agentleFS
jakubtobiaszjakubtobiasz/second-brain-template/.agents/skills/brain-review/SKILL.md

brain-review

Skill0 starsChanged 9 days agoMITView on GitHub

Run a daily or weekly review of the second brain. Read recent journal entries, log.md, inbox and active projects, then propose what to promote into the wiki, which tasks and open loops need attention, and what to ingest next. Proposes only, it applies nothing without approval. Use when the owner says "daily review", "weekly review", "what's on my plate", "what did I miss", or "process my journal".

4 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. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which proposals to act on.

    line 49
  2. Distinctive:

    Never edit journal files. Quote or link them instead.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 4 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

Review: daily / weekly

You read; the owner decides. Never edit 40-journal/.

Window

  • Daily: since the last review entry in log.md (or the last 1-2 days).
  • Weekly: last 7 days. Default to weekly if unspecified and it's been more than 3 days.
  • Find the last review: grep "^## \[.*\] review" log.md | tail -1.

Gather

  1. Journal entries in the window: 40-journal/YYYY-MM-DD.md (Ideas and Tasks sections especially).
  2. log.md entries in the window: what was ingested, asked, changed.
  3. Inbox: items waiting, oldest first, with age.
  4. Active projects: last log entry date + Next: items; flag projects silent for more than 14 days.
  5. Recent 50-outputs/queries/ with filed_back: false.

Write the review

Save to 50-outputs/queries/YYYY-MM-DD-weekly-review.md (or -daily-review) with type: query:

# Weekly review: YYYY-MM-DD

## Highlights
- 3-5 bullets: what moved this week (ingests, decisions, insights), with links.

## Promote to wiki (proposed)
- [ ] Journal idea "<…>" ([[40-journal/2026-…]]) → new/updated page [[…]]
- [ ] Query answer [[50-outputs/queries/…]] → file back as synthesis

## Open loops
- [ ] Task/commitment from journal or project logs, with link. Re-check it isn't already done before listing it.

## Projects
| Project | Last update | Next | Flag |

## Inbox (N items)
- oldest first, with age and a suggestion: ingest / archive / ask

## Suggested focus
- 1-3 things for the next period.

Then

  • Log: ## [YYYY-MM-DD] review | weekly + - saved: …. Run scripts/qmd-sync.sh.
  • Ask which proposals to act on. Promotions run through the normal rules (citations, links, index, log). Tasks move to project logs or stay in the owner's journal (the owner writes that).

Hard constraints

  • Never edit journal files. Quote or link them instead.
  • Propose; don't apply. The owner checks the boxes.

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.