Triage a GitHub issue or a reported problem — check it is real and not by design (code, git history, PRs, Hindsight memory), find the code and patterns to reuse, build a proof-of-concept fix and prove it solves the problem, then explain the problem and the fix in behaviours before doing the full fix. Use when asked to "triage
94%
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 required workflow runs `gh issue view <N> --comments` on a GitHub issue, which anyone can open or comment on, and also reads PR comments and issue search results, so outsider-authored text enters the agent's context without a further selection step.
vectorize-io/hindsight
5318be8
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.