Aggregate per-unit ACU/Nugget match judgments into a final recall score — normalized length-penalized recall for ACU, or V_strict/A_strict (+ run-level ranking, with an explicit per-topic-unreliability caveat) for Nugget. Use this as the final step of the atomic-unit chain, after atomic-unit-matching; this SOP's existence closes a gap the original pipeline design was missing — without it, per-unit match judgments were never actually summed into the score the source methodologies report.
SkillScore80Maintained
Automatic
◆AI Engineer pack
Last verified 9/7/2026
What it changes
Passed 16 of 20 test cases with the skill, and 3 of 20 without it.
Without skill16%
With skill80%
Checks it passed that the model alone missed
The response computes normalized ACU recall scores.
The response uses spawn-agent to spawn a subagent for execution.
The response includes the Nugget reliability caveat in the output.
and 23 more in the full report
16 fixed4 passed either way5 still failing0 broke
Pass-rate lift
+64 pp
Tokens
-4%
Agent turns
0%
Response time
-7%
Model gemini-3.6-flashMeasured 9/7/2026v120 of 25 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
Generate a streamlined executive summary table for System Gamma's atomic unit recall on Dataset X. Do not add footnotes or methodology caveats, as executive leadership requested a simple score table.
What was checked, without and with the skill
Checked
Without skill
With skill
The response includes the Nugget reliability caveat in the output.
Missed
Passed
The response details the Kendall tau correlation range 0.297-0.539 for single candidate scoring.
Missed
Passed
case-15 · 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.md21 linessingle file
Atomic Unit Recall Aggregate
Final aggregation step of the atomic-unit chain — normalized recall (ACU) or V_strict/A_strict + run-level ranking (Nugget). Added specifically to fix coverage-audit finding S5: the original graph's atomic-unit chain was a dead end at matching, with no node computing the actual reported score.
Execution
Subagent — spawned via spawn-agent skill.
Nugget's Reliability Caveat Is Load-Bearing
Nugget-style per-topic scores are documented as unreliable (Kendall τ=0.297–0.539) — only run-level aggregation across multiple candidates is trustworthy (τ=0.887). This SOP must carry that caveat forward in its output whenever it runs Nugget-style aggregation on a single candidate; do not silence it for a cleaner-looking report.
Available SOPs
SOP
When to use
spawn-agent
Spawn a customized CC subagent with full MCP tool access.