Loading...
Loading...
Found 91 Skills
Claude Code skill that makes AI agents respond in caveman-speak, cutting ~65-75% of output tokens while preserving full technical accuracy
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
Read-only audit of a Claude Code environment: CLAUDE.md size, MCP servers and tool deferral, model/effort settings, hooks, subagents, scheduled jobs, and prompt-cache behavior in the newest session log. Returns one ranked table of findings and a single highest-leverage fix. Use whenever the user asks why Claude Code is expensive, burning tokens or usage limits, hitting context limits, compacting too often, or has a low cache hit rate, or asks for a context, token, or cost audit, even if they never say 'context audit'.
Create production-ready skills from expert knowledge. Extracts domain expertise and system ontologies, uses scripts for deterministic work, loads knowledge progressively. Use when building skills that must work reliably in production.
Workflow for repository reconnaissance and operations using GitHub CLI (gh). Optimizes token usage by using structured API queries instead of blind file fetching.
Learn how to manage conversation context in AMCP to avoid LLM API errors from exceeding context windows. This skill covers SmartCompactor strategies, token estimation, configuration, and best practices.
Advanced search options in GrepAI. Use this skill for JSON output, compact mode, and AI agent integration.
Context compression and summarization methodology. Techniques for reducing token usage while preserving decision-critical information.
Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID. Optimized for low-token, file/line-based handoff.
Document debugging sessions with hypothesis tracking and knowledge base
Manage ECC skill loading — defer unused skills to save init tokens, restore on demand. Use when user wants to check, defer, or restore ECC skills.
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of extending context beyond the window via filesystem strategies.