---
name: task-optimisation-review
type: task
license: CC BY-NC-SA 4.0
description: Scheduled deployment of skill-optimisation-review — the periodic Pulse review of tooling conventions, operating shape, and the model-and-schedule efficiency of the scheduled layer. Loader only; the behaviour lives in skill-optimisation-review. Linear and GitHub connectors, the scheduled-tasks list, plus web access for the docs-driven tooling pass.
---

# task-optimisation-review

Scheduled deployment of `skill-optimisation-review`. This task carries no behaviour of its own — it is a loader.

**Read the canon artefact `skill-optimisation-review` (the saved skill of that name; locally at `.claude/skills/skill-optimisation-review/SKILL.md`) and follow it verbatim.**

Run context: scheduled autonomous run on the Linear and GitHub connectors, plus the scheduled-tasks list and **web access** (the tooling pass is documentation-led and must read each tool's current docs and changelog). Monthly, or on demand. Propose only — never edit a SKILL.md, a routine, a schedule, or any other canon directly; findings route by nature per the skill (canon to the Pulse friction queue, tooling and repo to `agent:R3-LAY`, schedule and model config to `human` assigned to Aled).

To change *what the optimisation review does*, edit `skill-optimisation-review` — never this file or the scheduled-task config. Add steps **here** only if this task must ever sequence more than the single skill.

Authored 2026-07-15 to close the gap in APP-544: this schedule ran live with no canon artefact, so it was absent from the agents site, invisible to `skill-ops-sync`'s parity diff, and uncounted by `skill-task-health` Pass B.