athola/qwen-delegation
Delegates tasks to Qwen CLI via delegation-core for Alibaba's models. Use when delegation-core selects Qwen or large-context batch processing is needed.
npx skills add https://github.com/athola/claude-night-market --skill qwen-delegation
This skill implements conjure:delegation-core for the Qwen CLI.
It provides Qwen-specific authentication, quota management,
and command construction.
For shared delegation patterns, see Skill(conjure:delegation-core).
Skill(conjure:delegation-core) determines Qwen is suitableqwen CLI is installed and configuredconjure:delegation-core)conjure:gemini-delegation)Installation:
# Install Qwen CLI
pip install qwen-cli
# Verify installation
qwen --version
# Check authentication
qwen auth status
# Login if needed
qwen auth login
# Or set API key
export QWEN_API_KEY="your-key"
Verification: Run python --version to verify Python environment.
# Basic file analysis
python ~/conjure/tools/delegation_executor.py qwen "Analyze this code" --files src/main.py
# With specific model
python ~/conjure/tools/delegation_executor.py qwen "Summarize" --files src/**/*.py --model qwen-max
# With output format
python ~/conjure/tools/delegation_executor.py qwen "Extract functions" --files src/main.py --format json
# Basic command
qwen -p "@path/to/file Analyze this code"
# Multiple files
qwen -p "@src/**/*.py Summarize these files"
# Specific model
qwen --model qwen-max -p "..."
qwen -p "..." > delegations/qwen/$(date +%Y%m%d_%H%M%S).md
The shared delegation executor can auto-select the best service:
# Auto-select based on requirements
python ~/conjure/tools/delegation_executor.py auto "Analyze large codebase" \
--files src/**/* --requirement large_context
For Qwen-specific models, CLI options, cost reference,
and troubleshooting, see modules/qwen-specifics.md.
qwen --version and qwen auth status (or QWEN_API_KEY env var set) both exit 0before any task is delegated; missing installation or failed authentication is reported
and stops execution.
delegations/qwen/YYYYMMDD_HHMMSS.md (timestampformat matching the Quick Start example), and that file exists on disk after delegation.
conjure:delegation-core selected a different provider (Gemini or local), this skillis not invoked; Qwen delegation only runs when delegation-core explicitly routes to Qwen.
delegation_executor.py auto logs which provider was selected andwhy before executing the task, so the selection is auditable.
Take athola/qwen-delegation from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.