Loading...
Loading...
Found 2,493 Skills
Persistent key-value storage in IDA databases. Use when asked to store metadata, track progress, or persist session state via netnode_kv.
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
Set up or verify Husky git hooks to ensure all tests run and coverage stays above 80% (configurable) for Node.js/TypeScript projects. This skill should be used when users want to enforce test coverage through pre-commit hooks, verify existing Husky/test setup, or configure coverage thresholds for Jest, Vitest, or Mocha test runners.
Manage file storage operations in Supabase Storage. Use for uploading, downloading, listing, and deleting files in buckets.
Implement GraphRAG patterns combining knowledge graphs with retrieval for complex reasoning. Use this skill when building RAG over interconnected data or needing relationship-aware retrieval. Activate when: GraphRAG, knowledge graph, graph retrieval, entity relationships, Neo4j RAG, graph database, connected data.
Use when debugging 'files disappeared', 'data missing after restart', 'backup too large', 'can't save file', 'file not found', 'storage full error', 'file inaccessible when locked' - systematic local file storage diagnostics
Learn how to create an interactive, draggable DOM using a Lit web component with CSS transforms and slots, enabling you to manipulate HTML and SVG elements within a canvas-like environment.
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.
Audit test coverage for code changes. Identifies untested logic and provides specific test recommendations. Read-only analysis. Use before PR or after implementation. Triggers: review coverage, check tests, test coverage, are tests adequate.
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
Structured paragraph curation for C5: **select -> evaluate -> subset -> fuse**, so drafts converge instead of only expanding. **Trigger**: paragraph curator, curation, select evaluate fuse, paragraph selection, 选段, 评价, 融合, 收敛, 去冗余. **Use when**: you are in C5, `sections/*.md` exist, and the writing loop drifts toward 'longer by accumulation' (repetition, redundant paragraphs, weak synthesis). **Skip if**: evidence packs are thin / `evidence-selfloop` is BLOCKED; or you are pre-C2 (NO PROSE). **Network**: none. **Guardrail**: do not invent facts; do not add/remove citation keys; do not move citations across subsections; keep section-level claims consistent with `output/ARGUMENT_SKELETON.md# Consistency Contract`.