菜单
Find and test free OpenRouter models. Lists available free models, tests their availability, and selects the best working model for code generation tasks. Use this before spawning agents to select cost-effective models.
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
Apple Silicon optimization for VMs, ML inference, and compression. Covers Metal GPU acceleration, MLX model inference, CoreML conversion, M-series zstd compression, Apple Virtualization Framework, and performance tuning.
Query Datadog APM traces, logs, metrics, SLOs, security signals, and service catalog. Create monitors, dashboards, and synthetic tests. Manage incidents and workflows. Use when investigating performance issues, searching logs, checking SLOs, analyzing costs, or automating Datadog operations.
Helm and Kubernetes deployment operations for ACR/AKS production, KIND local development, and resource management. Use for deploying charts, managing pods/services, configuring ingress, and troubleshooting K8s workloads.
Run Datadog Code Security scans — SAST, SAIST (AI-native SAST), SCA, secrets, IaC scanning, plus supply-chain protection (GuardDog, Supply-Chain Firewall) and IDE runtime defense (IDE Shepherd). Integrates via Code Security MCP Server for real-time scanning in Claude Code, Cursor, and VS Code. Use when asked to scan code for vulnerabilities, run a security audit, find bugs via static analysis, check dependencies for known CVEs, or protect against supply-chain attacks.
Editorial quality gate for i18n translations. Validates translation completeness, placeholder parity, terminology consistency, and wiring coverage across all locale files. Run before any PR that touches UI to prevent translation drift. Use when: adding new UI strings, modifying pages/components, or before releases.
VibeCode project conventions, patterns, and critical warnings. Preload into any agent working on this codebase.
| name | openrouter-models |
| description | Find and test free OpenRouter models. Lists available free models, tests their availability, and selects the best working model for code generation tasks. Use this before spawning agents to select cost-effective models. |
| author | gastown |
| version | 1.0.0 |
Find and test free models on OpenRouter to minimize costs while maintaining quality.
Set the OpenRouter API key:
export OPENROUTER_API_KEY="sk-or-v1-..."
Or the skill uses the default free-tier key.
python3 scripts/openrouter_free_model_selector.py --list
python3 scripts/openrouter_free_model_selector.py --test "qwen/qwen3-coder:free"
python3 scripts/openrouter_free_model_selector.py -v
MODEL=$(python3 scripts/openrouter_free_model_selector.py)
echo "Using: $MODEL"
python3 scripts/openrouter_free_model_selector.py --list --json
python3 scripts/openrouter_free_model_selector.py --json
deepseek/deepseek-r1-0528:free - DeepSeek R1 (best reasoning)qwen/qwen3-coder:free - Qwen Coder (optimized for code)meta-llama/llama-3.3-70b-instruct:free - Llama 3.3 70Bmistralai/mistral-small-3.1-24b-instruct:free - Mistral Smallgoogle/gemma-3-27b-it:free - Gemma 3 27BTo use with polecats:
# Select best free model
MODEL=$(python3 scripts/openrouter_free_model_selector.py)
# Configure for agent use
export OPENROUTER_MODEL="$MODEL"
If no free models work, falls back to:
anthropic/claude-3-haiku (cheap)openai/gpt-4o-mini (cheap)google/gemini-flash-1.5 (cheap)