atomicinnovation Update Linear Issue
!accelerator config context --skill update-linear-issue --fail-safe
Configuration: Set
work.integration: linearin.accelerator/config.md.
Update an existing Linear issue via issueUpdate. Work through the steps in
order. This skill never auto-invokes — it only runs when the user explicitly
types /update-linear-issue. Body/description content comes only from the
user's current turn, never synthesised from prior context.
Step 1: Parse arguments
Read the issue identifier (positional) and the mutating flags: --title,
--description, --state (a WorkflowState name resolved to its UUID via the
catalogue), --assignee-id, --priority. At least one is required.
Step 2: Render the preview
Show the resolved intent — the operation (issueUpdate), the target issue, and
the fields being set (--title/--description/--state/--assignee-id/
--priority) — under:
Proposed Linear write — review before sending
At least one mutating flag is required; with none the subcommand refuses before
any write (E_UPDATE_NO_OPS). A --state change resolves through
the catalogue and is refused before any write if the name is unknown or
ambiguous.
Step 3: Confirm before writing
Ask:
Apply this update to Linear? Reply y to confirm, n to revise, anything else to abort.
On a clear yes, proceed. On no/revise, rebuild the preview. On anything ambiguous, abort with "Aborted — no Linear write was made."
Step 4: Send and render
accelerator linear update <IDENTIFIER> [flags]
The subcommand reports the updated keyword on success (the trailing
updated\t<identifier> line, or the outcome field when a --state change
renders JSON). Confirm the updated fields and suggest /show-linear-issue <IDENTIFIER> to verify. On any non-zero exit, report the error — no write was
made.
!accelerator config instructions update-linear-issue --fail-safe