core-memory
Skill623 starsChanged 10 months agoMITView on GitHub
Semantic recall, exact cross-session search, remembering, and normal continuity
1 other project uses a version of this.
Adopted by
Most recently taken up by
- QuixiAI/agi-memoryword for word, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- QuixiAI/agi-memory★ 623100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audio-analysisSkill
- calendarSkill
- code-executionSkill
- connector-action-authorizationSkill
- cost-reportSkill
- councilSkill
- crm-lookupSkill
- daily-briefingSkill
- delegationSkill
- email-digestSkill
- expense-captureSkill
- github-issuesSkill
- gmail-actionsSkill
- gmail-connector-setupSkill
- home-assistantSkill
- host-nodeSkill
- humanizerSkill
- image-genSkill
- inbox-triageSkill
- integration-connector-setupSkill
- knowledge-ingestSkill
- meeting-follow-upSkill
- meeting-prepSkill
- memory-exchangeSkill
- notionSkill
- operationsSkill
- outreachSkill
- personal-notesSkill
- researchSkill
- self-inspectionSkill
- self-reflectionSkill
- skill-authoringSkill
- speechSkill
- spotifySkill
- travel-prepSkill
- trelloSkill
- twitter-x-actionsSkill
- twitter-x-connector-setupSkill
- weatherSkill
- weekly-reviewSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 7 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Use this skill for ordinary continuity: recalling relevant memories, opening exact source material, storing new experiences, maintaining …
- Distinctive: line 21
Before claiming you do not know something, check memory when the answer plausibly lives there.
- Very specific: line 25
Use sense_memory_availability for a cheap check when unsure whether memory is likely to help.
- Very specific: line 26
Use recall for targeted retrieval.
- Very specific: line 27
Use recall_at_time when the user asks what was known "as of" a past instant, and diff_memory_history when they ask what changed between two …
- Very specific: line 29
Use search_history for exact names, phrases, or details from earlier sessions, especially when semantic recall is weak or embeddings are …
- Very specific: line 31
When the answer depends on an ingested source rather than distilled memory, climb the cabinet ladder: search_documents for files or …
- Very specific: line 41
Use remember when a durable fact, event, preference, promise, or decision should persist.
- Distinctive: line 42
Use journal tools only for deliberate permanent entries, not ordinary memory.
- Distinctive: line 44
Use document approval tools when the user explicitly says to keep or let an ingested document fade.
- Very specific: line 45
Use manage_operator_policies to list standing instructions or revoke one only when the verified operator explicitly asks.
- Distinctive: line 50
Do not store secrets unless the user explicitly asks.
- Distinctive: line 51
Do not turn every minor sentence into memory.
- Distinctive: line 52
Keep tool use proportional.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Core Memory and Continuity
Use this skill for ordinary continuity: recalling relevant memories, opening exact source material, storing new experiences, maintaining goals, consulting the permanent journal, and resolving pending document-fade approvals.
When to Use
- The user asks about something that may already be in memory.
- The current conversation contains information worth preserving.
- A goal, schedule item, backlog item, or journal entry should be created or updated.
- The user answers a document-fade approval request.
- Before claiming you do not know something, check memory when the answer plausibly lives there.
Method
- Use
sense_memory_availabilityfor a cheap check when unsure whether memory is likely to help. - Use
recallfor targeted retrieval. Prefer specific queries over broad ones. - Use
recall_at_timewhen the user asks what was known "as of" a past instant, anddiff_memory_historywhen they ask what changed between two times or why. - Use
search_historyfor exact names, phrases, or details from earlier sessions, especially when semantic recall is weak or embeddings are unavailable. - When the answer depends on an ingested source rather than distilled memory,
climb the cabinet ladder:
search_documentsfor files orsearch_document_chunksfor citable passages ->open_document/open_document_chunkfor read-only inspection ->load_documents/load_document_chunks(with a reason) when the material must stay searchable ->search_historywithsources=["desk"]while reasoning ->open_desk_itemto scroll long items -> cite the document/chunk/page handle. Runlist_deskfirst -- do not re-load what is already on the desk.pin_desk_itemwhat stays actively needed;clear_deskwhen done (cleared items archive; sources stay in the cabinet). - Use
rememberwhen a durable fact, event, preference, promise, or decision should persist. - Use journal tools only for deliberate permanent entries, not ordinary memory.
- Use goal, schedule, or backlog tools when the user asks for ongoing commitments or work tracking. For durable watch-and-notify commitments that outlive the conversation ("let me know whenever X happens", "watch for email from Hope", recurring medication reminders), use
manage_responsibility; usemanage_scheduleonly for simple timed reminders that observe nothing. - Use document approval tools when the user explicitly says to keep or let an ingested document fade.
- Use
manage_operator_policiesto list standing instructions or revoke one only when the verified operator explicitly asks. A replacement is a revoke followed by the operator stating the new standing instruction.
Quality Guidelines
- Memory is evidence, not omniscience. If retrieved context is weak or absent, say so.
- Do not store secrets unless the user explicitly asks.
- Do not turn every minor sentence into memory; persist what will matter later.
- Keep tool use proportional. A direct answer does not need a recall if the answer is already present in the current conversation.
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.

