present and they want a critique. IMPORTANT: Any export action (export_mermaid, export_canvas, export_dashboard, etc.) must be preceded by `validate_story_structure`. If validation reports any issues, surface them with severity levels (error / warning) and require explicit user acknowledgment before continuing to export. Block exports when blocking (error-level) issues exist unless the user explicitly confirms they accept the risk. This skill provides a four-phase audit (Structure → Characters → Conflicts → Pacing) with a scored health report and p
Extract and analyze themes, motifs, and symbolic patterns from story graphs. Always activate when the user mentions: "themes", "motifs", "symbolism", "symbolic meaning", "deeper meaning", "underlying message", "theme analysis", "recurring elements", "patterns in story", "symbolic objects", or asks about "what does this story mean", "what is the message", or "what themes are present". Also activate when user exports or validates story and wants to understand the thematic depth. This skill identifies explicit and implicit themes, tracks motif recurrence, and provides thematic arc analysis — not just a list of tags.
| name | qwen-code-claw |
| description | Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks |
Use this skill when you need to:
npm install -g @qwen-code/qwen-code
For normal session reuse, prefer a global install over npx.
Check if authentication is already configured:
qwen auth status
If authentication exists, skip this section. If not authenticated, check if the BAILIAN_CODING_PLAN_API_KEY environment variable exists:
echo $BAILIAN_CODING_PLAN_API_KEY
If BAILIAN_CODING_PLAN_API_KEY exists, authenticate directly:
qwen auth coding-plan --region china --key $BAILIAN_CODING_PLAN_API_KEY
If the environment variable does not exist, interrupt and prompt the user to authenticate via qwen-oauth or coding-plan:
qwen auth
Or configure custom API after launching Qwen Code via /auth.
You should always use acpx to run Qwen Code over the Agent Client Protocol (ACP) instead of scraping PTY sessions.
To use acpx:
Install acpx globally (recommended) or use npx:
npm install -g acpx@latest
Or without installing:
npx acpx@latest
Install the acpx skill for full reference:
npx acpx@latest --skill install acpx
Read the acpx skill reference for every command, flag, and workflow pattern: See the ACPX Reference section below for details
For complete CLI reference with all options and examples: https://raw.githubusercontent.com/openclaw/acpx/main/docs/CLI.md
From now on, when you need to delegate work to Qwen Code, use acpx instead of spawning raw terminal sessions. For example:
npx acpx@latest qwen "fix the failing tests"
npx acpx@latest qwen "refactor the auth module"
npx acpx@latest qwen exec "one-shot: summarize this repo"
Tip: You should typically use the
--approve-allflag to prevent task interruptions.
acpx qwen 'inspect failing tests and propose a fix plan'
acpx qwen 'apply the smallest safe fix and run tests'
acpx qwen exec 'summarize repo purpose in 3 lines'
acpx qwen -s backend 'fix API pagination bug'
acpx qwen -s docs 'draft changelog entry for release'
acpx qwen 'run full test suite and investigate failures'
acpx qwen --no-wait 'after tests, summarize root causes and next steps'
acpx --format json qwen 'review current branch changes' > events.ndjson
acpx --cwd ~/repos/my-project --approve-all qwen -s pr-123 \
'review PR #123 for regressions and propose minimal patch'
--approve-all: No interactive prompts--approve-reads (default): Auto-approve reads/searches, prompt for writes--deny-all: Deny all permission requestsIf every permission request is denied/cancelled and none are approved, acpx exits with permission denied.
--no-wait for long-running tasks to avoid blocking--approve-all for non-interactive batch operations--format json for automation and script integration--cwd to manage context across multiple projects| Command | Description |
|---|---|
/help | Show available commands |
/clear | Clear conversation history |
/compress | Compress history to save tokens |
/stats | Show session info |
/auth | Configure authentication |
/exit | Exit Qwen Code |
Full reference: https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/commands.md
Config files (highest priority first): CLI args > env vars > system > project (.qwen/settings.json) > user (~/.qwen/settings.json) > defaults. Format: JSONC with env var interpolation.
Key settings:
| Setting | Description |
|---|---|
model.name | Model to use (e.g. qwen-max) |
tools.approvalMode | plan / default / auto_edit / yolo |
permissions.allow/ask/deny | Tool permission rules |
mcpServers.* | MCP server configurations |
Full reference: https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/configuration/settings.md
Supports Qwen OAuth (browser-based, 1000 free requests/day) and OpenAI-compatible API keys.
Full reference: https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/configuration/auth.md
Configure custom model providers via modelProviders in settings or environment variables (OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL).
Full reference: https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/configuration/model-providers.md
| Feature | Description | Docs |
|---|---|---|
| Approval Mode | Control tool execution permissions | https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/approval-mode.md |
| MCP | Model Context Protocol server integration | https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/mcp.md |
| Skills | Reusable skill system via /skill | https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/skills.md |
| Sub-agents | Delegate tasks to specialized agents | https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/sub-agents.md |
| Sandbox | Secure code execution environment | https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/sandbox.md |
| Headless | Non-interactive / CI mode | https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/docs/users/features/headless.md |
Well-known agent names resolve to commands:
qwen → qwen --acp# Default (prompt mode, persistent session)
acpx [global options] [prompt text...]
acpx [global options] prompt [options] [prompt text...]
# One-shot execution
acpx [global options] exec [options] [prompt text...]
# Session management
acpx [global options] cancel [-s <name>]
acpx [global options] set-mode <mode> [-s <name>]
acpx [global options] set <key> <value> [-s <name>]
acpx [global options] status [-s <name>]
acpx [global options] sessions [list | new [--name <name>] | close [name] | show [name] | history [name] [--limit <count>]]
acpx [global options] config [show | init]
# With explicit agent
acpx [global options] <agent> [options] [prompt text...]
acpx [global options] <agent> prompt [options] [prompt text...]
acpx [global options] <agent> exec [options] [prompt text...]
Note: If prompt text is omitted and stdin is piped,
acpxreads prompt from stdin.
| Option | Description |
|---|---|
--agent <command> | Raw ACP agent command (fallback mechanism) |
--cwd <directory> | Session working directory |
--approve-all | Auto-approve all requests |
--approve-reads | Auto-approve reads/searches, prompt for writes (default) |
--deny-all | Deny all requests |
--format <format> | Output format: text, json, quiet |
--timeout <seconds> | Maximum wait time (positive integer) |
--ttl <seconds> | Idle TTL for queue owners (default: 300, 0 disables TTL) |
--verbose | Verbose ACP/debug logs to stderr |
Flags are mutually exclusive where applicable.