How do I install the Transition Linear Issue skill?

Run npx skillmds@latest add atomicinnovation/transition-linear-issue in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Transition Linear Issue safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Transition Linear Issue?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Transition Linear Issue free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Transition Linear Issue?

atomicinnovation (@atomicinnovation) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Transition Linear Issue by atomicinnovation

Name: Transition Linear Issue
Author: atomicinnovation

Transition Linear Issue

Use this skill only when the user explicitly invokes /transition-linear-issue to move an existing Linear issue to a different workflow state. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. The target state name is resolved to its UUID from the cached catalogue (no live lookup). Shows a preview, requires explicit confirmation, then applies the transition.

File contents

Transition a Linear Issue

!accelerator config context --skill transition-linear-issue --fail-safe

Configuration: Set work.integration: linear in .accelerator/config.md.

Move a Linear issue to a target WorkflowState via issueUpdate, resolving the state name to its team-scoped UUID from the cached catalogue — there is no live lookup. Work through the steps in order. This skill never auto-invokes.

Step 1: Parse arguments

Read the issue identifier and the target state name (both positional, e.g. /transition-linear-issue BLA-123 "In Progress").

Step 2: Render the preview

Show the resolved intent — the operation (issueUpdate state change), the target issue, and the target state name — under:

Proposed Linear write — review before sending

State matching is case-insensitive and trimmed. Resolution happens inside the subcommand from the cached catalogue; a name that is not in the catalogue or is shared by two states is refused at send time before any write (E_TRANSITION_STATE_NOT_IN_CATALOGUE, E_TRANSITION_STATE_AMBIGUOUS).

Step 3: Confirm before writing

Ask:

Transition this issue? Reply y to confirm, n to revise, anything else to abort.

On a clear yes, proceed. On anything ambiguous, abort with "Aborted — no Linear write was made."

Step 4: Send and render

accelerator linear transition <IDENTIFIER> "<STATE-NAME>"

The subcommand emits a JSON envelope with a top-level outcome keyword. On transitioned, confirm the new state and suggest /show-linear-issue <IDENTIFIER> to verify. On a non-zero exit naming E_TRANSITION_STATE_NOT_IN_CATALOGUE or E_TRANSITION_STATE_AMBIGUOUS, the state could not be resolved and no write was made — suggest /init-linear to refresh, or ask the user to pick an unambiguous state.

!accelerator config instructions transition-linear-issue --fail-safe

---name: transition-linear-issuedescription: Use this skill only when the user explicitly invokes /transition-linear-issue to move an existing Linear issue to a different workflow state. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. The target state name is resolved to its UUID from the cached catalogue (no live lookup). Shows a preview, requires explicit confirmation, then applies the transition.---# Transition a Linear Issue!`accelerator config context --skill transition-linear-issue --fail-safe`> **Configuration**: Set `work.integration: linear` in `.accelerator/config.md`.Move a Linear issue to a target WorkflowState via `issueUpdate`, resolving thestate name to its team-scoped UUID **from the cached catalogue** — there is nolive lookup. Work through the steps in order. This skill never auto-invokes.## Step 1: Parse argumentsRead the issue identifier and the target state name (both positional, e.g.`/transition-linear-issue BLA-123 "In Progress"`).## Step 2: Render the previewShow the resolved intent — the operation (`issueUpdate` state change), the targetissue, and the target state name — under:> **Proposed Linear write — review before sending**State matching is case-insensitive and trimmed. Resolution happens inside thesubcommand from the cached catalogue; a name that is not in the catalogue or isshared by two states is refused at send time **before any write**(`E_TRANSITION_STATE_NOT_IN_CATALOGUE`, `E_TRANSITION_STATE_AMBIGUOUS`).## Step 3: Confirm before writingAsk:> Transition this issue? Reply **y** to confirm, **n** to revise, anything else> to abort.On a clear yes, proceed. On anything ambiguous, abort with "Aborted — no Linearwrite was made."## Step 4: Send and render```accelerator linear transition <IDENTIFIER> "<STATE-NAME>"```The subcommand emits a JSON envelope with a top-level `outcome` keyword. On`transitioned`, confirm the new state and suggest `/show-linear-issue<IDENTIFIER>` to verify. On a non-zero exit naming`E_TRANSITION_STATE_NOT_IN_CATALOGUE` or `E_TRANSITION_STATE_AMBIGUOUS`, thestate could not be resolved and no write was made — suggest `/init-linear` torefresh, or ask the user to pick an unambiguous state.!`accelerator config instructions transition-linear-issue --fail-safe`

Frequently asked questions