AI Tool Conversation History Summary
Analyze AI tool conversation histories for a given period and generate themed work summaries.
Scheduling
Goal
Collect AI tool conversation history for a date or window and synthesize it into a themed, project-oriented recap with saved Markdown output.
Intent signature
- User asks for daily recap, weekly/monthly summary, standup notes, work log, tool usage pattern, or AI conversation history analysis.
- User wants conversation histories grouped by work content rather than raw chronological logs.
When to use
- Summarizing a day or period of work activity
- Understanding the overall flow of work across multiple AI tools
- Analyzing tool-switching patterns between sessions
- Preparing daily standups, weekly retros, or work logs
When NOT to use
- Git commit-based code change retrospective -> use
oma retro
- Real-time agent monitoring -> use
oma dashboard terminal
- Productivity metrics -> use
oma stats get
Expected inputs
- Date, relative date, time window, or tool filter
- Conversation history available through
oma recap --json or fallback sources
- Desired daily or multi-day recap scope
Expected outputs
- Markdown recap saved to
.agents/results/recap/{date}.md or range filename
- TL;DR, overview, themes/projects, miscellaneous or side projects, and tool usage patterns
- User-facing summary in configured response language
Dependencies
oma recap --json
- Optional Claude fallback history at
~/.claude/history.jsonl
.agents/oma-config.yaml for language behavior
Control-flow features
- Branches by date resolution, window length, available tool history, and daily vs multi-day output shape
- Reads local history data and writes Markdown recap files
- Groups by content, not by tool
Structural Flow
Entry
- Resolve requested date or window.
- Collect normalized conversation history.
- Decide daily versus multi-day output structure.
Scenes
- PREPARE: Resolve time range and tool filters.
- ACQUIRE: Collect history through CLI or fallback; retain completion evidence where available.
- REASON: Group by content and classify each item as requested, in progress, or completed from its evidence.
- ACT: Write recap Markdown in the required format.
- VERIFY: Check that every completion claim has direct evidence, then check grouping, language, and output path.
- FINALIZE: Save and display summary.
Transitions
- If no date is specified, use today via
--date (bare --window is a rolling window ending now, not calendar-aligned).
- If window is 3 days or longer, group by project instead of day chronology.
- If CLI is unavailable, use Claude fallback only and report scope limits.
- If tasks are under threshold, group them into Miscellaneous or Side Projects.
Failure and recovery
- If history is unavailable, report missing source and requested range.
- If timestamps are ambiguous, use configured timezone and state assumption.
- If extracted data is sparse, produce a concise recap and note limited coverage.
Exit
- Success: recap file exists and summary is displayed.
- Partial success: missing tools/history or fallback-only coverage is explicit.
Logical Operations
Actions
| Action |
SSL primitive |
Evidence |
| Resolve date/window |
INFER |
Natural-language date rules |
| Collect history |
CALL_TOOL |
oma recap --json or jq fallback |
| Read extracted records |
READ |
Conversation history |
| Group and classify themes/projects |
INFER |
Time/content rules plus prompt, progress, completion, receipt, or artifact evidence |
| Validate output shape |
VALIDATE |
Daily or multi-day template |
| Write recap |
WRITE |
.agents/results/recap/ |
| Report summary |
NOTIFY |
Displayed recap |
Tools and instruments
oma recap --json
jq fallback for Claude history
- Markdown output templates
Canonical command path
oma recap --date YYYY-MM-DD --json
oma recap --window 7d --json
oma recap --json # rolling last 24h, not "today"
Resource scope
| Scope |
Resource target |
LOCAL_FS |
Conversation history and recap output files |
PROCESS |
oma recap, jq, date commands |
USER_DATA |
Conversation prompts and project activity |
MEMORY |
Theme grouping and summary notes |
Preconditions
- Requested time range can be resolved.
- At least one history source is available.
Effects and side effects
- Writes recap Markdown under
.agents/results/recap/.
- Reads local conversation history data.
Guardrails
- Evidence status: A prompt alone proves a request, not a result. Mark work completed only with an explicit completion/result message, a receipt, or an artifact that supports the stated outcome. Mark it in progress with progress evidence; otherwise call it requested. Do not infer completion from a tool invocation or elapsed time.
- TL;DR required: Top 3 supported outcomes. Use "completed" only when the evidence-status rule permits it; otherwise summarize requested or in-progress work plainly. Project name + status/outcome. No tool names or unnecessary detail.
- Overview: After TL;DR, describe the flow. Start with "I" as subject and preserve evidence status.
- Daily: themes by time block (15+ min). Rest goes to "Miscellaneous".
- Multi-day (3d+): sections by project, ordered by activity. Read like a sprint report, not a daily log.
