agentleFS
DioNanosDioNanos/nexuscrew/skills/memory/SKILL.md

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

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.
  • naman10parikhSkill

    ecosystem-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

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • Maliot100XSkill

    send-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

  • jh941213Skill

    docs-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

  • jh941213Skill

    docs-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

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
  1. Distinctive:

    Use the exposed Memory MCP tools rather than reading or editing the server's database, cache or state files directly.

    line 8
  2. Distinctive:

    Keep category names, tool names, JSON fields, paths and quoted source text unchanged unless the user explicitly asks to translate them.

    line 20
  3. Very specific:

    Every write is versioned; inspect memory_history when provenance matters.

    line 29
  4. Distinctive:

    Treat recalled state as a snapshot.

    line 30
  5. Very specific:

    Call memory_list to discover available categories.

    line 35
  6. Very specific:

    Read only relevant categories with memory_read, or load a bounded set with memory_context.

    line 36
  7. Very specific:

    Use memory_search when the category is unknown.

    line 38
  8. Distinctive:

    Do not load every category by default.

    line 40
  9. Distinctive:

    Never write another device's namespace unless the server ACL and the user's request explicitly authorize it.

    line 51
  10. Very specific:

    Use memory_append for a bounded append-only log category.

    line 56
  11. Distinctive:

    Do not simulate a journal by adding ever-growing dated keys to a normal memory category.

    line 59
  12. Very specific:

    Do not use memory_write on a log category.

    line 61
  13. Very specific:

    Do not use memory_append on a normal memory category.

    line 62
  14. Very specific:

    Use memory_search for BM25 full-text retrieval across categories.

    line 74
  15. Very specific:

    Use memory_search_semantic only when the server exposes and supports it.

    line 75
  16. Very specific:

    Use memory_history to inspect versions before restoring or explaining a change.

    line 76
  17. Very specific:

    If no Memory MCP tool is available and this skill is packaged with NexusCrew, the optional companion is documented in …

    line 80

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  1. the user's explicit language preference;
  2. the language of the current request;
  3. a reliable client or system locale;
  4. 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_read takes a category, 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_history when provenance matters.
  • Treat recalled state as a snapshot. Verify live files, flags and services before acting on drift-prone facts.

Warm up narrowly

  1. Call memory_list to discover available categories.
  2. Read only relevant categories with memory_read, or load a bounded set with memory_context.
  3. Use memory_search when 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:true for a top-level patch: supplied keys are inserted or overwritten, JSON null deletes a key, and untouched keys remain.
  • Pass expected_hash from 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_write on a log category.
  • Do not use memory_append on a normal memory category.

A useful convention is:

  • <name>_state: lean declarative state, updated with memory_write;
  • <name>_log: bounded event journal, updated with memory_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_search for BM25 full-text retrieval across categories.
  • Use memory_search_semantic only when the server exposes and supports it.
  • Use memory_history to 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):

NeedInstallProbe / 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 registrationregister the companion's stdio command in the AI client's MCP configsame 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.