Menu
Create a GitHub issue in nerdai/llm-agents-from-scratch and add it to project
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| 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.