atomic-unit-recall-aggregate
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
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.
In this repository34 other files it gives its agents.
- acu-nugget-recallSkill
- argumentative-zoningSkill
- atomic-unit-matchingSkill
- atomic-unit-writingSkill
- claim-label-predictionSkill
- claim-writingSkill
- domain-level-judgmentSkill
- dual-column-self-checkSkill
- engineering-config-gradingSkill
- first-pass-skimSkill
- keshav-three-passSkill
- multi-stage-cascade-extractionSkill
- paper-fetchSkill
- qalmriSkill
- qalmri-worksheetSkill
- qasper-evidence-qaSkill
- quality-appraisal-checklistSkill
- question-framingSkill
- rationale-selectionSkill
- reforms-gradingSkill
- reporting-standard-checklistSkill
- reproducibility-third-party-verificationSkill
- research-question-appraisalSkill
- rhetorical-structure-qualitySkill
- second-pass-graspSkill
- signalling-question-answeringSkill
- star-awardingSkill
- study-design-tool-gateSkill
- sum-threshold-scoringSkill
- template-slot-fillingSkill
- third-pass-deep-readSkill
- unit-classificationSkill
- unit-segmentationSkill
- worst-case-lookupSkill
The file
Files
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.
<!-- BEGIN available-tables (generated) -->Available SOPs
| SOP | When to use |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. |
<!-- END available-tables (generated) -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.