Summarize AI conversation histories for a specified date or period. Use for daily work recaps and cross-tool activity summaries.
77%
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 ./.agents/skills/oma-recap/SKILL.mdThe canonical home for this skill is oma-recap in first-fluke/oh-my-agent
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 reads the user's own local AI conversation history via `oma recap --json` or `~/.claude/history.jsonl`, which can contain web or document content the user's AI tools pulled in, but an outsider cannot force that content into the history, so it is low rather than medium.
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.