Lean imperative prose that assumes Claude's competence; it never explains what skills or agents are, and each line (gates, rationalization table, step constraints) earns its tokens.

Concrete, executable guidance throughout — named commands (tessl review run, tessl whoami, determinize-skill), exact thresholds (>=85%, --threshold 85), and specific file paths rather than vague direction.

A Mermaid flowchart plus numbered steps with explicit validation checkpoints (RED baseline -> GREEN verify -> REFACTOR loop -> quality gates table) provide clear sequencing and feedback loops for error recovery.

A single self-contained SKILL.md with no bundle files, well-organized into sections (Process, Step Details, Quality Gates, Rationalizations, Common Mistakes) and no nested references, satisfying the well-organized-structure anchor.

Lists multiple concrete actions — "creating a new skill, writing a skill from scratch, or converting a process into a reusable skill — enforces TDD, empirical validation, and quality monitoring" — matching the anchor for naming several specific actions.

Explicitly answers both what it does and when to use it via the "Use when..." trigger clause plus the concrete capabilities, satisfying the top anchor.

Natural user phrasing is well covered ("create a new skill", "writing a skill", "convert a process into a reusable skill"), terms a user would actually say, not jargon.

The skill-creation/TDD/empirical-validation niche is distinct and unlikely to trigger for unrelated skills, matching the clear-niche anchor.