Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →anthropics/investigation-memo
Draft or update the privileged investigation memo from the investigation log.
Passed 23 of 25 test cases with the skill, and 7 of 25 without it.
and 22 more in the full report
16 fixed7 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
We've added two new witness statements to the log for the 'TechCorp Data Exfiltration' investigation. Please update our existing memo draft with the recent entries.
| Checked | Without skill | With skill |
|---|---|---|
| The output explicitly displays the diff or summary of new findings added since the last version before presenting the updated draft. | Missed | Passed |
| The response marks the output with PRIVILEGED AND CONFIDENTIAL — ATTORNEY WORK PRODUCT. | Missed | Passed |
The instructions your model reads when the skill loads.
Drafts the first cut of the privileged investigation memo from the log, or updates an existing draft when new data has been added.
internal-investigation reference skill and run Mode 4 (Draft or update memo)./employment-legal:investigation-memo [matter name]
/employment-legal:investigation-memo [matter name]
(updates existing memo if one exists)
Detailed memo structure, credibility-assessment framework, and update rules live in the
internal-investigationreference skill — load it before doing substantive work.
test cases passed, vs 7 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.