agentleFS
edrethardoedrethardo/werkbank-board/.claude/skills/journaling/SKILL.md

journaling

Skill0 starsChanged 3 months agoMITView on GitHub

Use at session end, after completing or abandoning any task, or when an approach fails — record what happened in docs/journal/ so no future session re-investigates it.

2 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

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. Very specific:

    Add one line to docs/journal/INDEX.md under ## Entries, newest first (replacing the _(none yet)_ placeholder if it is still there):

    line 36
  2. Distinctive:

    After anything surprising: a wrong assumption, a tool quirk, a decision reversal.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Journaling

One file per entry: docs/journal/YYYY-MM-DD-<short-slug>.md. English, regardless of the user's language. Write for a stranger: a future session with zero memory of today.

Entry format

Frontmatter:

---
title: <one line>
date: YYYY-MM-DD
tags: [tag, tag]          # only tags from docs/TAGS.md — new tag = add it there, same commit
summary: <one sentence>
outcome: done | partial | failed | abandoned
---

Body sections, in order:

  1. What was asked — the user's request in one or two sentences.
  2. What I did — the actual changes, with file paths and commit subjects.
  3. What I tried that didn't work — and why — MANDATORY. With evidence: exact commands run, error messages seen, numbers measured. "It didn't work" without evidence is not an entry. If nothing failed, write "Nothing failed."
  4. Decisions made — each with its why.
  5. Follow-ups — what a next session should pick up, if anything.

Index — not optional

Add one line to docs/journal/INDEX.md under ## Entries, newest first (replacing the _(none yet)_ placeholder if it is still there):

- YYYY-MM-DD — [title](YYYY-MM-DD-slug.md) — outcome — tags — summary

An entry that is not in the index is a bug. Include the index line in the same commit as the entry.

When exactly

  • At session end (always, even for small sessions — three honest lines beat nothing).
  • Immediately after abandoning an approach, while the evidence is still in context.
  • After anything surprising: a wrong assumption, a tool quirk, a decision reversal.

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.