daily-digest
Generates a daily digest from stored memory files, summarizing decisions, lessons, actions, and questions into a dated journal entry.
- License 许可
- MIT
- 最近更新
- 2026-07-28
- Stars
- ★ 40
- Forks
- 1
01 前言 Front Matter
- name
- daily-digest
- metadata
- { "openclaw": { "tags": [ "digest", "journal", "summary", "decisions", "lessons", "actions" ], "author": "pmaeter", "license": "MIT-0", "version": "1.0.0", "category": "knowledge-consolidation" } }
- description
- Generates a daily digest from stored memory files, summarizing decisions, lessons, actions, and questions into a dated journal entry.
02 资源文件 1
- 参考文档_meta.json107 B
03 SKILL.md 正文
Daily Digest
Purpose
Generate a digest from a set of dated source files. The output is a single Markdown document organized by:
- Decisions — concrete choices the source files committed to.
- Lessons — what was learned (from a mistake, a near-miss, or an unexpected outcome).
- Actions — concrete steps that should be taken (or were taken) as a follow-up.
- Questions — open questions or unresolved threads.
Each section is grounded in source-file references so any line can be traced back to the file that motivated it.
Inputs
- A directory (or list) of dated source files. Canonical naming format
is ISO
YYYY-MM-DD.md, but the digest workflow accepts any filename containing a date.
Output
digest-YYYY-MM-DD.md(one digest per run) with the four sections above. Each bullet ends with a citation in the form(<source-file>).
Workflow
- List the source files; sort them chronologically.
- For each file, scan for cues:
- Decisions: "we decided", "we'll go with", "approved", "ship it".
- Lessons: "we learned", "in retrospect", "next time", "root cause was".
- Actions: "TODO", "next step", "owner:", "ETA", "follow-up".
- Questions: "?", "open question", "still unclear", "TBD".
- Bucket the extractions into the four sections, dedup by meaning (not exact string), and keep the original wording where possible.
- For multi-source synthesis, group bullets that recur in ≥ 2 source files (this is your "common patterns" view) and call out single- source items separately.
- Output the digest as Markdown, one bullet per finding, with the source filename appended to each bullet.
Application to incident postmortems
When the source files are incident postmortems rather than daily memory files, the same four sections still apply:
- Decisions ↔ commitments / mitigations / accepted risk in the postmortem.
- Lessons ↔ contributing factors / "what we learned" sections.
- Actions ↔ action items / preventative measures.
- Questions ↔ open follow-ups / unresolved root-cause threads.
The "common pattern" multi-source grouping is what turns a digest into a cross-incident insights view.
Runtime
The workspace injects this skill at /root/skills/daily-digest as an
instruction-only skill. There is nothing to install. Apply the workflow
above directly to the source files indicated by the user.
04 同仓库更多 Skills
cli-anything-zoom
Command-line interface for Zoom — manage meetings, participants, and recordings from the command line via the Zoom REST API.
netease-music-cli
CLI for NetEase Cloud Music — search songs/albums/playlists, get lyrics, and manage your music library from the terminal.
google-calendar-gcalcli
Install and use gcalcli for live Google Calendar read access using the provided OAuth cache.
Excel / XLSX
Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation. Use when (1) the task is about Excel, `.xlsx`, `.xlsm`, `.xls`, `.csv`, or `.tsv`; (2) formulas, formatting, workbook structure, or compatibility matter; (3) the file must stay reliable after edits.
duckdb-en
DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".
automate-excel
Automates reading, writing, merging, transforming, and validating Excel (.xlsx/.xls) files. Use when the user works with spreadsheets, .xlsx files, Excel data — for cleaning, joining, validating, deduplicating, aggregating, filtering, or auditing tabular data.