reforms-grading

Featured

Tactic: Grade an ML/CS paper's reproducibility configuration reporting as complete, partial, or none after checking that clinical appraisal tools do not apply. Use when the question is whether the work can be rerun.

AI & Automation 392 stars 34 forks Updated 1 weeks ago Apache-2.0

Install

View on GitHub

Quality Score: 94/100

Stars 20%
86
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
37
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# REFORMS Grading ## Orchestration Pattern 1. Fetch the paper; stop on `not_found`. 2. Run `study-design-tool-gate` and write its verdict to `01-study-design-tool-gate.json`. 3. If it selects a clinical/review instrument, stop and name that tool. If it selects `engineering-config-grading` or returns `not_applicable`, proceed. 4. Run `engineering-config-grading`, using that tool name when the gate returned `not_applicable`, and write `02-engineering-config-grading.json`. Record `proposal_sop: true`. Each justification must state what complete reporting would look like before grading the paper. Report the gate verdict, complete/partial/none counts, every `none` item, the unverified-proposal caveat, and both paths.

Details

Author
yogsoth-ai
Repository
yogsoth-ai/de-anthropocentric-research-engine
Created
6 months ago
Last Updated
1 weeks ago
Language
HTML
License
Apache-2.0

Integrates with

Model Context Protocol · AI

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

reforms-grading

Tactic: Grade an ML/CS paper's reproducibility configuration reporting as complete, partial, or none after checking that clinical appraisal tools do not apply. Use when the question is whether the work can be rerun.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

engineering-config-grading

(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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

engineering-config-grading

(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.

1 Updated 1 weeks ago
yogsoth-ai