Create well-formed Claude agents with proper YAML frontmatter, system prompts, and examples. Use when user wants to create a new agent, customize Claude behavior, or needs help structuring an agent definition.
Instrument safety checks, content filters, and guardrails for agent outputs
Use when the user is exploring possibilities, asking for ideas, or expressing uncertainty. Trigger cues include "ideas", "alternatives", "what could we do", "brainstorm", "different approaches", "I'm not sure yet". Use this skill to generate distinct conceptual directions before any evaluation or refinement.
Manages Bob's persistent memory across sessions. Use when learning something new, having a meaningful conversation, reflecting on experiences, starting any significant task, or when context suggests something should be remembered for later.
Recognize and avoid 15 common AI fluency anti-patterns that undermine effectiveness: over-reliance, prompt magic thinking, verification theater, and more.
Azure AI Speech Fast Transcription - Transcribe contact center calls with speaker identification using stereo channel separation or mono diarization. Returns results synchronously and faster than real-time.
Verified information generation and validation
Standardize AskUserQuestion patterns and provide reusable question templates for batch optimization
Create new AI agent implementations for the Yui Protocol system. Use when adding agents like Yui, Eiro, Kanshi.
Orchestrate adversarial player-coach loop for high-quality code synthesis. Based on dialectical autocoding methodology.
python-telegram-bot library for building Telegram bots. Use for handlers, callbacks, inline keyboards, conversations, and bot commands.
Create or update the feature specification from a natural language feature description. Only invoke when user explicitly requests to create a specification, spec, or feature specification.
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
Amazon Bedrock Prompt Management for creating, versioning, and managing prompt templates with variables, multi-variant A/B testing, and flow integration. Use when creating reusable prompt templates, managing prompt versions, implementing A/B testing for prompts, integrating prompts with Bedrock Flows, optimizing prompt engineering, or building production prompt catalogs.
Standardizing and formatting datasets for Unsloth, including chat template conversion and synthetic data generation (triggers: chat templates, ShareGPT, Alpaca, conversation_extension, add_new_tokens, standardize_sharegpt, formatting_prompts_func).
A simple skill that should be used to respond to a user when the enter the phrase "hello world".
Create a new AFI skill in afi-skills from a canonical template, including SKILL.md and initial eval stubs, while keeping domains, risk levels, and determinism aligned with existing patterns.
Use when you notice a pattern that should be in the config. Analyzes current setup, researches best practices, and proposes specific config changes. Also use when asked to improve agent behavior or workflows.
Assembles relevant context for agent spawns with prioritized ranking. Ranks packages by relevance, enforces token budgets with graduated zones, captures error patterns for learning, and supports configurable per-agent retrieval limits.
Build new agent skills. Use when creating diagnostic frameworks, CLI tools, or data-driven generators that follow the established skill patterns.
