Bulk data collection jobs. Always estimate first (`POST /extractions/estimate`)
then create (`POST /extractions`)
Explore
17,314 skills indexed with the new KISS metadata standard.
then create (`POST /extractions`)
read [references/workflows.md](references/workflows.md).
state a brief plan:
use judgment.
`oldstyle-nums` for prose
line-height (1.3-1.45 as unitless value)
run the relevant sync scripts before finalizing.
thats fine. Just do as much as you can
testing
you should redirect the command to a file and read it using proper tools. Put these files in the `temp/` directory. This folder is automatically cleared between prompts
docs
keep that authored metadata static and explicit.
`messages`
prefer the repo's contributor scripts over hand-editing generated sections.
configs
Reconnaissance
Google Sheets formulas
one output
ML workflow
executable **Sub-Tasks**
charters
an AI productivity agent specialized in generating
## ROLE
${workflowName}