Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when building or cleaning up the tables and figures of a Strategic Management Journal (SMJ) manuscript. Makes exhibits self-contained and persuasive; it does not run the analysis or write prose.
Use when preparing an accepted IEEE VIS paper for its IEEE TVCG camera-ready, covering de-anonymization, the VGTC/TVCG template and journal metadata (DOI, ORCID, IEEE keywords/index terms), integrating the second-round required changes without scope creep, permanentizing open-materials links, the Open Practices disclosure form, and the Graphics Replicability Stamp handoff.
Use when deciding what belongs in an IEEE VIS paper body versus its supplemental materials, covering the VGTC/TVCG 9+2 page budget, the supplemental video that VIS reviewers routinely watch, the one-week supplemental deadline extension, double-blind supplemental anonymization, and how to split a visualization paper between the reviewed pages and the archive.
Use when producing the final PVLDB version of an accepted VLDB paper, covering the volume-specific template, PDF/A compliance and font embedding, figure legibility floors, the availability paragraph and artifact URL, proceedings file naming and copyright steps, and planning presentation at the matching VLDB conference.
Use when running the final pre-submission preflight for World Development (WD) via Elsevier Editorial Manager — double-anonymized formatting, abstract/keyword limits, declarations, data statement, and house style. Final checks; it does not draft content.
Use when building and formatting the citation apparatus for a The Yale Law Journal (YLJ) piece — pinpoint cites, Bluebook form, and source support for every assertion. It governs cite construction; the final editorial cite-check and source-pull is ylj-footnotes-and-cite-check.
MANDATORY for every coding agent (Claude Code, Codex, or any other) — keep this repository's documentation in sync after any change to behavior, configuration, interfaces, events, schema, or features. Use automatically (without being asked) at the end of ANY change-set that adds or alters an env var, event type, hook behavior, session/agent state transition, API route or response shape, DB schema, WebSocket message, MCP tool, CLI command, or user-facing feature — and whenever the user asks to "update the docs / README / wiki / architecture". Knows the full doc surface (README + VN/CN/KO, ARCHITECTURE, root index.html, wiki + i18n, server/client READMEs, docs/*) and which docs each kind of change touches.
Diagnose an existing README against the source-analysis output and produce a structured action list (CUT/RELOCATE/RESTRUCTURE/REWRITE-HEADING/REORDER/ADD-CALLOUT) consumed by readme-edit. Splits its work into 0(a)(i) source-only draft, 0(a)(ii) anchored diagnosis.
Analyze a module's source code to produce a spine candidate, callout list, and API surface inventory for use by readme-draft and readme-analyze-existing.
High-judgment whole-document review for shape, pedagogy, and design-rationale. Catches the catalog-vs-teaching, composition-vs-enumeration, running-domain-vs-ad-hoc failure modes that readme-verify's gates pass on. Runs between draft and verify.