For fetching Rust/crate information, use this priority order:

Feature planning with 4 phases - Specify requirements, Design architecture, break into granular Tasks, Implement and Validate. Creates atomic tasks that agents can implement without errors. Triggers on "plan feature", "design", "new feature", "implement feature", "create spec".

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.

Amazon Bedrock AgentCore Policy for defining agent boundaries using natural language and Cedar. Deterministic policy enforcement at the Gateway level. Use when setting agent guardrails, access control, tool permissions, or compliance rules.

Structured multi-perspective debate for important architectural decisions and complex trade-offs

LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns, and persistent state management. Use for complex AI orchestration, agent coordination, and production-grade agentic systems.

Use when implementing complex multi-step tasks, fixing critical bugs, or when quality and completeness matter more than speed - ensures comprehensive implementation without shortcuts through systematic analysis, implementation, and verification phases

This skill provides guidance for training FastText text classification models with constraints on accuracy and model size. It should be used when training fastText supervised models, optimizing model size while maintaining accuracy thresholds, or when hyperparameter tuning for text classification tasks.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.

Redis-backed SSE stream management with stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process.

Personal knowledge management for Obsidian combining GTD, Zettelkasten, and PARA. Six workflows: (1) Capture - "capture this", "remember this", "save this thought", "note this down" - saves thoughts/tasks to daily inbox without categorization; (2) Process inbox - "process my inbox", "organize captures", "GTD processing" - clarifies items and routes to projects or permanent notes; (3) Daily plan - "plan my day", "what should I work on", "morning planning" - creates prioritized task list based on energy and context; (4) Daily closeout - "daily closeout", "review my day", "evening reflection" - marks progress and drafts tomorrow's plan; (5) Setup - "set up my second brain", "configure vault" - configures vault path and user goals; (6) Excalidraw - "create a diagram", "visualize this", "draw flowchart", "sketch this" - creates .excalidraw.md files with rectangles, ellipses, diamonds, arrows, lines, and text. Proactively offers to capture valuable insights during research conversations.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Expert developer experience optimizer specializing in build performance, tooling efficiency, and workflow automation. Masters development environment optimization with focus on reducing friction, accelerating feedback loops, and maximizing developer productivity and satisfaction.

python's package managing

Comprehensive guide to integrating DSPy with Microsoft Agent Framework in AgenticFleet, covering typed signatures, assertions, routing cache, GEPA optimization, and agent handoffs.

Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.

QA harness for LLM agents: scenario suites, flake controls, tool sandboxing, LLM-as-judge scoring, and regression protocols.

Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.

Create, edit, and manage Copilot Studio agent YAML files — topics, actions, knowledge sources, triggers, variables, and more.