Converges a chosen game concept into a single GAME_DESIGN.md covering player promise, core loop, level pacing, feedback, and a playable prototype slice.
An editorial leader's playbook for splitting work between humans and AI: participation boundaries, hybrid workflow patterns, voice preservation, slop prevention, and disclosure policy.
A music-planning skill that designs album concepts, tracklists and narrative arcs through 7 structured question phases and documents the result in an album README.
Captures and tracks album concepts in an IDEAS.md backlog with pending / in-progress / complete status flow.
Turns a short-drama script into reusable character, location, and prop definitions plus per-episode state changes in a single visual-setup document.
A Russian-language copy-editing skill that fixes only the formulaic, machine-sounding parts of a text while preserving its meaning and authorial voice.
A surgical editing skill that strips formulaic, machine-sounding patterns from Russian prose while preserving meaning, hedging and authorial voice.
A three-phase Russian-language editor that strips AI tells, bureaucratic filler, and fluff while restoring a human voice.
Scores any text across nine AI-tell signal categories and returns a structured report with quoted evidence and concrete fixes.
A second-pass editing skill that removes discourse-level AI tells — stated lessons, tidy single-track arcs, embodied emotion, vague allusions — that survive word-level humanizing.
Turns a novel bible and product brief into a compared set of game directions, then locks one playable concept using hard vetoes and explicit trade-offs in a single CONCEPT.md.
Builds a complete LaTeX/PDF literature survey on a research topic with 60+ verified citations, 6–10 topic-specific figures, and a classified literature table.
A craft rubric for writing and reviewing news, explainers, and issue analyses using the inverted pyramid, Toulmin argument, dialectical structure, and BBC due impartiality.
A craft skill for writing and reviewing the instruction layer itself — CLAUDE.md, .claude guides, policies and plan files — with operative rules, force tiers and bloat control.
Applies McKinsey SCR, Minto/MECE and BCG bold-bullet techniques to write and review executive summaries and roll-up overviews.
Generates and audits accessible alt text for figures in R package (pkgdown) sites and Quarto documents by reading the plotting code and surrounding prose.
A persona framework that has Claude read SOUL.md, STYLE.md and curated examples so it writes and argues exactly like a specific person.
Scores academic papers for AI-generated writing across five dimensions, then produces a detection report, a format-preserving rewritten .docx, or a full thesis draft.
A persona skill that makes Claude think and write in the mental models and voice of Wang Jianshuo, China's long-running blogger and founder of Baixing/Baixing AI.
Turns upstream ideation, plan and experiment artifacts into a complete LaTeX paper draft with figures, tables and a compiled PDF.