Summarize AI conversation histories for a specified date or period. Use for daily work recaps and cross-tool activity summaries.
73%
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 ./skills/oma-recap/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 workflow reads local AI tool conversation history via `oma recap --json` (and the `~/.claude/history.jsonl` fallback), which an outsider cannot POST into, but earlier sessions may contain outsider-authored web or tool content the agent did not select, so exposure is incidental and at most low.
first-fluke/oh-my-agent
2bd468c
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.