eod
Skill1 starsChanged 6 days agoMITView on GitHub
End-of-day check-in. Asks up to three questions about the topics that are live right now and files each answer in the vault daily note or the project note. Use when the user says "eod", "end of day", "fin de journée", or just before /wrap.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- sschemel/second-brain-startertheir own version, first seen Oct 30, 2026
- jcurbelo/agent-seedtheir own version, first seen Oct 17, 2026
- latuconsinafr/claude-code-configtheir own version, first seen Oct 13, 2026
- DINAKAR-S/company-ai-ostheir own version, first seen Aug 9, 2026
- DScardini91/agentic-ostheir own version, first seen Jun 26, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- jcurbelo/agent-seed★ 8same name
- DINAKAR-S/company-ai-os★ 2same name
- DScardini91/agentic-os★ 2same name
- latuconsinafr/claude-code-config★ 0same name
- sschemel/second-brain-starter★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
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
- Distinctive: line 16
Keep the live topics (at most 3) with the least trace today: no note, no commit, no thread update.
“Common” is measured: kept by at least 6 in 10 of the 5 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.
Files
End of day
Main session (AskUserQuestion needs it). Goal: capture what the owner worked on that no tool recorded. Cheap: scripts pick the topics, the model only asks and files.
1. Pick topics (no exploration)
bin/crow-notes --since 3d: tags and topics already noted (the ones with a trace are lower priority).<state>/open-threads.md(sections Me, Crow, Waiting; seerunbooks/open-threads.md), vaulthot.md, Jira In Progress / Merge Review (if connected),bin/crow-activity --since today.- Keep the live topics (at most 3) with the least trace today: no note, no commit, no thread update.
2. Ask
One AskUserQuestion call, one question per topic, each self-contained: the topic, what is known, 3 options (e.g. progressed / blocked / not touched today) plus the free "Other". Never more than 3 questions. Nothing live, nothing asked.
3. File (one answer, one place)
| Answer is about | Goes to |
| Something done or decided | bin/crow-note "<text> #tag" --section eod |
| A meeting or call | bin/crow-note "<text>" --section meetings |
| A blocker | bin/crow-note "<text> #blocage" --section eod |
| A project fact | the project note under 10 Work, appended as one bullet |
| A new open item | <state>/open-threads.md, one line - [ ] YYYY-MM-DD [project] text → next step under ## Me, ## Crow or ## Waiting (Waiting starts with the person) |
| An open item now finished | remove its line from open-threads.md and log - HH:MM [project] done: text in activity/YYYY-MM-DD.md |
| "Not touched" / skipped | nothing |
Rules: never write a status note into open-threads.md; write in the language of the note (French in the vault), short and declarative. Never edit outside the agreed sections, never rewrite existing lines, never touch another person's content. Tags: #team #naval #blocage #decision #demo (extend only when asked).
4. Report
Print what was written and where, one line each. Then suggest /wrap.
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
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.