- 2-4 bullets per theme/project: Concise essentials only. Don't enumerate every step.
- Themes by content: Group by actual work, not by tool.
- Time range (daily only):
(AM/PM/Evening HH:MM~HH:MM). AM: 12:00, PM: 12:0018:00, Evening: 18:00~.
- Save results: Write markdown to
.agents/results/recap/.
- Response language: the user's prompt language first, then
language in .agents/oma-config.yaml, then English.
- No em dashes: Use commas, periods, or parentheses instead of
— (em dash).
Process
1. Resolve Date
Determine the target date or window from the user's natural language input. Default is today.
Resolution rules:
- Relative day references (today, yesterday, day before yesterday, etc.) → calculate
--date YYYY-MM-DD
- Specific date mentions (month + day, or full date) → convert to
--date YYYY-MM-DD
- Relative weekday references (last Monday, this Friday, etc.) → calculate the date
- Period references (this week, last 3 days, past 2 weeks, etc.) → convert to
--window Nd
- No date specified → today, resolved to
--date YYYY-MM-DD (bare --window 1d is a rolling 24-hour window ending now, not the calendar day)
- The CLI caps windows at 30 days (longer values are trimmed with a warning) — when a requested period gets capped, say so in the recap
2. Collect Data
Extract normalized conversation history via CLI.
# Today (calendar day, all tools)
oma recap --date $(date +%F) --json
# Last 24 hours (rolling window ending now)
oma recap --json
# Time window (rolling, ends now; capped at 30d)
oma recap --window 7d --json
# Specific date
oma recap --date 2026-04-10 --json
# Tool filter (supported: grok, claude, codex, gemini, qwen, cursor, antigravity)
oma recap --tool claude,codex --json
Fallback when CLI is not installed: process Claude history only via inline jq:
# Uses the system timezone; export TZ=<zone> first to override, and state the
# timezone assumption in the recap (per the Failure and recovery rules).
TARGET_DATE=$(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.jsonl
3. Theme Analysis and Grouping
Read all extracted data and analyze with the following criteria:
Grouping rules:
- Only classify as a separate theme if the work spans 15+ minutes (based on timestamp gaps and prompt count)
- Merge consecutive prompts on the same topic into one theme
- Collect sub-15-minute tasks into a "Miscellaneous" section
- Group by work content, not by tool
Cross-tool analysis:
- Track workflow when multiple tools are used in the same time window
- Example: "Designed in Antigravity -> Implemented in Claude -> Reviewed in Codex"
- Derive insights from tool-switching patterns
Extract from each theme:
- Core work performed
- Key decisions made
- Tool combinations used
- Artifacts produced (docs, code, config, etc.)
4. Output Format
Save results to .agents/results/recap/{date}.md and display simultaneously.
Use the markdown templates in resources/output-formats.md:
- Daily format (1d or specific date): TL;DR → Overview → time-blocked themes → Miscellaneous → Tool Usage Patterns.
- Multi-day format (3d+): project-driven sprint-report structure with Side Projects for small (<30 prompts) work; follow the multi-day grouping rules in the same file.
Response language: the user's prompt language first, then language in .agents/oma-config.yaml, then English.
5. Save Results
Save to .agents/results/recap/{date}.md.
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.md
References
- Output format templates:
resources/output-formats.md
- Recap CLI:
oma recap --json
- Output directory:
.agents/results/recap/
- Language config:
.agents/oma-config.yaml
- Claude fallback history:
~/.claude/history.jsonl
1---2name: oma-recap3description: Summarize AI conversation histories for a specified date or period.4 Use for daily work recaps and cross-tool activity summaries.5metadata:6 source: https://skillmd.com/skills/tuyv/oma-recap7---89# AI Tool Conversation History Summary1011Analyze AI tool conversation histories for a given period and generate themed work summaries.1213## Scheduling1415### Goal16Collect AI tool conversation history for a date or window and synthesize it into a themed, project-oriented recap with saved Markdown output.1718### Intent signature19- User asks for daily recap, weekly/monthly summary, standup notes, work log, tool usage pattern, or AI conversation history analysis.20- User wants conversation histories grouped by work content rather than raw chronological logs.2122### When to use23- Summarizing a day or period of work activity24- Understanding the overall flow of work across multiple AI tools25- Analyzing tool-switching patterns between sessions26- Preparing daily standups, weekly retros, or work logs2728### When NOT to use29- Git commit-based code change retrospective -> use `oma retro`30- Real-time agent monitoring -> use `oma dashboard terminal`31- Productivity metrics -> use `oma stats get`3233### Expected