Browse Skills

Configure ECC interactively installs selected skills and rules from Everything Claude Code into user-level or project-level Claude Code directories, verifies paths, and offers optimization advice. Use it when setting up, fixing, or optimizing an Everything Claude Code installation.

Continuous Learning observes Claude Code sessions and turns recurring patterns into atomic, confidence-scored instincts that evolve into skills, commands, or agents. Use it to set up automatic learning, manage project-scoped versus global instincts, and export or import learned behaviors.

Continuous Learning automatically evaluates Claude Code sessions at the end and extracts reusable patterns as learned skills for future use. Use it when setting up a Stop hook to capture error resolutions, user corrections, workarounds, debugging techniques, and project conventions.

Cost-Aware LLM Pipeline combines model routing, budget tracking, retry logic, and prompt caching to control LLM API costs. Use it in applications that call Claude or OpenAI APIs to route simple tasks to cheaper models, stay within budget, and retry only transient errors.

Eval Harness provides a formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles. Use it to define pass/fail criteria, measure agent reliability with pass@k, and create regression test suites.

Foundation Models On-Device integrates Apple's FoundationModels framework for on-device generative AI on iOS 26. It covers text generation, @Generable structured output, custom tool calls, and snapshot streaming for privacy-sensitive or offline features.

Task Observer monitors multi-step agent sessions to capture user corrections, workflow patterns, and methodology gaps, then recommends new skills or improvements to existing ones. Use it during any tool-driven task or post-task feedback discussion to grow a skill library.

Adopt Vault scaffolds the Claude PKM system onto an existing Obsidian vault by scanning folder structure, interactively mapping folders to roles, and generating configuration files like settings.json and CLAUDE.md.

Onboard interactively sets up an Obsidian vault and loads hierarchical context for Claude Code sessions. Use it on first run to personalize the vault or on subsequent runs to load full project and area context.

GrepAI replaces built-in Grep and Glob tools with semantic code search and call-graph tracing, letting agents find code by intent instead of exact text. Use it before WebSearch, Grep, or Glob when exploring functionality, implementation details, or code relationships.

PGVector Semantic Search stores and searches vector embeddings in PostgreSQL using HNSW or IVFFlat indexes for semantic search, RAG, and nearest-neighbor queries. Use it to set up pgvector, tune recall and performance, or implement binary quantization for large datasets.

Postgres Hybrid Text Search combines BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Use it when building search that handles both exact terms and meaning, such as product names mixed with conceptual queries.