How do I install the Comment Linear Issue skill?

Run npx skillmds@latest add atomicinnovation/comment-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 Comment 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 Comment 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 Comment Linear Issue free to use?

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

Who published Comment Linear Issue?

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

Comment Linear Issue by atomicinnovation

Name: Comment Linear Issue
Author: atomicinnovation

Comment Linear Issue

Use this skill only when the user explicitly invokes /comment-linear-issue to add a Markdown comment to an existing Linear issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. It shows the comment preview, requires explicit confirmation, then posts the comment.

File contents

Comment on a Linear Issue

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

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

Add a Markdown comment to a Linear issue via commentCreate. Work through the steps in order. This skill never auto-invokes — it only runs when the user explicitly types /comment-linear-issue.

The comment body comes ONLY from text the user typed this turn or a file path the user named this turn — never synthesised from prior context.

Step 1: Parse arguments

Read the issue identifier (positional) and the body source (--body TEXT or --body-file PATH).

Step 2: Render the preview

Resolve the body: if --body-file PATH was given, read the file; otherwise take --body TEXT verbatim. If neither is present, STOP with E_COMMENT_NO_BODY.

Show the resolved intent — the operation (commentCreate), the target issue, and the Markdown body — under:

Proposed Linear write — review before sending

Step 3: Confirm before writing

Ask:

Post this comment 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 comment add <IDENTIFIER> --body "..."

The subcommand emits a JSON envelope with a top-level outcome keyword. On added, confirm the comment was posted. On any non-zero exit, report the error and stop.

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

---name: comment-linear-issuedescription: Use this skill only when the user explicitly invokes /comment-linear-issue to add a Markdown comment to an existing Linear issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. It shows the comment preview, requires explicit confirmation, then posts the comment.---# Comment on a Linear Issue!`accelerator config context --skill comment-linear-issue --fail-safe`> **Configuration**: Set `work.integration: linear` in `.accelerator/config.md`.Add a Markdown comment to a Linear issue via `commentCreate`. Work through thesteps in order. This skill never auto-invokes — it only runs when the userexplicitly types `/comment-linear-issue`.The comment body comes ONLY from text the user typed this turn or a file paththe user named this turn — never synthesised from prior context.## Step 1: Parse argumentsRead the issue identifier (positional) and the body source (`--body TEXT` or`--body-file PATH`).## Step 2: Render the previewResolve the body: if `--body-file PATH` was given, read the file; otherwise take`--body TEXT` verbatim. If neither is present, STOP with `E_COMMENT_NO_BODY`.Show the resolved intent — the operation (`commentCreate`), the target issue,and the Markdown body — under:> **Proposed Linear write — review before sending**## Step 3: Confirm before writingAsk:> Post this comment 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 anythingambiguous, abort with "Aborted — no Linear write was made."## Step 4: Send and render```accelerator linear comment add <IDENTIFIER> --body "..."```The subcommand emits a JSON envelope with a top-level `outcome` keyword. On`added`, confirm the comment was posted. On any non-zero exit, report the errorand stop.!`accelerator config instructions comment-linear-issue --fail-safe`

Frequently asked questions