Find the perfect skill

Data & AI

Build and deploy production ML systems with PyTorch, TensorFlow, and modern infrastructure.

Development

Safely modify Allbert's Rust source in an isolated worktree, run Tier A validation, and produce a patch.

Development

Persistent compounding memory for AI agents with MCP tools for session start/end, remember, recall, and check. Local markdown, Obsidian-compatible, with optional semantic search via Supabase.

Documentation

Extract historical content from STATE.md into cycle files (burst logs, adversary passes, session checkpoints, lessons). Slims STATE.md to <200 lines.

Development

Share durable, inspectable context and handoffs between AI agents using the local ECC Memory Vault. Save work state, transfer context, and search shared project knowledge.

Development

Implement backlogs through a feature-driven approach: read requirements, design, code, and document. Use for features, fixes, and improvements.

Data & AI

Deploy high-performance LLM APIs using vLLM's PagedAttention and continuous batching. Optimize latency/throughput, with OpenAI-compatible endpoints, quantization, and tensor parallelism.

Productivity

Analyzes gaps between the candidate profile and top-scoring job postings, and provides a prioritized learning plan.

Development

Skill to create a GitHub Pull Request from commits on the current branch. Handles push, title/body generation, and PR creation automatically without user confirmation unless issues arise.

Development

Create high-quality pull requests via gh pr create. Use when the user wants to create a PR, submit a PR, open a pull request, submit for review, or push changes for review.

Development

Guide for implementing tasks using Conductor's TDD workflow, managing phase checkpoints, git commits, and verification protocol.

DevOps

Executes DAG waves with controlled parallelism using the Task tool. Manages concurrent agent spawning, resource limits, and execution coordination.