queelius

This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.

Audit a book manuscript against Amazon KDP requirements: interior formatting, cover specs, metadata, and genre-specific checks. Handles technical books (LaTeX, math), fiction, and nonfiction. Produces a structured gap report with Critical and Warnings sections plus automation suggestions.

Orchestrate the full Amazon KDP publishing workflow: audit, listing craft, manuscript prep, cover generation, dashboard submission, pricing, publish. Phases gate each other. Handles both eBook and paperback. Manages MCP-driven cover generation or falls back to manual prep.

Discover latent themes in the metafunctor corpus. Use when the user wants to find implicit through-lines across their blog posts, surface recurring ideas they have not consciously framed as a series, or get candidate themes for a synthesis post. Reads titles, descriptions, and tags; proposes 3 themes that connect 4+ posts each, each with a single-sentence through-line. Output is a proposal, not a draft. Trigger phrases include "find themes in my posts", "what threads connect my writing", "latent themes in my corpus", "scribe".

Launch a multi-agent editorial review with 8 specialists (2 literature scouts plus 6 domain reviewers) orchestrated by an area-chair agent. Produces a unified report plus specialist reports in .papermill/reviews/. Updates .papermill/state.md.

Apply fixes from a multi-agent review report. Launches the reviser orchestrator, which triages the findings in .papermill/reviews/, dispatches section-writer specialists per finding domain, verifies each fix with the owning review specialist, and writes a revision report paired with the review. Closes the draft, review, revise loop. Updates .papermill/state.md.

Display a read-only dashboard for paper project status: stage, thesis, experiments, review history, venue, and suggested next action. Reads .papermill/state.md.

Fork an in-flight research-agent run at its current checkpoint into a named branch with its own state, log, and attempts, sharing the parent's goal and findings read-only. Use to pursue a competing strategy without disturbing the main line. The synthesize skill later compares branches.

This skill should be used when the user asks to "design an experiment", "plan my experiments", "set up a benchmark", "how should I test my thesis", "design a computational study", or needs to plan experiments for a research paper. Covers hypothesis formulation, variable identification, methodology selection, and success criteria definition. Produces a structured experiment plan with reproducibility in mind.

This skill should be used when the user asks to "outline my paper", "structure the paper", "design the paper sections", "create a paper outline", "organize my argument", or needs to design or refine paper structure. Generates a section-by-section outline with purpose, key arguments, estimated length, and narrative arc. Adapts to the paper type and venue conventions. Updates .papermill.md.

This skill should be used when the user asks to "polish my paper for submission", "pre-flight check", "is my paper ready to submit", "final check before submission", "prepare for submission", or needs final preparation before submitting a paper. Performs a systematic pre-flight check covering formatting, citations, figures, metadata, and build verification. Produces a checklist report with suggested fixes.

This skill should be used when the user asks to "survey related work", "find prior art", "literature review", "what papers are related to mine", "search for references", or needs to conduct a systematic literature survey. Reads thesis from .papermill.md, searches academic sources, classifies references, identifies gaps, generates BibTeX, and updates the state file. Can launch the surveyor agent for deep autonomous search.

This skill should be used when the user asks to "design a Monte Carlo simulation", "validate my theoretical result", "set up a simulation study", "how many replications do I need", "plan a coverage study", or needs to design simulations for verifying theoretical results. Covers sample size determination, convergence diagnostics, and result presentation. Specialized for statistical methodology papers.

This skill should be used when the user asks to "show paper status", "where am I on this paper", "what's the state of my paper", "papermill dashboard", or needs orientation on a paper project. Reads .papermill.md and presents a read-only dashboard showing stage, thesis, experiments, review history, venue, and suggested next actions.

This skill should be used when the user asks to "initialize a paper", "start a new paper project", "set up papermill", "onboard this repo", "refresh papermill", "update papermill state", or needs to create or update the .papermill.md state file. On new repos: discovers structure, infers format, gathers author info, creates state file. On existing repos: offers refresh mode that adds missing schema fields and new context without overwriting existing data.

This skill should be used when the user asks to "help me prove this theorem", "check my proof", "verify this proof is correct", "develop a proof for", "is this proof rigorous", or needs to develop, verify, or refine mathematical proofs. Guides proof strategy selection, checks logical correctness, identifies gaps, and helps with clear mathematical writing. Works with existing proof drafts or constructs from scratch.

