writing-skillslisted

# Writing Skills The reader of every skill is an agent. A line earns its place only if it changes the agent's behaviour versus what it would do anyway — text the agent already knows, filler, and repetition are bloat. Apply that test to every line you write. The same test scales up. Prefer the simplest thing that fixes an observed failure — often that is nothing at all: if the model already handles the task well, don't write the skill; if a line answers an imagined problem, don't write the line. Simple beats clever, and YAGNI applies to skills as much as to code. If the skill's intent, triggers, or location (personal `~/.claude/skills/`, project `.claude/skills/`, or a plugin's `skills/`) are unclear, ask before writing. ## How skills load Three tiers drive every design decision: 1. **Always in context:** every installed skill's `name` and `description` (plus `when_to_use` if set), ~100 tokens each. The listing caps `description` + `when_to_use` at 1,536 chars combined; when the total listing budget overflows, least-used skills' descriptions are truncated first (`/doctor` shows this). At library scale, every description word is a recurring cost. 2. **On trigger:** the SKILL.md body. Keep under ~500 lines / ~5,000 tokens. 3. **On demand:** bundled files, loaded only when referenced. Free until read. ## Workflow ### Step 1 — Choose the invocation mode first Decide before writing anything else; it shapes the description and the body: - **Model-invoked** (default): the a