context-degradation
Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
274 skills found
Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.
Automate video editing by using Whisper to transcribe and AI to identify filler words, pauses, and mistakes, then generating optimized FFmpeg commands for clean, professional cuts.
Transforms feature requests, bug reports, and improvement ideas into structured, actionable markdown project plans using repository research and industry best practices.
Convert PRDs, API docs, and requirements into structured acceptance, testing, integration, and launch checklists.
Intelligently migrate existing brownfield projects to the AgenticDev structure using AI-powered analysis to reorganize documentation, generate rich frontmatter, and preserve git history.
A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.
Analyzes markdown files to identify token-wasting patterns, providing actionable suggestions to optimize documentation for LLM consumption and token efficiency.
Create high-performance AI skills by reverse-engineering successful GitHub projects and proven open-source methodologies.
Guided statistical analysis with test selection, assumption checking, power analysis, and APA-formatted reporting for academic and experimental research.
AI-powered browser automation server for web interaction, data extraction, and research using the Model Context Protocol.
Draft competitive research proposals for NSF, NIH, DOE, DARPA, and NSTC. Master agency-specific criteria, budget preparation, visual schematics, and submission compliance.
Synthesize performance profiling data into actionable recommendations and evidence-backed technical decisions.