brainstorm-sync
Capture brainstorm discoveries that aren't in the plan — the thinking that makes this project unique
发现 编程开发 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Capture brainstorm discoveries that aren't in the plan — the thinking that makes this project unique
Two-phase codebase analysis. Phase 1: discover features from code. Phase 2: trace workflows.
Execute implementation plans one commit at a time. Follow the order from brainstorm, implement, test REAL, commit.
Autonomous overnight execution. Orchestrate subagents to implement a plan while human sleeps.
Workflow-first design through collaborative dialogue. Use before creating features, building components, or modifying behavior.
Research pipeline for topology-aware GNN representation learning on power grids using the PowerGraph benchmark. Use when (1) building physics-guided GNNs for power flow (PF), optimal power flow (OPF), or cascad...
Comprehensive IEEE PES paper review for Physics-Guided SSL GNN power grid research. Use when reviewing paper sections, checking claims against evidence, validating physics consistency (PF/Line Flow/Cascade), au...
Kumo development assistant for MySQL database management tool. Use when working on Kumo features, understanding architecture, writing tests, or navigating the codebase. Helps with React components, API endpoint...
Expert assistant for Kumo's Query Module (src/features/query). Use when working with SQL Editor, Monaco editor integration, query execution, result grids, tabs management, AI features, or any query-related comp...
Convert experiment results to Markdown research notes and optionally update research state with evidence
Analyze SAE decoder weights - output influence, feature importance, and decoder similarity
Run credibility checks on feature interpretations including split-half stability and shuffle null tests
Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments
Manage research state for SAE feature analysis including hypotheses, evidence tracking, and research history
Propose next mechanistic interpretability experiments based on research state, hypotheses, and existing evidence
Domain expert for Splatoon 3 competitive gear abilities and weapon meta. Use when: (1) Labeling or classifying gear build features from SAE analysis, (2) Understanding why specific ability combinations appear i...
Orchestrate a systematic research program to investigate and meaningfully label SAE features
Manage feature labeling workflow - queue management, label storage, similar features, progress tracking
Quick "first look" overview of SAE features - top tokens, activation stats, weapons, families, sample contexts
Reference catalog of recurring SAE feature patterns - check when labeling new features, add new patterns as discovered
Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identification
Execute mechanistic interpretability experiments from JSON specs - family sweeps, itemsets, interactions, minimal cores, validation
Match SAE features between Ultra (24K) and Full (2K) models based on activation patterns and token overlap
Reference for ability family semantic groupings and gameplay meanings
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。