Helps you build AI agents that handle long sessions well, covering how to manage the context window, compress and hand off summaries, diagnose degraded performance, and evaluate agent output. Each part is a reusable skill you can apply to your own agent.
@muratcankoylanRuns an autonomous loop for SaaS content marketing and copywriting, with commands to initialize, run, check status, and cancel it. A stop hook keeps the loop going when an agent stops.
@muratcankoylanThis skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric…
@muratcankoylanThis skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief…
@muratcankoylanThis skill should be used when long-running agent sessions need context compression, structured summarization, compaction,…
@muratcankoylanThis skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context…
@muratcankoylanThis skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the…
@muratcankoylanThis skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy,…
@muratcankoylanUse this skill when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content…
@muratcankoylanThis skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional…
@muratcankoylanThis skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time…
@muratcankoylanThis skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable…
@muratcankoylanThis skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding…
@muratcankoylanThis skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\",…
@muratcankoylanCancel the active Ralph Marketer loop
@muratcankoylanInitialize a new Ralph Marketer project in the current directory
@muratcankoylanStart the Ralph Marketer autonomous copywriter loop
@muratcankoylanCheck the content pipeline status for Ralph the Marketer
@muratcankoylanIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
