Total 31,160 skills, AI & Machine Learning has 5043 skills
Showing 12 of 5043 skills
Rewrite AI-sounding text into natural, human writing by removing common LLM patterns while preserving meaning and tone.
Multi-agent review of implementation plans. Use after creating a plan but before implementing, especially for complex or risky changes.
Monitor running agent loops, triage failures, clean up after completion, and decide when to intervene. Use when a loop is running and needs babysitting, when a loop just finished and needs post-merge verification, when stories are skipping/failing and need diagnosis, or when stale test artifacts need cleanup. Triggers on: 'check the loop', 'what happened with the loop', 'loop finished', 'clean up after loop', 'why did that story skip', 'monitor loop', 'nanny the loop', or any post-start loop management task. Distinct from agent-loop skill (which handles starting loops).
AI situational awareness — internal threat detection for hallucination risk, scope creep, and context degradation. Maps Cooper color codes to reasoning states and OODA loop to real-time decisions. Use during any task where reasoning quality matters, when operating in unfamiliar territory, after detecting early warning signs such as an uncertain fact or suspicious tool result, or before high-stakes output like irreversible changes or architectural decisions.
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.
Comprehensive guide to AI SDK v6 for agent development, tool definitions, multi-step agentic workflows, and result extraction patterns
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
Browse and search the Hence gallery (hence.sh) to discover projects built with AI coding agents. Use when the user wants inspiration, wants to see what others have built, asks about projects on Hence, or mentions searching for AI-built projects. Triggers on queries like "show me cool projects", "search Hence", "find CLI tools on Hence", or "what are people building with Claude Code".
Analyze and correct previous responses when questioned or when contradictions are detected. Use this skill when the user challenges your reasoning, points out inconsistencies, or asks 'what makes you think that?' to help you review your logic, identify errors in your previous statements, and provide accurate corrections. Useful for maintaining consistency, admitting mistakes, and rebuilding trust through transparent self-evaluation.
Model Context Protocol (MCP) server development and AI/ML integration patterns. Covers MCP server implementation, tool design, resource handling, and LLM integration best practices. Use when developing MCP servers, creating AI tools, integrating with LLMs, or when asking about MCP protocol, prompt engineering, or AI system architecture.
Scoped CLAUDE.md memory system that reduces context token spend. Creates directory-level context files, tracks savings via dashboard, and routes agents to the right sub-context.
Multi-AI Parallel Deep Research. Triggered when users need comprehensive research, in-depth study, multi-party comparison, or comprehensive analysis covering multiple dimensions and sources for a certain topic. Suitable for complex topics (technical selection, competitor analysis, industry trends, controversial topics, etc.), not suitable for simple fact queries. Conduct parallel research through multiple AI services, cross-validate, and output a comprehensive report with citations.