Implements a complete workflow for resolving GitHub issues directly from Claude Code. Guides through the full lifecycle from fetching issue details, analyzing requirements, implementing the solution, verifying correctness, performing code review, committing changes, and creating a pull request. Use when user asks to "resolve issue", "implement issue", "work on issue
70
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is giuseppe-trisciuoglio/developer-kit
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow reads GitHub issues via the `gh` CLI (`gh issue view`), which allows outsider-authored free text (issue bodies and comments) to be ingested into the agent's execution context, representing an indirect prompt injection risk.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.