Player-facing patch notes from git history and changelogs. Translates developer language into player communication.
78%
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
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/patch-notes/SKILL.mdThe 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 runtime path runs `git log --oneline -20` and the Phase 2 fallback `git log` over the release range, ingesting every commit message without selecting an item, and external contributors can land commit messages through merged PRs, so this is treated as medium under the recall-first override.
Donchitos/Claude-Code-Game-Studios
abc0de7
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.