Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →anthropics/tres-rollup-review
Compute the EXACT sub-transaction impact of a rollup rule in TRES Finance — every filter applied — and flag genuine problems (zero matches, overlap, config mistakes) before the rule is created. Two modes. Mode A: a pre-create quality gate invoked by the tres-rollup-rules skill to vet proposed candidate rules. Mode B: standalone review of a rule someone submitted or of existing PENDING rules.
Passed 13 of 18 test cases with the skill, and 4 of 18 without it.
and 11 more in the full report
11 fixed5 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When reviewing an Active or Pending rule in Mode B that is fully functional and has no issues, what text should be returned in the findings summary?
| Checked | Without skill | With skill |
|---|---|---|
| Outputs a findings summary stating no issues were found along with matching counts | Missed | Passed |
The instructions your model reads when the skill loads.
Take a fully-specified rollup rule and compute exactly which sub-transactions it will claim — with every one of its filters applied — then flag genuine problems. You do NOT design new rollups and you do NOT execute mutations.
All GraphQL runs through the TRES Finance MCP connector (execute tool). All
variable keys and nested input fields MUST use camelCase, never snake_case.
The tres-rollup-rules discovery step groups sub-txs only at the
(wallet, asset, direction) level — it never applies a single candidate's full filter
combination (fees + method_ids + subtx_type + amount bounds + counterparty +
excludeRollups together). This skill does exactly that, per rule, via the
subTransactionRollupRulePreview query (which runs the engine's real
query_sub_transactions), giving:
It is also usable standalone to review a rule someone submitted (Mode B) — a case the discovery skill doesn't cover.
tres-rollup-rules)When tres-rollup-rules invokes this skill (via the Skill tool), these instructions
load into the same context that already holds the candidate rule objects — they
are not passed as arguments, they are already in the conversation above. Iterate those
candidates one at a time; for each, run the checks below and emit exactly one
verdict:
test cases passed, vs 4 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.