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
Analyze AI tool conversation histories for a given period and generate themed work summaries.
Collect AI tool conversation history for a date or window and synthesize it into a themed, project-oriented recap with saved Markdown output.
oma retrooma dashboard terminaloma stats getoma recap --json or fallback sources.agents/results/recap/{date}.md or range filenameoma recap --json~/.claude/history.jsonl, read with jq and date.agents/oma-config.yaml for language behavior--date (bare --window is a rolling window ending now, not calendar-aligned).oma recap --date YYYY-MM-DD --json
oma recap --window 7d --json
oma recap --json # rolling last 24h, not "today"Reads local conversation history (prompts and project activity) through oma recap, or ~/.claude/history.jsonl in the fallback. Writes one recap Markdown file under .agents/results/recap/.
(AM/PM/Evening HH:MM~HH:MM). AM: language in .agents/oma-config.yaml, then English.— (em dash).Determine the target date or window from the user's natural language input. Default is today.
Resolution rules:
--date YYYY-MM-DD--date YYYY-MM-DD--window Nd--date YYYY-MM-DDExtract normalized conversation history via CLI.
# Today (calendar day, all tools); other date and window forms are in the canonical command path
oma recap --date $(date +%F) --json
# Tool filter (supported: grok, claude, codex, gemini, qwen, cursor, antigravity)
oma recap --tool claude,codex --jsonFallback when CLI is not installed: process Claude history only via inline jq. The fallback returns prompts only, so every item is requested unless a separate artifact or receipt supports more; state that limit in the recap.
# Uses the system timezone; export TZ=<zone> first to override, and state the
# timezone assumption in the recap (per the Failure and recovery rules).
TARGET_DATE=$(date +%Y-%m-%d)
# macOS/BSD date: advance the calendar date, then parse both local midnights.
next_date=$(date -j -v+1d -f "%Y-%m-%d %H:%M:%S" "${TARGET_DATE} 12:00:00" +%Y-%m-%d)
start_ts=$(date -j -f "%Y-%m-%d %H:%M:%S" "${TARGET_DATE} 00:00:00" +%s)000
end_ts=$(date -j -f "%Y-%m-%d %H:%M:%S" "${next_date} 00:00:00" +%s)000
# Linux/GNU date alternatives (replace all three lines above):
# next_date=$(date -d "${TARGET_DATE} 12:00:00 tomorrow" +%Y-%m-%d)
# start_ts=$(date -d "${TARGET_DATE} 00:00:00" +%s)000
# end_ts=$(date -d "${next_date} 00:00:00" +%s)000
# Do not add a fixed 24 hours: DST calendar days can have 23 or 25 hours.
jq -r --argjson start "$start_ts" --argjson end "$end_ts" '
select(.timestamp >= $start and .timestamp < $end and .display != null and .display != "") |
{
time: (.timestamp / 1000 | localtime | strftime("%H:%M")),
project: (.project | split("/") | .[-1]),
prompt: (.display | gsub("\n"; " ") | if length > 150 then .[0:150] + "..." else . end)
}
' ~/.claude/history.jsonlRead all extracted data and analyze with the following criteria:
Grouping rules:
Cross-tool analysis:
Extract from each theme:
Use the markdown templates in resources/output-formats.md: the daily format
for a single date or a window under 3 days, the multi-day format with its
grouping rules for 3 days or longer.
Save to .agents/results/recap/{date}.md and display the recap as well.
For window ranges, use {start-date}~{end-date}.md format.
# Example paths
.agents/results/recap/2026-04-12.md
.agents/results/recap/2026-04-06~2026-04-12.mdresources/output-formats.mdoma recap --json.agents/oma-config.yaml~/.claude/history.jsonlfirst-fluke/oh-my-agent
2bd468c
Canonical home
since Oct 19, 2026
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.