agentleFS
TakaGotoTakaGoto/rag-learning-academy/.claude/skills/journal/SKILL.md

journal

Skill24 starsChanged 19 days agoMITView on GitHub

Write a quick note about what you learned or what confused you

21 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

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

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 4

    Distinctive

    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. Very specific:

    If the learner provides text with the command (e.g., /journal embeddings finally make sense — it's just coordinates in meaning space), use …

    line 12
  2. Distinctive:

    If no text is provided, prompt: "What's on your mind?

    line 14
  3. Distinctive:

    Keep their original words.

    line 37
  4. Distinctive:

    Keep it short. Respond based on the category:

    line 41
  5. Distinctive:

    Don't turn this into a teaching moment unless they ask.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 16 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

Journal: Capture Your Thoughts

A lightweight way for learners to jot down what clicked, what confused them, or what they want to revisit. These notes feed back into the curriculum director's recommendations.

Step 1: Get the Entry

If the learner provides text with the command (e.g., /journal embeddings finally make sense — it's just coordinates in meaning space), use that directly.

If no text is provided, prompt: "What's on your mind? Could be something that clicked, something confusing, a question for later, or just a note to yourself."

Step 2: Categorize

Tag the entry with one of these categories based on content:

  • insight — something that clicked or a connection they made
  • confusion — something they don't understand yet
  • question — something they want to explore later
  • idea — a project idea or experiment they want to try
  • note — general observation

Step 3: Save the Entry

Append to progress/journal.md. Create the file if it doesn't exist.

Format:

### [date] — [category]
[their entry text]

Keep their original words. Don't rewrite or polish — this is their voice, their notes.

Step 4: Brief Response

Keep it short. Respond based on the category:

  • insight: Acknowledge it. "Solid mental model. That analogy will serve you well when things get more complex."
  • confusion: Normalize it and offer help. "That's a common sticking point. Want me to /explain [topic] from a different angle?"
  • question: Acknowledge and bookmark. "Good question. We'll hit that in [relevant module]. Or run /explain [topic] now if you're curious."
  • idea: Encourage it. "That's worth trying. When you're ready, /sandbox can help you prototype it."
  • note: Just confirm. "Noted."

Don't turn this into a teaching moment unless they ask. The journal is for them, not for the system.

Suggest next steps if appropriate:

  • /lesson to continue learning
  • /roadmap to check your progress
  • /explain [topic] if a confusion entry points to a specific concept

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.