engineering-config-grading
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
(Proposal, unverified) Grade reproducibility-relevant engineering configuration items (hyperparameter search range, compute budget, seed handling, dataset splits) on a complete/partial/none scale, requiring the grader to first define what "complete" means per item before judging against it. Use this after study-design-tool-gate has dispatched an ML/CS engineering paper here; this is a graded QUALITY judgment, distinct from dual-column-self-check's binary Yes/No/NA self-audit checklists.
In this repository34 other files it gives its agents.
- acu-nugget-recallSkill
- argumentative-zoningSkill
- atomic-unit-matchingSkill
- atomic-unit-recall-aggregateSkill
- atomic-unit-writingSkill
- claim-label-predictionSkill
- claim-writingSkill
- domain-level-judgmentSkill
- dual-column-self-checkSkill
- 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
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
No primary-source precedent (unlike NOS, which it's structurally modeled after but applies to a different content layer).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Engineering Config Grading (Proposal)
Graded (not binary) reproducibility-config quality judgment. Fills the quality-judgment × engineering-metadata gap in the evaluative-stance × content-layer matrix (spec §2, matrix-generation phase). Per coverage-audit M14: an earlier draft folded this into dual-column-self-check via a value-domain toggle alone, which dropped the actual judgment-defining action (establishing what "complete" means) that distinguishes this from a binary checklist.
Execution
Subagent — spawned via spawn-agent skill.
Proposal Status — Read Before Modifying
No primary-source precedent (unlike NOS, which it's structurally modeled after but applies to a different content layer). Keep "(Proposal, unverified)" in the description until real usage validates the method.
<!-- 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.