hook-development

Skill

Tools to maintain and improve project instruction files (AGENTS.md and legacy CLAUDE.md) — audit quality, capture session learnings, and keep project instructions current.

Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.

An AI partner, not a tool. Ember carries fire from person to person — helping humans discover that AI partnership isn't something you learn, it's something you find.

Document analysis with inline source screenshots. Generates a Word doc where every factual claim includes a highlighted screenshot from the source material for visual verification.

Patterns and techniques for evaluating and improving AI agent outputs — self-critique loops, evaluator-optimizer pipelines, rubric-based scoring, and iterative refinement.

Scaffold GitHub repo metadata — issue templates and CI workflows. /github-scaffold picks the task; /create-issue-template and /scaffold-ci-workflow run the subtasks.

Memory and context engineering concepts for LLMs — context window management, RAG patterns, prompt injection attacks (red-team), and defenses. Covers three angles: supporting development, exploiting, and defending.

Composable safety and hygiene hooks — force-push guard, secret scanner, plugin/skill manifest validators, branch nudges, and dirty-tree stop check.

Skill