This skill should be used when the user asks to "KDP audit", "check manuscript formatting", "is my book ready for KDP", "Amazon publishing requirements", "Kindle formatting check", "manuscript readiness", "book formatting audit", "prepare for Amazon KDP", or mentions KDP/Amazon publishing compliance. It audits a book manuscript against Amazon KDP (Kindle Direct Publishing) requirements for both eBook and paperback formats, handling technical books (LaTeX, math-heavy) and fiction/general nonfiction.

This skill should be used when the user asks to "craft Amazon listing", "write book blurb", "KDP blurb", "book description", "Amazon keywords", "book categories", "KDP listing", "improve my blurb", "help with book marketing metadata", or mentions creating or refining the marketing copy for a book on Amazon KDP. It generates blurb, keywords, categories, and author bio — the four artifacts that determine discoverability and conversion on Amazon.

This skill should be used when the user asks to "publish on KDP", "publish my book", "Amazon book publishing", "Kindle Direct Publishing", "self-publish", "publish on Amazon", "KDP workflow", "submit to Amazon KDP", "publish to Kindle", or mentions Amazon/KDP book publishing. It guides the complete workflow for publishing a book through Amazon KDP, handling both technical books and fiction/nonfiction.

This skill should be used when the user asks to "publish to PyPI", "upload to PyPI", "PyPI release", "publish my Python package", "package for PyPI", "submit to PyPI", "PyPI submission", or mentions PyPI publishing. It guides the complete workflow: auditing package metadata, running tests, building distributions, testing on TestPyPI, and publishing to PyPI.

This skill should be used when the user asks to "publish my package", "publication pipeline", "get this published", "how do I publish this", or mentions publication without specifying an ecosystem. It detects the project type (R package, Python package, or book manuscript) and routes to the appropriate ecosystem-specific publication skill.

This skill should be used when the user asks to "audit for CRAN", "check CRAN readiness", "prepare for CRAN submission", "CRAN check", "is my package CRAN ready", "submit to CRAN", or mentions CRAN submission compliance. It audits an R package against CRAN Repository Policy and submission requirements, producing a structured gap report with actionable fixes.

This skill should be used when the user asks to "audit for JOSS", "check JOSS readiness", "JOSS reviewer checklist", "prepare for JOSS submission", "is my package JOSS ready", "JOSS requirements", or mentions JOSS submission compliance. It evaluates an R package and its paper.md against the complete JOSS reviewer checklist, producing a structured gap report.

This skill should be used when the user asks to "draft a JOSS paper", "write paper.md", "create JOSS paper", "write JOSS submission", "draft paper.md for JOSS", or mentions writing a JOSS software paper. It analyzes an R package and drafts a complete paper.md and paper.bib following JOSS format requirements and patterns from successful R package papers.

Generate a persona directory from arkiv data. Creates the three-domain structure (arkiv/, portrait/, memory/), a rich CLAUDE.md behavioral core, deep portrait synthesis, dual MCP config, and all supporting files. Use when building a new persona from scratch.

Test a simulacrum's fidelity against source data. Runs held-out tests, calibration interviews, and hallucination checks. Use after generating a persona to assess quality.

Inspect a persona directory and display summary statistics. Shows arkiv data inventory, portrait files, memory session stats, and provenance. Use to understand what a persona contains.

Interview a person to elicit personality data for their simulacrum. Produces arkiv-format JSONL. Use when building a new persona or enriching an existing one with first-person data.

Validate a persona directory against the eidola v0.3 spec. Checks required files, three-domain structure (arkiv/portrait/memory), CLAUDE.md structure, data integrity, and immutable/mutable boundary. Use before sharing or after modifications.

Update a persona's CLAUDE.md and portrait/ files when new data arrives. Lightweight alternative to full regeneration that preserves manual edits. Use when new arkiv data has been imported.

Cross-post blog content to social platforms. Claude handles audit, user selection, and generates rewrites for short-form platforms.

Use when you need personal metadata about the user — name, email, ORCID, GitHub username, affiliations, education, or any other personal details. Also use when populating author fields, git identity, paper metadata, profile info, personalized content, or consolidating identity across platforms (linking handles, name variants, and emails so they resolve to the same person).

Use mf (metafunctor) to manage papers, projects, and content for the Hugo static site. Invoke for paper processing, project syncing, content linking, database queries, and backup operations.