askit-standards-watchlisted
Install: claude install-skill product-on-purpose/agent-skills-toolkit
# askit-standards-watch
## Purpose
[STANDARD.md](../../STANDARD.md) sec 6 states, as normative text, that **where agentskills.io evolves the Universal tier MUST track it; higher tiers remain this Standard's domain.** Tracking is only auditable against a recorded starting point. This skill owns that starting point (`docs/internal/standards-watch/upstream-pin.json`), detects when the upstream has moved away from it, maps each delta to the checks it lands on, and produces a **proposal**. It never applies one.
## When to use
When someone asks whether the upstream spec has changed, before cutting a Standard MINOR, on a periodic governance sweep, or when re-pinning the upstream revision after an ADR is accepted.
## The one hard rule
**This skill proposes. A human decides. Nothing here edits a check module, `STANDARD.md`, an existing ADR, or the pin.**
The Standard grows only by ADR with the warn-first burndown of sec 7.7 (a new or tightened requirement ships as a `warn` for one MINOR, then becomes an `error`). A watcher that edited a check would convert a governed decision into a silent one, which is the single thing that would make the gate untrustworthy. The deterministic half is write-incapable by construction: `scripts/lib/standards-watch.mjs` and `scripts/standards-watch.mjs` import only `readFileSync` from `node:fs` and emit everything to stdout, and [a test](../../tests/unit/standards-watch.test.mjs) fails the build if any write API appears in either file. Your obligati