Kata GEMINI.md

Kata 1.1 ⚔️

Personal skill collection for Gemini CLI. Eight skills covering the complete engineering workflow: think, design, check, hunt, write, learn, read, health. Now with advanced Architecture, Security, and Synthesis modes.

Structure

skills/
├── RESOLVER.md   -- central trigger → skill routing table
├── check/        -- code review before merging
│   ├── agents/   -- reviewer-security.md, reviewer-architecture.md
│   └── references/  -- persona-catalog.md
├── design/       -- production-grade frontend UI
├── health/       -- Gemini CLI config audit
│   └── agents/   -- inspector-context.md, inspector-control.md
├── hunt/         -- systematic debugging
├── learn/        -- research to published output
├── read/         -- fetch URL or PDF as Markdown
├── think/        -- design and validate before building
└── write/        -- natural prose in English
    └── references/  -- write-en.md
.gemini-plugin/
  marketplace.json    -- plugin registry for npx/plugin distribution

Each skill has a SKILL.md (loaded on demand by Gemini). Supporting content lives in subdirectories. skills/RESOLVER.md is the human-readable index of "which trigger goes to which skill"; keep it in sync when you change a skill's scope.

Skill vs Script: Latent vs Deterministic

Before adding a new capability, decide which layer it belongs in. Kata's eight skills are all fat skills (Markdown carrying judgment). Anything that is pure verification, lookup, or table-driven enforcement belongs in scripts/ or rules/, not in a SKILL.md.

Question	YES →	NO →
Does the user need the model to think, adapt, or ask?	Skill	Script / rule
Does the same input always produce the same output?	Script / rule	Skill
Does it depend on the user's project environment?	Skill	Script / rule
Is it a lookup, list, or status check?	Script / rule	Probably skill
Does behavior shift with conversation context?	Skill	Script / rule