Ship a GitHub issue that a person labelled for Tessl the Perihelion way: read the issue and the repository, plan it with the plan skill when it needs a design, build it test-first with the build skill on the issue's own branch, and open one pull request for the issue. Stops without a trace when a person has taken the issue back.
85%
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 reads GitHub issues and comments via `gh issue view` and webhook payloads, which can contain outsider-authored free text.
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.