update-tasks
Skill7 starsChanged 49 days agoMITView on GitHub
Lightweight refresh of a human-readable snapshot note mirroring your task manager's open to-dos, if you keep one for quick scanning. Reruns the export script so the note reflects current state, rather than relying on however stale it was last left. Standalone - use before trusting the snapshot note for anything. Trigger: /update-tasks, or asking to refresh/update tasks or the task export note.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- end-taskSkill
- end-the-daySkill
- link-taskSkill
- log-completed-tasksSkill
- pick-meetings-to-prepSkill
- prep-meetingSkill
- search-mailSkill
- setupSkill
- start-the-daySkill
- suggest-brag-itemsSkill
- surface-stale-tasksSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Very specific: line 33
Run your export script (e.g.
- Distinctive: line 43
Never edit the task manager itself, and never hand-edit the snapshot note
- Distinctive: line 44
if it's regenerated wholesale each run, manual edits just get overwritten next time.
- Distinctive: line 46
If the export script fails (task manager not running, a permission not yet granted, etc.), report the error plainly rather than guessing at …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Update Tasks
Purpose
A snapshot note is only as fresh as the last time the export script ran. This skill exists purely to rerun that script on demand, so any check against the note - by this skill, another skill, or the user directly - is checking current state, not a stale copy.
This is deliberately narrow - it doesn't analyse, prioritise, or surface
stale tasks (that's surface-stale-tasks's job). It just refreshes the
source of truth for anything that wants to read a readable snapshot rather
than a raw export.
Trigger
/update-tasks, or asking to refresh/update tasks, the task list, or the
task export note.
Process
- Run your export script (e.g.
skills/things3-export/run.shfor Things3) to regenerate the snapshot note from your task manager's current state. - Report back briefly - how many to-dos, across how many groups (most export scripts print this themselves), and note that the snapshot is current as of now.
- Nothing else. Don't read the note's contents unless asked a follow-up question about what's in it - this skill's job ends at refreshing it.
Notes on conventions
- Never edit the task manager itself, and never hand-edit the snapshot note
- if it's regenerated wholesale each run, manual edits just get overwritten next time.
- If the export script fails (task manager not running, a permission not yet granted, etc.), report the error plainly rather than guessing at a fix.
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.