inputs34- Date, relative date, time window, or tool filter35- Conversation history available through `oma recap --json` or fallback sources36- Desired daily or multi-day recap scope3738### Expected outputs39- Markdown recap saved to `.agents/results/recap/{date}.md` or range filename40- TL;DR, overview, themes/projects, miscellaneous or side projects, and tool usage patterns41- User-facing summary in configured response language4243### Dependencies44- `oma recap --json`45- Optional Claude fallback history at `~/.claude/history.jsonl`46- `.agents/oma-config.yaml` for language behavior4748### Control-flow features49- Branches by date resolution, window length, available tool history, and daily vs multi-day output shape50- Reads local history data and writes Markdown recap files51- Groups by content, not by tool5253## Structural Flow5455### Entry561. Resolve requested date or window.572. Collect normalized conversation history.583. Decide daily versus multi-day output structure.5960### Scenes611. **PREPARE**: Resolve time range and tool filters.622. **ACQUIRE**: Collect history through CLI or fallback; retain completion evidence where available.633. **REASON**: Group by content and classify each item as requested, in progress, or completed from its evidence.644. **ACT**: Write recap Markdown in the required format.655. **VERIFY**: Check that every completion claim has direct evidence, then check grouping, language, and output path.666. **FINALIZE**: Save and display summary.6768### Transitions69- If no date is specified, use today via `--date` (bare `--window` is a rolling window ending now, not calendar-aligned).70- If window is 3 days or longer, group by project instead of day chronology.71- If CLI is unavailable, use Claude fallback only and report scope limits.72- If tasks are under threshold, group them into Miscellaneous or Side Projects.7374### Failure and recovery75- If history is unavailable, report missing source and requested range.76- If timestamps are ambiguous, use configured timezone and state assumption.77- If extracted data is sparse, produce a concise recap and note limited coverage.7879### Exit80- Success: recap file exists and summary is displayed.81- Partial success: missing tools/history or fallback-only coverage is explicit.8283## Logical Operations8485### Actions86| Action | SSL primitive | Evidence |87|--------|---------------|----------|88| Resolve date/window | `INFER` | Natural-language date rules |89| Collect history | `CALL_TOOL` | `oma recap --json` or `jq` fallback |90| Read extracted records | `READ` | Conversation history |91| Group and classify themes/projects | `INFER` | Time/content rules plus prompt, progress, completion, receipt, or artifact evidence |92| Validate output shape | `VALIDATE` | Daily or multi-day template |93| Write recap | `WRITE` | `.agents/results/recap/` |94| Report summary | `NOTIFY` | Displayed recap |9596### Tools and instruments97- `oma recap --json`98- `jq` fallback for Claude history99- Markdown output templates100101### Canonical command path102```bash103oma recap --date YYYY-MM-DD --json104oma recap --window 7d --json105oma recap --json # rolling last 24h, not "today"106```107108### Resource scope109| Scope | Resource target |110|-------|-----------------|111| `LOCAL_FS` | Conversation history and recap output files |112| `PROCESS` | `oma recap`, `jq`, date commands |113| `USER_DATA` | Conversation prompts and project activity |114| `MEMORY` | Theme grouping and summary notes |115116### Preconditions117- Requested time range can be resolved.118- At least one history source is available.119120### Effects and side effects121- Writes recap Markdown under `.agents/results/recap/`.122- Reads local conversation history data.123124### Guardrails1251261. **Evidence status**: A prompt alone proves a request, not a result. Mark work **completed** only with an explicit completion/result message, a receipt, or an artifact that supports the stated outcome. Mark it **in progress** with progress evidence; otherwise call it **requested**. Do not infer completion from a tool invocation or elapsed time.1272. **TL;DR required**: Top 3 supported outcomes. Use "completed" only when the evidence-status rule permits it; otherwise summarize requested or in-progress work plainly. Project name + status/outcome. No tool names or unnecessary detail.1283. **Overview**: After TL;DR, describe the flow. Start with "I" as subject and preserve evidence status.1294. **Daily**: themes by time block (15+ min). Rest goes to "Miscellaneous".1305. **Multi-day (3d+)**: sections by project, ordered by activity. Read like a sprint report, not a daily log.1316. **2-4 bullets per theme/project**: Concise essentials only. Don't enumerate every step.1327. **Themes by content**: Group by actual work, not by tool.1338. **Time range (daily only)**: `(AM/PM/Evening HH:MM~HH:MM)`. AM: ~12:00, PM: 