refreshing-typescript-guidancelisted
Install: claude install-skill monte3l/m3l-automation
Sweep this repo's TypeScript-facing surface against upstream TypeScript's
current state and diff it against what was true the last time this ran, then
enter plan mode with a remediation plan. **No `tsconfig*.json`, `eslint.config.js`,
rule, or hook file is edited by this skill** — the only write is the tracker
(Step 5); every actual fix goes through the user-approved plan, the same as
`auditing`.
**This skill must only run in the main (hub) agent, never inside a
subagent.** Step 6 calls `EnterPlanMode`, and Step 3 dispatches subagents via
the Agent tool; spokes carry `disallowedTools: Agent` and cannot do either. If
you find yourself executing this skill as a subagent inside a larger task,
stop and surface the refresh request back to the hub instead.
## Why this exists, not just `researching-typescript-guidance`
That skill answers "what does upstream say about X" once, for whatever X the
invoking task names. Nothing in the repo ever asks the inverse question — is
what's _already configured_ still what upstream ships? This repo hardcodes a
lot of compiler-owned surface: 20+ options in `tsconfig.base.json`,
`isolatedDeclarations` across every `tsconfig.build.json` except
`m3l-console-web`'s (which Vite, not `tsc`, ships from), the
`.js`-extension rule `guard-js-extension.mjs` enforces, `.claude/rules/scripts.md`'s
"annotate, never `satisfies`" ban, `eslint.config.js`'s unrevisited
`recommendedTypeChecked` preset choice, and `attw --profile esm-only` in
`check:exports`. None