agentleFS
Sign inStart free
rumotionrumotion/ai-agent-project-template/.agents/skills/docs-memory-maintainer/SKILL.md

docs-memory-maintainer

Skill1 starsChanged 41 days agoMITView on GitHub

Updates project documentation and Memory Bank files after meaningful changes. Use after features, refactors, setup changes, architecture decisions, or user requests to update memory.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Update only what changed.

    line 17
  2. Very specific:

    If asked to "remember" something that must survive a model switch, the answer is a Memory Bank file.

    line 42

≈ “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

Docs and Memory Maintainer Skill

Read:

  1. AGENTS.md
  2. memory-bank/00-index.md
  3. Relevant Memory Bank files
  4. Relevant docs in docs/

Update policy

Update only what changed.

Prioritize:

  • memory-bank/activeContext.md
  • memory-bank/progress.md
  • memory-bank/decisions.md
  • memory-bank/systemPatterns.md
  • memory-bank/techContext.md

Keep entries concise.

Where memory goes

The checked-in Memory Bank is the only durable, cross-model store.

  • Write durable project state to memory-bank/*.md. It is committed, so every model and machine sees it.
  • Never write durable state to an MCP memory server. The starter memory server persists to .mcp/memory.json, which is gitignored — anything stored there is invisible to the next model and lost on a fresh clone. Treat it as session scratch only.
  • The same applies to provider-native memory (Claude auto memory, Gemini saved memory, Codex local memory): advisory recall, never the source of truth.

If asked to "remember" something that must survive a model switch, the answer is a Memory Bank file. See docs/context-memory-bridges.md.

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.

Check your setup, free