pskoett publishes skills that help AI agents plan and validate software work, including a plan-interview workflow for scoping features before implementation, a skill tester that checks other skills against the Agent Skills spec, and a pipeline orchestrator that routes coding tasks to the right skills. Their work also covers agent infrastructure, with an MCP builder guide for creating servers that connect LLMs to external APIs in Python and TypeScript, and a control-session orchestrator for coordinating multiple agent sessions. A distinctive thread is attention to process, from interviews and session history to cross-session learning aggregation in CI.
Self Improving Agent
1 skills · 790 stars
Self Improving Agent Captures and maintains learnings, errors, and corrections.
Pskoett Ai Skills
41 skills · 329 stars
Context Decay Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it c…
Context Decay Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it c…
Context Surfing Monitors context window health during large, long-running, multi-session, or explicitly context-s…
Context Surfing Monitors context window health during large, long-running, multi-session, or explicitly context-s…
Control Session Orchestrator Control-plane workflow for coordinating multi-agent, multi-session project work from a single Cod…
Control Session Orchestrator Control-plane workflow for coordinating multi-agent, multi-session project work from a single Cod…
Eval Creator [Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them.
Eval Creator [Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them.
Eval Creator Ci [Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows).
Eval Creator Ci [Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows).
Export Data Export local records using ExportTool.
Intent Framed Agent Frames coding-agent work sessions with explicit intent capture and drift monitoring.
Intent Framed Agent Frames coding-agent work sessions with explicit intent capture and drift monitoring.
Learning Aggregator [Beta] Cross-session analysis of accumulated .learnings/ files.
Learning Aggregator [Beta] Cross-session analysis of accumulated .learnings/ files.
Learning Aggregator Ci [Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows).
Learning Aggregator Ci [Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows).
Mcp Builder Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact…
Plan Interview Ensures alignment between user and Claude during feature/spec planning through a structured inter…
Plan Interview Ensures alignment between user and Claude during feature/spec planning through a structured inter…
Pre Flight Check [Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before…
Pre Flight Check [Beta] Session-start scan that surfaces relevant learnings, recent errors, and eval status before…
Self Healing Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root caus…
Self Healing Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root caus…
Self Healing Ci CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery…
Self Healing Ci CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery…
Self Improvement Captures learnings, errors, corrections, and feature requests to enable continuous improvement.
Self Improvement Captures learnings, errors, corrections, and feature requests to enable continuous improvement.
Self Improvement Ci CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows).
Session Context [Beta] Retrieves task-relevant prior sessions and returns a short, cited brief of decisions, corr…
Session Context [Beta] Retrieves task-relevant prior sessions and returns a short, cited brief of decisions, corr…
Simplify And Harden Post-completion self-review for coding agents that runs simplify, harden, re-verification, and mi…
Simplify And Harden Post-completion self-review for coding agents that runs simplify, harden, re-verification, and mi…
Simplify And Harden Ci CI-only Simplify & Harden workflow for pull requests using gh-aw (GitHub Agentic Workflows).
Skill Creator Guide for creating effective skills.
Skill Pipeline Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct c…
Skill Pipeline Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct c…
Skill Tester Validates all interactive skills in this repo against the Agent Skills spec, project conventions,…
Skill Tester Ci Validates all CI skills in this repo.
Verify Gate Runs project compile, test, and lint commands between implementation and quality review.
Verify Gate Runs project compile, test, and lint commands between implementation and quality review.