promote
Skill17 starsChanged 7 months agoMITView on GitHub
Extract key learnings from daily logs and promote them to identity/memory.md. Run automatically via launchd once per day, or manually after a productive day.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- rzaaeeff/agent-ledgertheir own version, first seen Nov 16, 2026
- warrendeanlangeveldt/code-kittheir own version, first seen Nov 15, 2026
- HiteSit/real-scientist-skillstheir own version, first seen Nov 15, 2026
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- ArcticFox2029/chamnantheir own version, first seen Nov 5, 2026
- jbaruch/nanoclaw-hosttheir own version, first seen Oct 31, 2026
Used with
Projects with it also use decide, review and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dirienSkilldecide
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- oliver-kriska/claude-elixir-phoenix★ 573same name
- dedalus-labs/wingman★ 181same name
- HiteSit/real-scientist-skills★ 27same name
- wrg32786/aigent-os★ 26same name
- Hassaan146/claude-skills★ 18same name
- ArcticFox2029/chamnan★ 10same name
- nmhjklnm/yaohe★ 9same name
- anotherben/claude-harness★ 7same name
- anis-dr/skills★ 4same name
- rzaaeeff/agent-ledger★ 4same name
10 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- daily-standupSkill
- distill-sessionSkill
- heartbeatSkill
- humanizerSkill
- memory-updateSkill
- playwright-cliSkill
- researchSkill
- search-memorySkill
- self-improveSkill
- setupSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Read the last 3 days of daily-logs/ files
- Very specific: line 21
Read current identity/memory.md (hot) and relevant memory/*.md files (cold)
- Distinctive: line 30
Only promote things needed in every conversation
- Very specific: line 31
Update ## Current State and ## Active Work
- Very specific: line 32
Add one-liner to ## Session Log
- Distinctive: line 33
Keep under 2500 tokens — push detail to cold files
- Very specific: line 35
Add detailed entries with datestamps: <!-- promoted YYYY-MM-DD -->
- Distinctive: line 36
Don't duplicate — consolidate with existing entries
- Distinctive: line 37
Remove stale entries that are clearly no longer relevant
- Very specific: line 38
If identity/memory.md is over 2500 tokens, archive oldest entries to memory/archive-YYYY-MM.md
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Daily log promotion — extract signal from raw conversation logs into long-term memory.
Hot/Cold Memory Architecture
- Hot:
identity/memory.md— always in context, kept under 2500 tokens. Only the essentials. - Cold:
memory/*.md— topic files searched on-demand. Detailed context lives here.memory/projects.md— project details, architecture, statusmemory/preferences.md— recurring patterns, style choicesmemory/decisions.md— key decisions with reasoningmemory/people.md— people contextmemory/archive-YYYY-MM.md— older entries rotated out of hot memory
Steps
- Read the last 3 days of
daily-logs/files - Read current
identity/memory.md(hot) and relevantmemory/*.mdfiles (cold) - Extract and route:
- Key decisions (with rationale) →
identity/memory.mdCurrent State +memory/decisions.md - Lessons learned →
memory/decisions.md - New preferences →
memory/preferences.md - Project context →
memory/projects.md - People context →
memory/people.md - Active work / open threads →
identity/memory.mdActive Work
- Key decisions (with rationale) →
- For
identity/memory.md(hot layer):- Only promote things needed in every conversation
- Update
## Current Stateand## Active Work - Add one-liner to
## Session Log - Keep under 2500 tokens — push detail to cold files
- For
memory/*.md(cold layer):- Add detailed entries with datestamps:
<!-- promoted YYYY-MM-DD --> - Don't duplicate — consolidate with existing entries
- Remove stale entries that are clearly no longer relevant
- Add detailed entries with datestamps:
- If
identity/memory.mdis over 2500 tokens, archive oldest entries tomemory/archive-YYYY-MM.md - Report what was promoted, where it went, and what was skipped
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

