Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →anthropics/investigation-query
Ask questions against an open investigation log — what witnesses said, where accounts conflict, what gaps exist, what the strongest evidence is on each issue.
Passed 10 of 22 test cases with the skill, and 4 of 22 without it.
and 7 more in the full report
6 fixed4 passed either way12 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Check the Nexus Corp investigation log to see what custodian Ray Miller reported about keycard access on the 4th floor.
| Checked | Without skill | With skill |
|---|---|---|
| Outputs the standardized missing info sentence including topic name and reviewed entries count. | Missed | Passed |
| Offers to flag the missing 4th floor keycard topic as a gap. | Missed | Passed |
The instructions your model reads when the skill loads.
Answers questions against the investigation log — what witnesses said, where accounts conflict, what gaps exist, what the strongest evidence is on each issue.
internal-investigation reference skill and run Mode 3 (Query)./employment-legal:investigation-query [matter name]
What did the respondent say about the December team dinner?
/employment-legal:investigation-query [matter name]
Where do the complainant's and respondent's accounts conflict?
/employment-legal:investigation-query [matter name]
What do we still need?
Detailed log-query process, citation rules, and gap-flagging templates live in the
internal-investigationreference skill — load it before doing substantive work.
test cases passed, vs 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.