Given a bug report (GitHub issue, Jira ticket, file, or pasted text), find its root cause and decide per symptom whether it is a one-off or one instance of a pattern worth fixing at the root, then file or sight a deduplicated refactor ticket when it is. Use proactively whenever handed a bug report and asked what is wrong or whether something deeper is broken.
93%
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 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 intakes bug reports from GitHub issues and Jira tickets, ingesting outsider-authored free text into bug.json during intake.
BuilderIO/agent-native
a0356c6
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.