원클릭으로
conventional-comments
Use this skill when writing, rewriting, or reviewing feedback comments so they follow the Conventional Comments format.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use this skill when writing, rewriting, or reviewing feedback comments so they follow the Conventional Comments format.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Review an agent's own code changes or another contributor's pull request by dispatching specialist agents, verifying every finding, and reporting only evidence-backed issues. Use when the user asks for a code review, PR review, review of a diff, or a multi-agent quality audit.
Interact with the CreatorSignal API: submit video ideas for AI validation, poll for scored Go/Refine/Kill verdicts, manage channels and webhooks, and check quota. Use this skill whenever the user mentions CreatorSignal API, video idea validation, cs_live_ tokens, validation polling, webhook endpoints, or programmatic idea submission.
This skill should be used when interfacing with the Buffer social media scheduling API. It handles scheduling social media posts, checking the queue, listing channels, creating ideas, and managing Buffer accounts.
Interact with the Buttondown newsletter API to manage tags, automations, subscribers, and emails. Use this skill whenever the user mentions Buttondown, newsletter tags, newsletter automations, email subscribers, or wants to manage any aspect of their Buttondown newsletter -- even if they just say 'my newsletter' without explicitly naming Buttondown.
| name | conventional-comments |
| description | Use this skill when writing, rewriting, or reviewing feedback comments so they follow the Conventional Comments format. |
Use this skill when feedback needs to be clear, reviewable, and easy to scan. It is useful for code review, document review, design feedback, RFC comments, editing notes, and any other feedback thread where tone and actionability matter.
Source standard: https://conventionalcomments.org/
Write each comment in this shape:
<label> [decorations]: <subject>
[discussion]
label is one intent label, such as suggestion, issue, or question.decorations are optional comma-separated context tags in parentheses.subject is the direct comment.discussion is optional supporting context, reasoning, or next step.Examples:
suggestion: Rename this helper to match the domain term used in the rest of the module.
That makes the call sites easier to connect back to the product copy.
issue (blocking): This branch returns a 200 response when validation fails.
Could we return the existing validation error response here so clients can recover correctly?
Choose the narrowest accurate label:
| Label | Use when |
|---|---|
praise | Calling out something genuinely good or worth preserving. |
nitpick | Requesting a trivial preference-based change. Usually non-blocking. |
suggestion | Proposing an improvement. Explain what to change and why. |
issue | Identifying a concrete problem. Pair with a suggested fix when possible. |
todo | Flagging a small necessary task. |
question | Asking for clarification because the concern is uncertain. |
thought | Sharing a related idea that should not block the work. |
chore | Requesting a process step required before acceptance. Link the process when possible. |
note | Highlighting useful context with no requested action. |
Optional expressive labels can be used if they are clearer in context:
| Label | Use when |
|---|---|
typo | Fixing spelling or small text mistakes. |
polish | Improving quality when nothing is strictly wrong. |
quibble | Calling out a very small preference without implying importance. |
Use decorations only when they add useful context.
Common decorations:
| Decoration | Meaning |
|---|---|
(blocking) | The work should not be accepted until this is resolved. |
(non-blocking) | The work can be accepted without resolving this first. |
(if-minor) | Resolve only if the fix is small or trivial. |
Domain decorations can clarify scope, such as (security), (test), (ux), (performance), (docs), or (accessibility). Keep decoration lists short. If the list gets long, split the feedback into separate comments.
issue, suggestion, chore, and todo, make the expected action explicit.question instead of overstating the problem.praise only when it is specific and true.For a single comment, return only the comment:
suggestion (test): Add coverage for the empty input case.
That is the branch most likely to regress because it exits before the normalization step.
For a batch of comments, group them as a list:
- issue (blocking): The migration drops `account_id` before the backfill runs.
Could we split this into a backfill migration and a later cleanup migration?
- note: This parser now matches the API contract more closely.
For Codex inline code review, use the conventional comment text in the title or body of the code comment, while keeping the comment tied to the smallest useful line range.
Before returning comments, check that:
<label>: or <label> (<decorations>):.