memory
Skill4 starsChanged 36 days agoApache-2.0View on GitHub
Use when reading or writing persistent AI-agent state through a Memory MCP server, including category discovery, versioned reads and writes, merge patches, optimistic concurrency, bounded append-only journals, search, context loading and history. Keep durable state separate from bounded logs and choose the user-facing language from the request.
99 other projects use a version of this.
Adopted by
Most recently taken up by
- jaydubya818/ClaudeClaw-Mission-Controltheir own version, first seen Nov 8, 2026
- naman10parikh/pennytheir own version, first seen Nov 8, 2026
- NaturNestAI-Labs/beings-protocoltheir own version, first seen Nov 8, 2026
- maxtechera/memorytheir own version, first seen Nov 8, 2026
- wubinKKK/private-ai-workbenchtheir own version, first seen Nov 8, 2026
- shetengteng/skillix-hubtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ecosystem-reference, fractal-delegation and 10 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.
naman10parikhSkillecosystem-reference
Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.
Also in 5 projects that use this
naman10parikhSkillfractal-delegation
Also in 5 projects that use this
Maliot100XSkillsend-user-message
Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp). Use when the agent needs to notify, alert, or send an unsolicited message to a user — especially during heartbeat invocations, scheduled tasks, or when the agent wants to reach out without a prior user message in the current conversation. Triggers: 'send message to user', 'notify user', 'alert user', 'message the user on discord/telegram/whatsapp', or any need to proactively communicate with a paired sender.
Also in 4 projects that use this
jh941213Skilldocs-ci
문서 CI(링크·OpenAPI lint·breaking 게이트·mermaid 검증)나 문서 드리프트 감지(docs.yaml 신선도 검사)를 설치하거나 돌릴 때 사용. 문서 내용 작성은 docs-architecture·docs-interfaces·docs-manuals.
Also in 3 projects that use this
jh941213Skilldocs-interfaces
API·이벤트 인터페이스 문서(OpenAPI·swagger·AsyncAPI 명세, 엔드포인트 레퍼런스, API 구성도·시퀀스, API CHANGELOG)를 만들거나 코드와 맞출 때 사용. 시스템 구성도는 docs-architecture, API 설계 원칙은 api-design-principles.
Also in 3 projects that use this
- +6 more from naman10parikh
- +1 more from jh941213
Other versions99 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 99
- google-gemini/gemini-cli★ 109ksame name
- jlia0/tinyclaw★ 3.6ksame name
- TinyAGI/tinyagi★ 3.6ksame name
- TinyAGI/tinyclaw★ 3.6ksame name
- Chachamaru127/claude-code-harness★ 3.2ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- Muuuun/luxas★ 1.2ksame name
- shobcoder/shob★ 575same name
- boshu2/agentops★ 453same name
- makushingu/harness-maxxing★ 161same name
89 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 repository8 other files it gives its agents.
- aidesktopSkill
- cellforgeSkill
- crewSkill
- liveSkill
- mail-assistantSkill
- nexuscrew-agentSkill
- nexuscrewSkill
- vl-msaSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 6 are distinctive, and 11 are very specific to this project.
0
Common
Most of the 82 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the exposed Memory MCP tools rather than reading or editing the server's database, cache or state files directly.
- Distinctive: line 20
Keep category names, tool names, JSON fields, paths and quoted source text unchanged unless the user explicitly asks to translate them.
- Very specific: line 29
Every write is versioned; inspect memory_history when provenance matters.
- Distinctive: line 30
Treat recalled state as a snapshot.
- Very specific: line 35
Call memory_list to discover available categories.
- Very specific: line 36
Read only relevant categories with memory_read, or load a bounded set with memory_context.
- Very specific: line 38
Use memory_search when the category is unknown.
- Distinctive: line 40
Do not load every category by default.
- Distinctive: line 51
Never write another device's namespace unless the server ACL and the user's request explicitly authorize it.
- Very specific: line 56
Use memory_append for a bounded append-only log category.
- Distinctive: line 59
Do not simulate a journal by adding ever-growing dated keys to a normal memory category.
- Very specific: line 61
Do not use memory_write on a log category.
- Very specific: line 62
Do not use memory_append on a normal memory category.
- Very specific: line 74
Use memory_search for BM25 full-text retrieval across categories.
- Very specific: line 75
Use memory_search_semantic only when the server exposes and supports it.
- Very specific: line 76
Use memory_history to inspect versions before restoring or explaining a change.
- Very specific: line 80
If no Memory MCP tool is available and this skill is packaged with NexusCrew, the optional companion is documented in …
“Common” is measured: kept by at least 6 in 10 of the 82 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
Memory
Use the exposed Memory MCP tools rather than reading or editing the server's database, cache or state files directly.
Select response language
Choose the language for explanations and summaries in this order:
- the user's explicit language preference;
- the language of the current request;
- a reliable client or system locale;
- English.
Keep category names, tool names, JSON fields, paths and quoted source text unchanged unless the user explicitly asks to translate them.
Understand the model
- A category is a named JSON document.
memory_readtakes acategory, not a nested key. - Reads may be broadly available while writes are scoped by the server's device or actor ACL.
- Every write is versioned; inspect
memory_historywhen provenance matters. - Treat recalled state as a snapshot. Verify live files, flags and services before acting on drift-prone facts.
Warm up narrowly
- Call
memory_listto discover available categories. - Read only relevant categories with
memory_read, or load a bounded set withmemory_context. - Use
memory_searchwhen the category is unknown.
Do not load every category by default.
Write safely
memory_write {category, data} replaces the category by default, where
data is the JSON object to store.
- Set
merge:truefor a top-level patch: supplied keys are inserted or overwritten, JSONnulldeletes a key, and untouched keys remain. - Pass
expected_hashfrom the prior read/list result for read-modify-write workflows so concurrent updates fail instead of being overwritten. - Never write another device's namespace unless the server ACL and the user's request explicitly authorize it.
Separate state from journals
Use memory_append for a bounded append-only log category. The server stamps
entries and prunes them according to retention.
- Do not simulate a journal by adding ever-growing dated keys to a normal memory category.
- Do not use
memory_writeon a log category. - Do not use
memory_appendon a normal memory category.
A useful convention is:
<name>_state: lean declarative state, updated withmemory_write;<name>_log: bounded event journal, updated withmemory_append.
Facts that must never be pruned belong in normal durable state or an external document store, not in a bounded log.
Search and inspect
- Use
memory_searchfor BM25 full-text retrieval across categories. - Use
memory_search_semanticonly when the server exposes and supports it. - Use
memory_historyto inspect versions before restoring or explaining a change. - Report writes only after the tool confirms them.
If no Memory MCP tool is available and this skill is packaged with NexusCrew,
the optional companion is documented in ../../MCP_COMPANIONS.md. Explain the
missing capability and ask before installing or configuring anything.
Dependencies
Bundled: nothing — this skill is documentation only.
External (you must provide):
| Need | Install | Probe / failure mode |
| A Memory MCP server (companion) | optional companion mcp-memory-rs: https://github.com/DioNanos/mcp-memory-rs — the repository's Install section is authoritative and may change; this skill deliberately does not duplicate its commands (not verified here) | if the companion is not registered, the client exposes no memory_* tools; ask the client for its tool list rather than guessing |
| Client MCP registration | register the companion's stdio command in the AI client's MCP config | same failure mode as above: absent tools, not a runtime error |
Without the companion this skill is not usable in that session: say so and
suggest the companion once (see the packaged mcp-companions.json catalog)
instead of approximating with file reads.
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.

