agentleFS
yokeloopyokeloop/yoke/skills/journal/SKILL.md

journal

Skill1 starsChanged 4 months agoMITView on GitHub

Appends a concise, newest-first entry to `.yoke/journal.md` summarizing the session's real work and linking the relevant `.yoke/ai/<slug>/` artifacts — the first layer of yoke's connected memory. Manual trigger only, no hook. Activates when the user writes "journal", "log the session", "session journal", "write a journal entry", "log what changed", "update the journal", "record this session".

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use triage and code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read .yoke/journal.md. When it is missing, create it with the title # Journal and a one-line note.

    line 46
  2. Distinctive:

    Add a sub-entry at the top of today's section and fill in only the fields that apply, keeping each terse:

    line 50
  3. Very specific:

    When an entry for this work already exists (a prior /yoke:journal run this session), augment it instead of writing a duplicate.

    line 64
  4. Distinctive:

    Write entries in English, whatever the conversation language.

    line 68
  5. Very specific:

    Leave staging and committing to the user (e.g.

    line 72

“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

Append a short summary of this session's real work to .yoke/journal.md — an index into the detail, not a duplicate of it. The journal is the first layer of yoke's connected memory: journal → .yoke/ai/<slug>/ artifacts → the future git layer. Run it manually at or during the end of a session; no hook triggers it.

Resolve the current timestamp with a shell call (date '+%Y-%m-%d %H:%M %Z') — never invent the date or time. Treat any $ARGUMENTS as an optional focus or title for the entry.

What to log

Record only concrete work and the decisions behind it:

  • changes to skills, commands, agents, docs, or code; new, deleted, or renamed files; config changes
  • fixes and their root causes
  • alternatives deliberately rejected, so no one revisits them

Link the session's relevant artifacts by path — .yoke/ai/<slug>/<slug>-plan.md, .yoke/ai/<slug>/<slug>-report.md, .yoke/adr/NNNN-*.md — instead of restating their contents.

Skip discussions without changes, Q&A, dead-end diagnostics, and file reads. When nothing is worth recording, tell the user and write nothing.

Format

.yoke/journal.md is newest-first: the latest date section sits right after the title, and within a date the newest sub-entry comes first. Group by ## YYYY-MM-DD, then by ### HH:MM TZ — <short title>.

Steps:

  1. Read .yoke/journal.md. When it is missing, create it with the title # Journal and a one-line note.
  2. Find today's ## YYYY-MM-DD section; when absent, add one at the top, right after the title.
  3. Add a sub-entry at the top of today's section and fill in only the fields that apply, keeping each terse:
### 14:32 CET — <short title>

**What done:** what exactly changed (1–3 sentences)
**Files:** `path/one`, `path/two`
**Artifacts:** `.yoke/ai/<slug>/<slug>-plan.md`, `.yoke/ai/<slug>/<slug>-report.md` (if any)
**Why:** reason / context
**Rejected:** the alternative and why it was dropped (if any)
**Commit:** `<sha>` (check `git log`) or "not committed"

When an entry for this work already exists (a prior /yoke:journal run this session), augment it instead of writing a duplicate. Repeated runs append; never overwrite earlier entries.

Write entries in English, whatever the conversation language.

After writing

Leave staging and committing to the user (e.g. via /yoke:gca) — .yoke/ is committed by default unless the user ignores it. Report what was added and under which date and time.

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.