Judge, per atomic content unit, whether a target text (summary, abstract, or other candidate text) contains it — binary present/absent (ACU) or ternary support/partial_support/not_support (Nugget), per caller's value domain. Use this after atomic-unit-writing has produced the reference units, as the matching step before recall aggregation.
SkillScore91Maintained
Automatic
◆AI Engineer pack
Last verified 9/7/2026
What it changes
Passed 20 of 22 test cases with the skill, and 14 of 22 without it.
Without skill64%
With skill91%
Checks it passed that the model alone missed
Identifies Nugget as using a ternary value domain
Restricts ACU coverage judgment to two binary states
Indicates that spawned subagents have full MCP tool access
and 3 more in the full report
6 fixed14 passed either way2 still failing0 broke
Pass-rate lift
+27 pp
Tokens
-33%
Agent turns
0%
Response time
-27%
Model gemini-3.6-flashMeasured 9/7/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
In Nugget-based evaluation, a reviewer asks whether a nugget can only be marked as completely present or completely absent. What coverage options does the Nugget framework allow?
What was checked, without and with the skill
Checked
Without skill
With skill
Explains that Nugget evaluation uses a ternary classification scheme
Missed
Passed
case-11 · gemini-3.6-flash · 9/7/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md17 linessingle file
Atomic Unit Matching
Per-unit coverage judgment against a target text — binary (ACU) or ternary (Nugget) value domain. Middle step of the atomic-unit 3-chain.
Execution
Subagent — spawned via spawn-agent skill.
Available SOPs
SOP
When to use
spawn-agent
Spawn a customized CC subagent with full MCP tool access.