Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or...
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation,...
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation,...
Academic research synthesis, paper analysis, and comprehensive literature reviews across disciplines
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash
Design and validate REST and GraphQL APIs with OpenAPI/GraphQL schema generation, security hardening, and OWASP API Security compliance.
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
Meta-skill for extracting and creating reusable Claude Code skills from past work sessions. Analyzes git history, code patterns, workflows, and documentation to identify harvestable skills, then...
Use when making decisions under time pressure or uncertainty, preventing errors in complex procedures, designing decision rules or checklists, simplifying complex choices, or when user mentions...
変数名改善、関数抽出、マジックナンバー定数化、デッドコード削除、コードレビュー。コードが読みにくい、リファクタリング、PRレビューが必要な時に使用。動作は変えない。
Interact with ClickUp tasks and documents - get task details, view comments, create and manage tasks, create and edit docs. Use when working with ClickUp task/doc URLs or IDs.
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations