
Weekly Digests
Writes a week-by-week chapter series narrating a project's claude-mem history
- Repository
- thedotmack/claude-mem
- Stars
- 110,174
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill has the agent turn a project's full claude-mem activity log into a multi-chapter story, with one chapter per ISO calendar week. It splits the timeline into per-week files, then writes each chapter in order, with each chapter's writer receiving a short summary of the previous chapters so the narrative stays continuous. The output is a folder of digest files plus a weekly index table.
Great for
- Developers who want a readable, chronological story of how a project evolved
- Teams wanting a retrospective narrative of coding sessions week by week
- Anyone already running claude-mem who wants a serial history instead of one long report
Skip it if
- Users wanting a single short summary; the skill produces one chapter per week, so long histories yield many files and a long run (the 'timeline-report' skill is better for that)
- Projects with sensitive history, since the timeline may include security-related or sensitive observations that get copied into written files
- Environments where the agent should not write into arbitrary folders or launch many sub-agent runs, as the process is slow and multi-step
Try asking
- “Create weekly digests for this project's claude-mem timeline”
- “Give me a week-by-week story of the project's history”
- “Run a serial timeline with narrative chapters”
- “Continue the story week by week from the saved timeline”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
weekly-digests.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip weekly-digests.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip weekly-digests.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Confirm the output directory is safe to write into before starting, since the skill creates several files and folders
- Run it on a project with a reasonable number of weeks first to gauge runtime, because subagents run one after another
- Review the generated digests for sensitive content before sharing them outside your team
What's inside
- SKILL.md
Redistributed unmodified from thedotmack/claude-mem under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.