12:00~18:00, Evening: 18:00~.1349. **Save results**: Write markdown to `.agents/results/recap/`.13510. **Response language**: the user's prompt language first, then `language` in `.agents/oma-config.yaml`, then English.13611. **No em dashes**: Use commas, periods, or parentheses instead of `—` (em dash).137138### Process139140### 1. Resolve Date141142Determine the target date or window from the user's natural language input. Default is today.143144**Resolution rules:**145- Relative day references (today, yesterday, day before yesterday, etc.) → calculate `--date YYYY-MM-DD`146- Specific date mentions (month + day, or full date) → convert to `--date YYYY-MM-DD`147- Relative weekday references (last Monday, this Friday, etc.) → calculate the date148- Period references (this week, last 3 days, past 2 weeks, etc.) → convert to `--window Nd`149- No date specified → today, resolved to `--date YYYY-MM-DD` (bare `--window 1d` is a rolling 24-hour window ending now, not the calendar day)150- The CLI caps windows at 30 days (longer values are trimmed with a warning) — when a requested period gets capped, say so in the recap151152### 2. Collect Data153154Extract normalized conversation history via CLI.155156```bash157# Today (calendar day, all tools)158oma recap --date $(date +%F) --json159160# Last 24 hours (rolling window ending now)161oma recap --json162163# Time window (rolling, ends now; capped at 30d)164oma recap --window 7d --json165166# Specific date167oma recap --date 2026-04-10 --json168169# Tool filter (supported: grok, claude, codex, gemini, qwen, cursor, antigravity)170oma recap --tool claude,codex --json171```172173**Fallback when CLI is not installed**: process Claude history only via inline jq:174175```bash176# Uses the system timezone; export TZ=<zone> first to override, and state the177# timezone assumption in the recap (per the Failure and recovery rules).178TARGET_DATE=$(date +%Y-%m-%d)179# macOS/BSD date: advance the calendar date, then parse both local midnights.180next_date=$(date -j -v+1d -f "%Y-%m-%d %H:%M:%S" "${TARGET_DATE} 12:00:00" +%Y-%m-%d)181start_ts=$(date -j -f "%Y-%m-%d %H:%M:%S" "${TARGET_DATE} 00:00:00" +%s)000182end_ts=$(date -j -f "%Y-%m-%d %H:%M:%S" "${next_date} 00:00:00" +%s)000183# Linux/GNU date alternatives (replace all three lines above):184# next_date=$(date -d "${TARGET_DATE} 12:00:00 tomorrow" +%Y-%m-%d)185# start_ts=$(date -d "${TARGET_DATE} 00:00:00" +%s)000186# end_ts=$(date -d "${next_date} 00:00:00" +%s)000187# Do not add a fixed 24 hours: DST calendar days can have 23 or 25 hours.188189jq -r --argjson start "$start_ts" --argjson end "$end_ts" '190 select(.timestamp >= $start and .timestamp < $end and .display != null and .display != "") |191 {192 time: (.timestamp / 1000 | localtime | strftime("%H:%M")),193 project: (.project | split("/") | .[-1]),194 prompt: (.display | gsub("\n"; " ") | if length > 150 then .[0:150] + "..." else . end)195 }196' ~/.claude/history.jsonl197```198199### 3. Theme Analysis and Grouping200201Read **all** extracted data and analyze with the following criteria:202203**Grouping rules:**204- Only classify as a separate theme if the work spans **15+ minutes** (based on timestamp gaps and prompt count)205- Merge consecutive prompts on the same topic into one theme206- Collect sub-15-minute tasks into a "Miscellaneous" section207- Group by **work content**, not by tool208209**Cross-tool analysis:**210- Track workflow when multiple tools are used in the same time window211- Example: "Designed in Antigravity -> Implemented in Claude -> Reviewed in Codex"212- Derive insights from tool-switching patterns213214**Extract from each theme:**215- Core work performed216- Key decisions made217- Tool combinations used218- Artifacts produced (docs, code, config, etc.)219220### 4. Output Format221222Save results to `.agents/results/recap/{date}.md` and display simultaneously.223224Use the markdown templates in `resources/output-formats.md`:225- **Daily format** (1d or specific date): TL;DR → Overview → time-blocked themes → Miscellaneous → Tool Usage Patterns.226- **Multi-day format** (3d+): project-driven sprint-report structure with Side Projects for small (<30 prompts) work; follow the multi-day grouping rules in the same file.227228**Response language: the user's prompt language first, then `language` in `.agents/oma-config.yaml`, then English.**229230### 5. Save Results231232Save to `.agents/results/recap/{date}.md`.233For window ranges, use `{start-date}~{end-date}.md` format.234235```bash236# Example paths237.agents/results/recap/2026-04-12.md238.agents/results/recap/2026-04-06~2026-04-12.md239```240241## References242243- Output format templates: `resources/output-formats.md`244- Recap CLI: `oma recap --json`245- Output directory: `.agents/results/recap/`246- Language config: `.agents/oma-config.yaml`247- Claude fallback history: `~/.claude/history.jsonl`