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.
534 skills found
Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.
Reference for all MCP tools exposed by the CCOS server, enabling capability discovery, session management, and governed RTFS execution for autonomous agent workflows.
Synthesize interview transcripts into a structured template including Jobs to Be Done (JTBD), satisfaction signals, and actionable items.
Expert Rust development guide based on real-world code reviews. Ideal for idiomatic code, performance tuning, error handling, and avoiding common pitfalls in CLI and production tools.
Implement Extreme Programming (XP) practices including TDD, pair programming, and continuous integration to enhance team collaboration and technical excellence in software engineering.
Explains complex concepts using master teaching frameworks like Feynman, Socratic, and Cognitive Load theory to ensure deep, clear understanding.
Automated compliance validation tool for collector bot packages using 8 specialized parallel agents.
A specialized skill for generating high-quality technical documentation, code comments, API specs, and README patterns. Automates standard documentation workflows for C# and TypeScript projects.
Context Engineering agent skill to initialize, generate, and execute comprehensive implementation blueprints (PRPs) for one-pass software development.
An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.
Manages the OpenClaw release lifecycle: prepares branches, updates versioning across multiple platforms, generates changelogs, and orchestrates npm and binary artifact publishing.
Write INVEST-compliant user stories with testable Given-When-Then acceptance criteria to bridge the gap between requirements and development.