researching-typescript-guidancelisted
Install: claude install-skill monte3l/m3l-automation
Research a TypeScript language, compiler, or toolchain question by fanning
out parallel web-search agents restricted to **owner-normative TypeScript
sources only**, then synthesizing their findings into a single briefing that
merges agreement into consensus and calls out contradictions. **No code,
config, or test files are written during this skill** unless the user
explicitly asks to persist a snapshot (Step 5) — it otherwise ends with an
inline briefing.
**This skill must only run in the main (hub) agent, never inside a
subagent.** It dispatches subagents via the Agent tool; spokes carry
`disallowedTools: Agent` and cannot do this themselves. If you find yourself
executing this skill as a subagent inside a larger task, stop and surface the
research request back to the hub instead.
**This is not `typescript-configuration`.** That skill answers "how is _this
repo's_ tsconfig wired, and how do I change it safely." This one answers
"what does the _owner_ of the TypeScript language/compiler/toolchain
currently say." A question about `tsconfig.base.json`'s existing flags routes
there; a question about whether a flag's upstream semantics still match what
this repo believes routes here. Same split against `eslint-flat-config`
(this repo's `eslint.config.js` mechanics) and `vitest-testing` (this repo's
Vitest config) — both are "how is X wired here," neither is "what does
upstream currently recommend."
## Steps
### 1 — Scope the topic
Read the research topic from the user's inv