writing-great-skills

name	writing-great-skills
description	Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
disable-model-invocation	true

A skill exists to wrangle determinism out of a stochastic system. Predictability — the agent taking the same process every run, not producing the same output — is the root virtue; every lever below serves it.

Bold terms are defined in GLOSSARY.md; look them up there for the full meaning.

Invocation

Two choices, trading different costs:

• A model-invoked skill keeps a description, so the agent can fire it autonomously and other skills can reach it (you can still type its name too). It adds context load — the description sits in the window every turn. Mechanics: omit disable-model-invocation, and write a model-facing description with rich trigger phrasing ("Use when the user wants…, mentions…").
• A user-invoked skill strips the description from the agent's reach: only you, typing its name, can invoke it, and no other skill can. Zero context load, but it spends cognitive load — you are the index that must remember it exists. Mechanics: set disable-model-invocation: true; the description becomes a human-facing one-line summary, trigger lists stripped.

Pick model-invocation only when the agent or another skill must reach the skill on its own. If it only ever fires by hand, make it user-invoked and pay no context load.

When user-invoked skills multiply past what you can remember, that piled-up cognitive load is cured by a router skill: one user-invoked skill that names the others and when to reach for each.

Writing the description

A description does two jobs — state what the skill is, and list the branches that should trigger it. Every word adds context load, so prune it even harder than the body:

• Front-load the skill's leading word — the description is where it does its invocation work.
• One trigger per branch. Synonyms that rename a single branch are duplication ("build features using TDD … asks for test-first development" is one branch written twice). Collapse them; keep only genuinely distinct branches.
• Cut identity that's already in the body. Keep the description to triggers, plus any "when another skill needs…" reach clause.

Information hierarchy

A skill mixes two content types — steps and reference — freely: all steps, all reference, or both. The core decision is which to use and where each sits on the information hierarchy, a ladder ranked by how immediately the agent needs the material:

1. In-skill step — an ordered action in SKILL.md, the primary tier: what the agent does, in order. Each ends on a completion criterion, the condition that signals done. Make it checkable (can the agent tell done from not-done?) and, where it matters, exhaustive ("every modified model accounted for", not "produce a change list") — a vague criterion invites premature completion.
2. In-skill reference — a definition, rule, or fact in SKILL.md, consulted on demand. Often a legitimately flat peer-set (every rule of a review on one rung) — fine, not a smell. This skill is all reference.
3. External reference — reference pushed out of SKILL.md into a separate file, reached by a context pointer, loaded only when the pointer fires. Spans disclosed reference (a sibling file like GLOSSARY.md, still part of the skill) through fully external reference that lives outside the skill system and any skill can point at.

A demanding completion criterion drives thorough legwork — the digging the agent does within the work — whether or not the skill has steps, since "every rule applied" binds flat reference just as "every step done" binds a sequence.

Push too little down and the top bloats; push too much and you hide material the agent needs. That tension is the whole decision.

Progressive disclosure is the move down the ladder — out of SKILL.md into a linked file — so the top stays legible. Mechanics: a linked .md file in the skill folder, named for what it holds (this skill discloses its definitions to GLOSSARY.md). Each distinct way a skill is used is a branch — different runs taking different paths. Branching is the cleanest disclosure test: inline what every branch needs, push behind a pointer what only some branches reach. A context pointer's wording, not its target, decides when and how reliably the agent reaches the material.

Where the ladder decides how far down a piece sits, co-location decides what sits beside it: keep a concept's definition, rules, and caveats under one heading rather than scattered, so reading one part brings its neighbours with it.

When to split

Granularity is how finely you divide skills, and each cut spends one of the two loads, so split only when the cut earns it:

• By invocation — split off a model-invoked skill when you have a distinct leading word that should trigger it, or another skill must reach it. You pay context load for the new always-loaded description, so that independent reach has to be worth it.
• By sequence — split a run of steps when the steps still ahead (a step's post-completion steps) tempt the agent to rush the one in front of it (premature completion). Keeping them out of view encourages more legwork on the current task.

Pruning

• Single source of truth — keep each meaning in one authoritative place, so changing behaviour is a one-place edit.
• Relevance — check every line: does it still bear on what the skill does?
• No-ops — hunt sentence by sentence: run the no-op test on each sentence in isolation, and when one fails, delete the whole sentence rather than trim words. Be aggressive — most failing prose should go, not be rewritten.

Leading words

A leading word is a compact concept already in the model's pretraining that the agent thinks with while running the skill (e.g. lesson, fog of war, tracer bullets). Repeated through the text (or, for a strong one, used once), it accumulates a distributed definition and anchors a whole region of behaviour in the fewest tokens, by recruiting priors the model already holds.

It serves predictability twice. In the body it anchors execution: the agent reaches for the same behaviour every time the word appears. In the description it anchors invocation: when the same word lives in your prompts, docs, and code, the agent links that shared language to the skill and fires it more reliably.

Hunt for chances to refactor skills onto leading words. A triad spelled out at three sites (duplication), a description spending a sentence to gesture at one idea — each begs to collapse into a single token:

• "fast, deterministic, low-overhead" → tight — one quality restated, collapsed into a pretrained word (a tight loop).
• "a loop you believe in" → red — converts a fuzzy gate into a binary observable state (the loop goes red on the bug, or it doesn't).

You win twice: fewer tokens, and a sharper hook for the agent to hang its thinking on. Assume every skill carries restatements that leading words retire — go find them.

Failure modes

Use these to diagnose issues the user may be having with the skill.

• Premature completion — ending a step before it's genuinely done, attention slipping to being done. Defence, in order: sharpen the completion criterion first (cheap, local); only if it is irreducibly fuzzy and you observe the rush, hide the post-completion steps by splitting (the sequence cut).
• Duplication — the same meaning in more than one place. Costs maintenance and tokens, and inflates a meaning's prominence on the ladder past its real rank.
• Sediment — stale layers that settle because adding feels safe and removing feels risky. The default fate of any skill without a pruning discipline.
• Sprawl — a skill simply too long, even when every line is live and unique. Hurts readability and maintainability and wastes tokens. The cure is the ladder: disclose reference behind pointers, and split by branch or sequence so each path carries only what it needs.
• No-op — a line the model already obeys by default, so you pay load to say nothing. The test: does it change behaviour versus the default? A weak leading word (be thorough when the agent is already thorough-ish) is a no-op; the fix is a stronger word (relentless), not a different technique.