3,748 tools found
Diagnoses LLM context degradation - lost-in-middle, poisoning, distraction, confusion, and clash - with benchmarks and mitigation patterns.
Skill for treating project context as a managed artifact alongside code, with 5 canonical docs and a Context to Spec to Plan to Implement workflow.
Foundational concepts for context engineering - the anatomy of context, attention budget constraints, and progressive disclosure for agent systems.
An elite context engineering specialist for dynamic context assembly, vector/knowledge-graph retrieval, memory systems, and multi-agent orchestration.
Compaction, observation masking, KV-cache reuse, and context partitioning techniques that extend an LLM agent effective context capacity.
Skill documenting LLM context-window strategies: tiered routing, serial-position optimization, importance-based summarization, and token budgets.
Fetches current library and framework documentation through Context7 for research in Claude Code conversations.
Skill for designing tiered LLM conversation memory - buffer, short-term, long-term, entity - with consolidation and user isolation.
Automates ConvertKit (Kit) subscriber management, tagging, and broadcast operations through Composio's Kit toolkit via Rube MCP.
Build apps that programmatically interact with GitHub Copilot via the Copilot SDK - sessions, custom tools, hooks, MCP servers, and streaming.
A copy-editing skill built on the Seven Sweeps Framework - clarity, voice, benefit-framing, proof, specificity, emotion, risk.
A conversion copywriting skill with a mandatory context-gathering and brief-confirmation gate before writing honest, testable, benefit-led marketing copy.
