Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →learnprompt/receipt-renamer
Prepare a dry-run rename plan for a batch of receipt PDFs.
Passed 9 of 15 test cases with the skill, and 5 of 15 without it.
and 6 more in the full report
8 fixed5 passed either way7 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which CLI option flag identifies the source batch manifest file `incoming/batch-1/receipts.json` when running `plan-renames.mjs`?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies --batch as the manifest file option flag. | Missed | Passed |
The instructions your model reads when the skill loads.
Use the naming policy, keep the run as a dry run, and let the deterministic planner do the filename work.
incoming/normal-batch/receipts.jsonreports/reports/Confirm this is a dry run and that no files should be renamed yet.
Read the naming policy.
Run:
node .agents/skills/receipt-renamer/scripts/plan-renames.mjs \
--batch <batch-manifest> \
--policy .agents/skills/receipt-renamer/references/naming-policy.md \
--report <report-path> \
--json <json-path>
If the planner exits 21, stop and report which receipt is missing currency.
If the planner exits 23, stop and report which target filename conflicts.
On success, summarize the planned target filenames and point to both generated report files.
Only run npm test if the caller explicitly asks for verification after the dry-run plan exists.
0.test cases passed, vs 5 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.