Consolidate memory
AI operating system for product managers. 65 Claude Code skills, 7 multi-perspective review agents, a memory system. Battle-tested in real PM work.
npx -y skills add talgacapri/pm-os --skill consolidate-memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Consolidate memory from the last 24 hours of local Claude logs (~/.claude) into memory/recent-memory.md, memory/long-term-memory.md, and memory/project-memory.md; promote durable facts and patterns from recent to long-term, and run nightly via launchd automation.
SKILL.md
3.1 KB, as published. Nobody here has run it
Why this exists, and what I'd change
Why it exists. Single-file rolling memory gets noisy fast. Long-term decisions get buried under last week's standup chatter. This skill splits memory into three files (recent, long-term, project) and promotes the durable stuff up the chain.
Design tradeoffs.
- Three memory files instead of one. Recent (48h rolling), long-term (distilled facts and preferences), project (active initiative state). Cost: more files to grep, and promotion logic is heuristic and occasionally wrong.
- Nightly cron promotion via launchd, not in-session. Promotion runs at 2am local time. Cost: same-day insights don't move into long-term until tomorrow. If the cron breaks, memory drifts silently.
- Reads from
~/.claudelogs, not a dedicated event stream. I chose to scrape what's already there. Cost: depends on Claude Code's log format staying stable. Will break if Anthropic changes it.
What I'd change. Add an explicit "remember this" command that promotes a fact immediately to long-term, instead of waiting for the cron to maybe catch it.
Consolidate Memory
Keep a persistent memory layer up to date from real conversation history.
Scope
This skill does four things:
- Reads local conversation logs from
~/.claude(last 24h for extraction). - Updates rolling context in
memory/recent-memory.md(48h window). - Updates
memory/project-memory.md(active initiatives, open decisions, next actions). - Promotes durable facts/preferences/patterns into
memory/long-term-memory.md.
Commands
/consolidate-memory run
/consolidate-memory status
/consolidate-memory install-nightly
Equivalent CLI:
python scripts/memory/consolidate_memory.py --run
Files
memory/recent-memory.md- Rolling 48-hour memorymemory/long-term-memory.md- Distilled durable memorymemory/project-memory.md- Active project state
Legacy mirrors are kept in:
long-term-memory.mdcontext-library/pm-os-learning-log.md
Promotion Rules
Promote from recent -> long-term when signals look durable:
- repeated mentions (frequency threshold)
- explicit preference language (
prefer,always,never,tone,style) - durable operational facts (
scheduled,deadline, recurring workflows)
Nightly Automation (macOS)
Install/update launchd job:
bash scripts/memory/install_consolidate_memory_launchd.sh
This writes:
~/Library/LaunchAgents/com.pmos.consolidate-memory.plist
And schedules a nightly run at 2:20 AM local time.
Output Expectations
After each run, script prints a JSON summary:
- number of source files read
- extracted decisions/preferences/facts
- promoted facts/preferences/patterns