What problem does it solve? Turning a half-formed idea into a lean, outcome-driven AI skill is hard: most generated skills ship bloated instructions, generic procedure, and no evidence they beat the bare model. This Skill guides the full lifecycle of building, editing, and quality-analyzing skills so every line earns its place. ## Core Features & Use Cases - Build and Edit Flow: Scaffolds new skills from a template via init_skill.py, hardens vague ideas through questioning, captures decisions in a memlog, and applies an earn-its-place test to every line. - Analyze Scanners: Runs deterministic pre-pass scripts (token metrics, workflow integrity, frontmatter lint) plus LLM lenses, then renders a self-contained HTML and Markdown report with severity-graded findings. - Customization Surface: Optionally emits a customize.toml with three-layer merge rules (base, team, personal overrides) for activation hooks, persistent facts, and output paths. - Use Case: Point it at an existing skill and say "analyze" to get a graded HTML report on leanness, structure, and frontmatter conformance, or describe a new workflow idea and have it scaffolded, eval-tested, and linted before handoff. ## Quick Start Ask the assistant to build a new skill from your idea, or give it the path to an existing skill and ask it to analyze or edit that skill.
