Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/Cleaning Up Research Sessions
Safely remove intermediate files from completed research sessions while preserving important data
Passed 19 of 22 test cases with the skill, and 14 of 22 without it.
and 3 more in the full report
5 fixed14 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are auditing `research-sessions/2026-03-01-kinase/` after completing our synthesis. Is `initial-search-results.json` safe to remove, and what is the reason?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies initial-search-results.json as a candidate for removal. | Passed | Passed |
| Explains that the underlying paper screening data is preserved in papers-reviewed.json. | Missed | Passed |
The instructions your model reads when the skill loads.
Remove intermediate files created during research workflow while preserving all important data.
Core principle: Conservative cleanup with user confirmation. Never delete anything important.
Use this skill when:
When NOT to use:
NEVER delete these (protected list):
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.