Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 8 skills + 24 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP-class manuscripts.
Skill Claude CodeCodex
Fully automatic radial exploration engine for divergent research ideation, or for exhaustively finding ways to solve one concrete hard problem. The data model is a phylogenetic tree: root = the starting point (topic / problem / current research state), node = one idea, depth = number of divergence layers, width =…
Skill Claude CodeCodex
Make the plugin yours. Walks the whole calibration chain for one field — corpus intake, profile extraction, per-axis calibration, optional model training, a held-out provenance measurement, and finding-level labelling against your own standard, style and target journal — then verifies the result. Every axis reports…
Skill Claude CodeCodex
Whole-document condensation. Removes every passage that is unnecessary or already stated elsewhere: claims and numbers repeated across sections, zero-information paragraphs, dead definitions and uncited figures, verbose constructions. Executes SCIPAPERSTANDARD §5.3 (condense, do not accumulate): the default direction…
Skill Claude CodeCodex
The single de-AI skill. Chains three passes over one target file: (1) in-house de-AI subsystem measurement (L0 lexicon plus L1-L4 structural and learned signals), (2) a vendored humanizer structural-tell audit (AIScientists-Dev/academic-humanizer Layers 1-5 plus blader/humanizer patterns 2.12-2.16 and the Pass-2…
Skill Claude CodeCodex
Review every paper figure from the compiled document at print-realistic 150 DPI. Verify figure/caption/data consistency, required labels, units, references, readability, accessibility, float placement, and cross-figure visual coherence. Report SCIPAPERSTANDARD typed findings: objective figure/build contradictions as…
Skill Claude CodeCodex
Pre-submission final-review orchestrator. Each round loads /sci-paper:paper and SCIPAPERSTANDARD as the framework, then runs paper-review (all A-R dimensions, including the narrative spine and adversarial escalation), figure-review, de-ai (--audit-only structural-tell audit) and the physics, mainline and logic…
Skill Claude CodeCodex
A research-paper review method that checks the reasoning, statistics, and match between claims and evidence.
Skill Claude CodeCodex
A research-paper review method that checks whether the paper's main story and contributions make sense to a reader unfamiliar with the work.
Skill Claude CodeCodex
Strict, source-traced scientific paper review. Runs all A-R dimensions under the SCIPAPERSTANDARD feedback contract: mathematics, physics, logic and statistics, language and de-AI, document structure and narrative spine (contribution graph plus a seven-question cold read), citation existence and relevance, data and…
Skill Claude CodeCodex
Load the unified SCIPAPERSTANDARD writing guidance, formula derivation conventions, scientific-integrity rules, canonical L0 examples, and field-specific reference anchors for ApJ/MNRAS/PRD-level papers. Use when writing or reviewing scientific content.
Skill Claude CodeCodex
A physics fact-checking skill that tests a scientific manuscript from basic principles. It checks units, limiting cases, symmetries, conservation laws, statistical assumptions, calculations, numerical sources, and references.
Skill Claude CodeCodex
Funding-proposal editing mode (NSF Project Summary/Description, NIH Specific Aims, fellowship proposals). Keeps the vision-and-feasibility register a paper would trim, enforces claim-feasibility matching, edits the score-forming first pages hardest, and applies the shared L0 lexical policy. Never invents preliminary…