agentleFS
synamcpssynamcps/synamcps-server/.cursor/skills/save-syna-brain-memory/SKILL.md

save-syna-brain-memory

Skill4 starsChanged 12 days agoApache-2.0View on GitHub

Saves chat history and summaries of SynaMCPs server logic or visual changes to the syna-brain MCP server as second brain memory. Use when finishing a meaningful change to server logic, APIs, data objects, securebus, admin/UI visuals, or when the user asks to remember, save to brain, or persist session context.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the user-syna-brain MCP namespace (knowledge_search, knowledge_save, knowledge_get, knowledge_delete) as the project second brain.

    line 13
  2. Very specific:

    Default memory storage id (confirmed by successful knowledge_save):

    line 18
  3. Very specific:

    If the server remaps storageId to another allowed storage, use the storageId returned on the save response for later search/get.

    line 26
  4. Very specific:

    If knowledge_save fails with an auth error, call mcp_auth on user-syna-brain, then retry.

    line 29
  5. Distinctive:

    Do not delete prior memories unless the user asks to replace one.

    line 59

≈ “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.

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

Save chat history and summary to syna-brain

Use the user-syna-brain MCP namespace (knowledge_search, knowledge_save, knowledge_get, knowledge_delete) as the project second brain.

Storage

Default memory storage id (confirmed by successful knowledge_save):

268fc510-74c5-475e-9e39-74f751aaef43

Alternate:

033870b5-72a8-42c9-a15e-6dcc2e4b7c7b

If the server remaps storageId to another allowed storage, use the storageId returned on the save response for later search/get.

If knowledge_save fails with an auth error, call mcp_auth on user-syna-brain, then retry. Do not invent a substitute store.

When to save

Save after work that changes durable understanding of this repo, especially:

  • SynaMCPs server logic (handlers, MCP tools, policy, auth, data object kinds, securebus, workers)
  • Visual / UI changes (admin, /app, landing-facing copy that lives here)
  • Multi-step designs or decisions the next session would otherwise re-discover
  • Explicit user request: “save to brain”, “remember this”, “persist this chat”

Skip for trivial typos, pure renames with no behavior change, or failed explorations the user does not want kept.

Workflow

  1. Search first — knowledge_search on the memory storage with a focused query (feature name, package path, or topic). Note related docIds.
  2. Write a summary — durable facts only; no secrets (tokens, private keys, .env, session cookies). Prefer architecture, APIs, file paths, decisions, and open follow-ups.
  3. Save — knowledge_save with:
    • storageId: memory storage above
    • mimeType: text/markdown
    • title: SynaMCPs | <area> | <short topic> | <YYYY-MM-DD>
    • text: body using the template below
  4. Report — in the user reply, mention that memory was saved (title + docId if returned). If save failed, say so and keep the summary in chat.

Do not delete prior memories unless the user asks to replace one; prefer a new dated note that supersedes older context in prose.

Memory note template

# <topic>

## Context
- Chat / task: <one line>
- Date: <YYYY-MM-DD>

## Summary
<2–6 sentences: what changed or was decided>

## Server logic / behavior
- <bullet: packages, endpoints, MCP tools, invariants>

## Visual / UI (if any)
- <bullet: screens, components, UX notes>

## Key paths
- `path/to/file.go` — <why it matters>

## Decisions
- <decision and why>

## Open follow-ups
- <optional>

## Chat highlights
- <optional: critical Q/A or constraints from the session, not a full transcript>

Tool call shape

Discover schemas with GetDynamicTools on namespace user-syna-brain if needed, then invoke via CallDynamicTool:

  • Search: knowledge_search — { storageId, query, topK }
  • Save: knowledge_save — { storageId, title, text, mimeType: "text/markdown" }

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.