andyed

andyed/science-agent

Plugin Claude Code

Citation, prose, figure, and rigor auditing for AI-assisted research drafts.

andyed/science-agent

Plugin Claude Code

Citation, prose, figure, and rigor auditing for AI-assisted research drafts.

andyed/science-agent

Agent

Verify figure caption numerics against their summary.json sidecars. For each figure section in an INDEX.md, walks the linked stats dump, extracts numerics from the caption prose, and matches them. Catches stale prose where a value drifted between figure regeneration and caption update. Sibling to citation-audit…

andyed/science-agent

Agent

Review research artifacts for scientific rigor before they're committed or pushed. Catches framing errors (nulls as detection limits, p-values without effect+CI, undefined metrics), unsupported claims, and presentation problems. Sibling to citation-audit (which checks citation structure) and the planned claim-audit…

andyed/science-agent

Command

Generate a key-claims summary from notebooks with ## Key Claims sections. Args: [-o ].

andyed/science-agent

Command

Search arXiv by free text; surfaces published DOIs ready to verify. Args: "query" [--max=10] [--sort=relevance] [--id=2401.12345].

andyed/science-agent

Command

Audit recent arXiv papers for citation quality. Args: [count] [--cat=cs.AI].

andyed/science-agent

Command

Audit citations in a directory against a BibTeX file. Args: --bibtex= [--json] [--verbose].

andyed/science-agent

Command

Verify figure caption numerics against summary.json sidecars. Args: [--json].

andyed/science-agent

Command

Verify [NB##:K##] claim references in prose against notebook sources. Args: [--aggregate= ] [--notebooks= ] [--cross-repo= ].

andyed/science-agent

Command

Lint paper drafts for AI-tell prose patterns. Args: [--severity=warn] [--no-pencil] [--no-muriel] [--no-native] [--summary] [--json].

andyed/science-agent

Command

Fuzzy-search CrossRef by title. Args: "title query.

andyed/science-agent

Command

Verify a single DOI against CrossRef. Args.

andyed/science-agent

Hook

Runs when a session starts, running an inline shell check. From andyed/science-agent.

andyed/science-agent

Skill Claude CodeCodex

Verify what AI writes about science — catch confabulated citations, drifted notebook numbers, and stale figure captions before they ship. Use when adding or reviewing academic citations, BibTeX entries, DOIs, or empirical claims in .md/.tex/.bib/.ipynb files; when writing a literature review; or when the user says…

andyed/muriel

Plugin Claude Code

Andy Edmonds' Claude Code plugins.

andyed/muriel

Settings file Claude Code

Agent settings declaring 14 allowed tools.

andyed/muriel

Plugin Claude Code

Multi-channel visual production skill with brand-token enforcement and 8:1 contrast minimum.

andyed/muriel

Agent

Vision-model critique agent for muriel-produced visual artifacts. Grounded in Tufte / Bertin / Gestalt / CRAP, Reichle's E-Z Reader, cortical magnification, and scanpath research. Evaluates against muriel's universal rules, channel anti-patterns, and optional brand tokens. Names issues with evidence and cites the…

andyed/muriel

Agent

Forger juror seat for a muriel jury. Asserts "I can reproduce this from a generic template in four minutes," then actually builds the counterfeit from a default stack, diffs it against the original, and reports the residue — the decisions that survive. Judges one thing only, distinguishability from competent generic…

andyed/muriel

Agent

The Pedant jury seat. Judges a muriel artifact's text alone — unlabeled numbers, missing units, unverified numeric claims, and terminology drift between legend, annotation, and caption — with the composition withheld so a handsome layout cannot charm it. Applies the numeric-claim probe list from muriel-critique.md…

andyed/muriel

Agent

The Squinter jury seat. Blurs a muriel artifact with muriel.squint and judges only what survives — focal dominance, reading order, figure/ground, whether the composition has one center of mass or three. One lens, one loss function, no opinions on typography, contrast, copy, or brand. Emits the juror ballot defined in…

andyed/muriel

Agent

The Stranger jury seat. Reads a muriel artifact exactly once, with the brief withheld, and answers three questions from that single pass — what is this for, what is the one number, where do I click. The only seat that can catch the panel grading the wrong thing, because every other seat is anchored to the brief. Fails…

andyed/muriel

Agent

The Thumbnail jury seat. Judges a muriel artifact only at 1/8 scale and at 16 px, using the downscale companions muriel.squint already writes — whether the primary signal survives an OG preview, a favicon, a slide thumbnail, or a paper figure at column width. One lens, one loss function, no opinions on full-size…