Capture a durable lesson, correction, or convention from this session as a reusable adept skill, then sync it to every harness. Apply when the user corrects you, when a fix generalizes, or when you say 'I'll remember that.'
Write a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running `adept agent add`.
Compose a loop — a scheduled system that discovers work, hands it to agents, verifies with an independent evaluator, persists state, and reschedules itself. Apply when the user wants automation that runs on a timer, a triage/babysitter routine, or asks about `adept loop add`.
Write a good, portable adept skill: pick the right activation, craft a triggering description, keep it scan-safe and within harness byte budgets. Apply when creating or editing a SKILL.md or running `adept skill add`.
Team expertise billboard via `adept exchange`: ask teammates for expertise and stack responses. Apply when the user wants a colleague's input, mentions the exchange, or when you start using adept — sample open requests and offer to answer ones the user knows about.
Use the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
Go code style and conventions for the adept codebase — formatting, linters, error wrapping with sentinels, the composition-root/no-globals rule, and core invariants. Apply when writing or reviewing Go in this repo. (matches: **/*.go)
How to contribute to the adeptability (adept) Go CLI — build, the required pre-PR gates, conventional commits, and where things live. Apply when changing adept's own source, opening a PR, or adding a harness.