Menu
Create a GitHub issue in nerdai/llm-agents-from-scratch and add it to project
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | create-issue |
| description | Create a GitHub issue in nerdai/llm-agents-from-scratch and add it to project |
| disable-model-invocation | true |
nerdai/llm-agents-from-scratch#11 (owner: nerdai)Before doing anything, confirm you have enough information. If any of the following are unclear, ask the user before proceeding:
Do not create the issue until you have a clear title and kind.
Identify issue details from the user's request:
Chapter N label if the issue is scoped to a chapterCreate the issue:
gh issue create \
--repo nerdai/llm-agents-from-scratch \
--title "<title>" \
--body "<body>" \
--label "<label>"
Add to project #11:
gh project item-add 11 --owner nerdai --url <issue-url>
If the Chapter N label doesn't exist yet, create it first:
gh label create "Chapter N" \
--repo nerdai/llm-agents-from-scratch \
--color 0075ca \
--description "Chapter N — <title>"
Confirm with the issue URL.
## Overview
<1-2 sentence summary of what needs to be done>
## Acceptance Criteria
- [ ] <criterion>
- [ ] <criterion>
## Related
<chapter, dependency, or context>
Title format: Diagram: <description>
Label: diagram (create if it doesn't exist)
## Overview
<What this diagram communicates and where it appears in the book>
## Chapter
Chapter N — <chapter title>
## Diagram type
<UML class diagram / sequence diagram / flowchart / table / other>
## Content to show
- <element>
- <element>
## Notes
<Any layout hints, style notes, or references>
| Label | When to use |
|---|---|
Chapter N | Issue scoped to a specific chapter |
diagram | Book diagram to create |
enhancement | New feature or capability |
bug | Bug fix |
documentation | Docs, notebooks, or book content |
Compute the complete Hailstone sequence for a given starting number by repeatedly calling the next_number tool until the value 1 is reached.
Compute the top-10 most frequent words in any text passage supplied by the user.
Compute a sequence for a given starting number by repeatedly calling the next_number tool until the value 1 is reached.
Bump the package version (major, minor, or patch), then sync CITATION.cff, src/_version.py, and CHANGELOG.md. Use when asked to cut a release or bump the version.