quick-task-capture
Skill1 starsChanged 12 days agoMITView on GitHub
Use when the user says "remember to X", "I need to Y later", "add a todo", "capture this", "log a task", or otherwise wants something tracked without leaving the conversation. Also the back-end for the /stos-task slash command.
In this repository29 other files it gives its agents.
- ads-studioSkill
- blog-post-and-newsletterSkill
- calendarSkill
- chapter-draftingSkill
- character-mergeSkill
- financeSkill
- getting-startedSkill
- manuscript-importSkill
- manuscript-revisionsSkill
- markersSkill
- marketing-studioSkill
- mentionsSkill
- pen-namesSkill
- sales-studioSkill
- social-handoffSkill
- story-bibleSkill
- stos-setupSkill
- tasksSkill
- timelineSkill
- time-trackingSkill
- wordpress-connectSkill
- wordpress-llm-optimizationSkill
- wordpress-mediaSkill
- wordpress-pagesSkill
- wordpress-postsSkill
- wordpress-productsSkill
- wordpress-seoSkill
- worldbuilding-mergeSkill
- worldbuildingSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
If the user gave more context than fits in the title, put it in a short description.
- Very specific: line 21
If the user named a pen name, scope it (see pen-names skill).
- Very specific: line 22
Call stos_tasks_create({ fields: { task_name, description?
- Very specific: line 29
You: Call stos_tasks_create({ fields: { task_name: "Schedule call with audiobook narrator", description: "Aim for next week" } }).
- Very specific: line 33
You: Call stos_tasks_create({ fields: { task_name: "Finish chapter 12 by Friday" } }).
- Distinctive: line 37
Don't ask follow-up questions for a quick capture.
- Distinctive: line 38
Don't pull the full task list afterward.
- Distinctive: line 39
Don't try to schedule, prioritize, or assign — that's a different flow.
≈ “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
Quick Task Capture
When to Use
The user wants a one-shot task captured into StorytellerOS. Triggers:
- "Remember to email the cover designer about the rebrand"
- "Add a todo: finish chapter 12 by Friday"
- "I need to log an expense for the editor later"
- The
/stos-taskslash command
Flow
- Extract a short, action-oriented title (≤ 80 characters). Strip filler like "remember to" or "I need to".
- If the user gave more context than fits in the title, put it in a short description.
- If the user named a pen name, scope it (see
pen-namesskill). Otherwise omit and let it land on the active pen name. - Call
stos_tasks_create({ fields: { task_name, description? }, penNameId? }).task_nameis the required field. - Confirm back to the user with the task title and (if returned) the id, in one line. Don't recap the full body.
Examples
User: "Remember to schedule a call with the audiobook narrator next week."
You: Call stos_tasks_create({ fields: { task_name: "Schedule call with audiobook narrator", description: "Aim for next week" } }). Reply: "Captured: 'Schedule call with audiobook narrator'."
User: "/stos-task finish chapter 12 by Friday"
You: Call stos_tasks_create({ fields: { task_name: "Finish chapter 12 by Friday" } }). Reply: "Captured: 'Finish chapter 12 by Friday'."
Don't
- Don't ask follow-up questions for a quick capture. The whole point is speed. If something is genuinely ambiguous (e.g., "remember to do that thing"), ask once, briefly.
- Don't pull the full task list afterward. The user wanted to add one thing, not review everything.
- Don't try to schedule, prioritize, or assign — that's a different flow.
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.

