agentleFS
Sign inStart free
poruzettoporuzetto/ultra-second-brain/skills/diary/SKILL.md

diary

Skill1 starsChanged 5 months agoMITView on GitHub

Chat with / check the ultra-second-brain memory. Use when the user asks "what have we tried/learned about X", "have I solved this before", "what failed last time", "check the diary", or wants references that drill into detailed records. Reads the `memory` MCP server provided by this plugin.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Get the headline: Call memory.recall(query=<question>, scope="all").

    line 13
  2. Distinctive:

    Keep it tight: short answer first, evidence one click away.

    line 28
  3. Very specific:

    If $ARGUMENTS is empty, call memory.status() and memory.recall(scope="diary"), summarize the most recent diary findings, and ask what they …

    line 30

“Common” is measured: kept by at least 6 in 10 of the 10 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

Diary — query your second brain

You have a memory MCP server (from the ultra-second-brain plugin). Use it to answer the user's question. $ARGUMENTS is the question (may be empty).

How to answer

  1. Get the headline. Call memory.recall(query=<question>, scope="all").
    • diary hits are the distilled, groundbreaking findings — lead with these.
    • records are detailed unit entries (edits, commands, iterations, commits).
  2. If they ask what failed / what was tried, also call memory.reflect(task=<question>) to surface past dead-ends and their fixes, so you can tell them what to avoid.
  3. For a specific experiment, call memory.iterations(experiment_id=…) to lay out the full arc, including the failed attempts.
  4. To drill in, call memory.get(id_or_slug=…) on any record/finding for the full text and its cross-vault references.

How to present

  • Lead with the headline finding (one or two lines).
  • Then list references: for each, show vault_id/record_id and the obsidian:// link so the user can jump straight to the full detail in the relevant repo's wiki.
  • Keep it tight: short answer first, evidence one click away. Don't dump raw records.

If $ARGUMENTS is empty, call memory.status() and memory.recall(scope="diary"), summarize the most recent diary findings, and ask what they want to dig into.

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