context-compression
Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
395 skills found
Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.
Syntax and construction guide for HashQL J-Expr queries, supporting #literal, #struct, #list, and function call patterns for HashQL files.
A runtime skill discovery engine for AI agents. Search and retrieve specialized agent skills (SKILL.md) on-demand via REST API or MCP to inject procedural knowledge into your agent's context.
Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.
A comprehensive framework for creating, structuring, and managing reusable AI Agent Skills to standardize instruction-driven workflows.
Generate diverse landing page narrative angles, define target audiences, and specify required evidence for conversion-focused marketing workflows.
Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.
A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.
Track exercise reps like pushups and squats for the Peon Trainer. Log progress directly through your AI agent to trigger voice lines and stay motivated while coding.
Expert code review agent that performs systematic audits of git changes for SOLID violations, security vulnerabilities, performance regressions, and architectural smells.
Legacy alias for the pull request creation workflow. Redirects to sentry-skills:pr-writer to ensure standard PR writing practices are followed.
Format and lint JS, TS, and JSON files on the current branch using Biome. Useful for code cleanup before commits or PRs.