simplify-and-harden

Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work.

Ensures alignment between user and Claude during feature/spec planning through a structured interview process.

Captures learnings, errors, corrections, and feature requests to enable continuous improvement.

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it.

Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth.

Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then…

Frames coding-agent work sessions with explicit intent capture and drift monitoring.

[Beta] Retrieves task-relevant prior sessions and returns a short, cited brief of decisions, corrections, failed approaches, and unresolved work.

[Beta] Cross-session analysis of accumulated .learnings/ files.

[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows).

[Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows).

Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements.