Skip to content

Commit e48fa19

Browse files
mhenkeqwencoder
andcommitted
docs: add Qwen Code CLI task() syntax to subagent skills
- dispatching-parallel-agents: Add Qwen task() examples alongside Claude Task() - requesting-code-review: Add Qwen task() dispatch syntax - writing-skills: Add Qwen task() syntax for testing examples Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
1 parent 6a927c0 commit e48fa19

File tree

3 files changed

+35
-0
lines changed

3 files changed

+35
-0
lines changed

skills/dispatching-parallel-agents/SKILL.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -63,6 +63,14 @@ Each agent gets:
6363

6464
### 3. Dispatch in Parallel
6565

66+
```python
67+
# In Qwen Code CLI environment
68+
task(subagent_type="general-purpose", description="Fix agent-tool-abort.test.ts failures")
69+
task(subagent_type="general-purpose", description="Fix batch-completion-behavior.test.ts failures")
70+
task(subagent_type="general-purpose", description="Fix tool-approval-race-conditions.test.ts failures")
71+
# All three run concurrently
72+
```
73+
6674
```typescript
6775
// In Claude Code / AI environment
6876
Task("Fix agent-tool-abort.test.ts failures")

skills/requesting-code-review/SKILL.md

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,23 @@ HEAD_SHA=$(git rev-parse HEAD)
3131

3232
**2. Dispatch code-reviewer subagent:**
3333

34+
**For Qwen Code CLI:**
35+
```python
36+
task(
37+
subagent_type="code-reviewer",
38+
description="Code review for [feature]",
39+
prompt="""
40+
WHAT_WAS_IMPLEMENTED: [What you just built]
41+
PLAN_OR_REQUIREMENTS: [What it should do]
42+
BASE_SHA: [Starting commit]
43+
HEAD_SHA: [Ending commit]
44+
DESCRIPTION: [Brief summary]
45+
"""
46+
)
47+
```
48+
49+
**For Claude Code:**
50+
3451
Use Task tool with superpowers:code-reviewer type, fill template at `code-reviewer.md`
3552

3653
**Placeholders:**

skills/writing-skills/SKILL.md

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -541,6 +541,16 @@ Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:
541541
- What rationalizations did they use (verbatim)?
542542
- Which pressures triggered violations?
543543
544+
**For Qwen Code CLI:**
545+
```python
546+
task(subagent_type="general-purpose", description="Test pressure scenario")
547+
```
548+
549+
**For Claude Code:**
550+
```typescript
551+
Task("Test pressure scenario")
552+
```
553+
544554
This is "watch the test fail" - you must see what agents naturally do before writing the skill.
545555

546556
### GREEN: Write Minimal Skill

0 commit comments

Comments
 (0)