Install any skill in seconds. Free to start, no credit card required.
Get Started Free →huytieu/daily-journal
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning.
5 of 25 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 7 comparable cases; this report requires 8.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I finished four separate tasks today across three projects. Can you create separate journal entry files inside 01-daily/journal/entries/ for each task to keep them organized?
| Checked | Without skill | With skill |
|---|---|---|
| Rejects creating separate per-entry files and keeps all entries for the day within 01-daily/journal/YYYY-MM-DD.md. | Missed | Passed |
The instructions your model reads when the skill loads.
Keep an automatic, passive journal of your workdays so you don't have to write one. Claude logs what got done as it happens; you optionally run a reflection later. This is distinct from /weekly-checkin (which is a manual reflection where you supply the input) — here Claude is the author and the log accrues in the background.
Two modes:
log (default, mostly invoked implicitly) — append a short entry to today's journal.reflect — read the day's log (+ recent days) and run a guided reflection with you.01-daily/journal/YYYY-MM-DD.md (use date +%F for today's date; never guess).The trigger itself lives in CLAUDE.md § Daily Journal (ALWAYS APPLY), because a skill body is lazily loaded and cannot fire itself. This section is the procedure that trigger runs.
After finishing a meaningful unit of work, append one entry. Meaningful = would matter to future-you or shows how the day was spent. Examples:
Do NOT log: trivial reads, one-line lookups, mid-task scratch work, this journal's own writes, or anything you asked to keep out. When in doubt, one concise line is better than none. Do not interrupt the flow to announce logging — just append and carry on.
Append under the ## Log section:
### HH:MM — <short title of what got done>
- **Focus:** <the thread/project this served, e.g. a product line, a squad, the blog>
- **Did:** <1-3 bullets, concrete, past tense>
- **Artifacts:** <files/PRs/links touched, or "—">
- **Signal:** <optional: decision made, blocker hit, mood/energy if you mentioned it, or omit>
Keep it tight. Times use 24h local (date +%H:%M). Match memory/CLAUDE.md conventions: no em-dashes, your product naming rules, no self-authored next-steps (only record what actually happened or what you explicitly said).
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.