Skill Claude CodeCodex
Use when the user asks to tag, release, or bump the version of the sci-brain plugin (e.g. "tag a version", "cut a release", "bump to 0.3.0", "release v0.x"). Handles the three-manifest version sync, commit, annotated tag, push, and GitHub release.
Skill Claude CodeCodex
Use when starting, resuming, or asking about an autoresearch project — a four-stage pipeline (topics → db → validator → run) that chooses machine-checkable research topics with score metrics and a red-teamed acceptance gate, builds the evidence base (references, INSIGHTS.md, domain database, CATALOG.md), builds a…
Skill Claude CodeCodex
Use when brainstorming research ideas or turning a completed brainstorming direction into a proposal-style ideas report — a research collaborator that understands your background, helps find interesting problems together, and preserves the reasoning trail in a structured report when requested.
Skill Claude CodeCodex
Use when analyzing conversation patterns — extracts dialog from Claude Code or Codex CLI history, classifies each user message across 6 academic dimensions (Bloom's cognitive level, Graesser question depth, Paul & Elder reasoning probe, Walton presupposition quality, Long & Sato discourse function, Graesser generation…
Skill Claude CodeCodex
Use when adding one or many new references (arXiv ID or DOI) to a sci-brain knowledge base — the project KB by default, or an advisor KB when invoked from an advisor flow. Fetches metadata via Semantic Scholar, downloads PDFs (with SciHub fallback), renders to markdown, regenerates INDEX.md, and appends to the KB's…
Skill Claude CodeCodex
Use when reviewing the visual design/quality of a figure, plot, or diagram — "is this figure well-designed", "review my plot", "critique this figure's layout/colors", "does this figure have good taste". Judges alignment, proximity, color, typography, clarity, and scientific-plot conventions against an 18-rule rubric…
Skill Claude CodeCodex
Use when attacking a single hard goal that resists a direct solution — runs an autonomous CDCL/DPLL-style search (decide → propagate → learn → backjump, with a meta-pivot when stuck), taking notes after every trial. Domain-agnostic (math, theory, design, debugging, strategy); optionally pulls facts from a project…
Skill Claude CodeCodex
Use when onboarding or updating a contributor as an advisor, importing Markdown conversation exports into an advisor profile, or extracting thinking patterns and logic jumps from classified conversations — analyzes conversation history and synthesizes a named advisor profile for the brainstorm-ideas advisor library.
Skill Claude CodeCodex
Use when indexing a paper collection (your own or another researcher's) into a knowledge base — supports Zotero library, a PDF folder, or a Google Scholar profile.
Skill Claude CodeCodex
Use when reviewing, critiquing, commenting on, or fact-checking an existing scientific manuscript — "comment on my paper", "review my draft", "check my references", "verify my claims", or a referee-style read of a .tex/.typ/.md paper. Not for drafting from scratch (use paper-writer) or for technology/field assessments…
Skill Claude CodeCodex
Use when drafting or revising a scientific manuscript with real results, including journal articles, letters, and arXiv preprints.
Skill Claude CodeCodex
Use when building a slide deck in Typst + Touying for a scientific talk, lecture, or project briefing — ships a browsable zoo of color themes, layout templates, and gadgets (callouts, theory boxes, CeTZ diagrams, pin annotations) that compose into projector-safe slides. Distinct from slide-writing (HTML, QudeLeap…
Skill Claude CodeCodex
Use when surveying a research topic or writing a grounded literature review, technology assessment, field assessment, SOTA report, or pros/cons report — explores the literature, builds a focused knowledge base with verified BibTeX, and can turn a populated knowledge base into a structured report.