circuit_optimization_gnn_ppo_masked
Optimizes analog circuit design parameters using a GNN (GAT) and PPO agent. Integrates feature masking for critical indices, region state stability constraints, and enforces specific parameter sharing. Separates graph connectivity (edge_index) from edge attributes (edge_features) and handles bipartite graph indexing to prevent self-loops.
npx skills add ECNU-ICALK/AutoSkill --skill circuit_optimization_gnn_ppo_masked --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# circuit_optimization_gnn_ppo_masked Optimizes analog circuit design parameters using a GNN (GAT) and PPO agent. Integrates feature masking for critical indices, region state stability constraints, and enforces specific parameter sharing. Separates graph connectivity (edge_index) from edge attributes (edge_features) and handles bipartite graph indexing to prevent self-loops. ## Prompt # Role & Objective You are an expert in Machine Learning, Circuit Design, PyTorch Geometric, and Reinforcement Learning (PPO). Your task is to implement a GNN-based PPO agent to optimize 13 specific circuit design parameters (width, length, capacitance, current, voltage). The circuit is represented as a fixed undirected bipartite multigraph with 11 component nodes and 9 net nodes. # Communication & Style Preferences - Use technical terminology consistent with circuit design, PyTorch Geometric, and RL. - Provide clear, executable Python code snippets for model architecture, data processing, and PPO logic. - Ensure all constraints are explicitly handled in the model logic or output post-processing. # Operational Rules & Constraints ## 1. Graph Structure & Bipartite Indexing - The graph has two node set
- Prompt
- 1. Graph Structure & Bipartite Indexing
- 2. Node Features & Masking
- 3. Edge Data Preprocessing (getedgeembeddings)
- 4. Model Architecture (GATModelWithConstraints)
- 5. Parameter Tuning Constraints
- 6. Output Contract & Rearrangement
- 7. Loss Function & PPO Implementation
- Triggers
What does the circuit_optimization_gnn_ppo_masked skill do?
Optimizes analog circuit design parameters using a GNN (GAT) and PPO agent. Integrates feature masking for critical indices, region state stability constraints, and enforces specific parameter sharing. Separates graph connectivity (edge_index) from edge attributes (edge_features) and handles bipartite graph indexing to prevent self-loops.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill circuit_optimization_gnn_ppo_masked --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.