543 skills · sorted by relevance
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Find the relevant guidance for writing Remotion animations that agents can understand and that remain editable in Studio’s Visual Mode. It points to resources for scene structure, editable styles and animations, and interactive custom components.
Coordinates a mathematical modeling competition project from planning to final checks. It records formatting and language preferences, creates a plan and task checklist, and calls dedicated skills for modeling, coding, diagrams, paper writing, and verification.
Coordinate AI-style writing reviews, voice-preserving rewrites, file edits, and before-and-after checks. Route each request to the appropriate related skill, carry context between stages, and report which checks ran and whether the original meaning was preserved.
Review English prose for formulaic phrases and other patterns associated with AI writing, then make targeted edits while preserving meaning and voice. Choose findings only, a rewritten version, or direct edits to a prose file.
Build and evaluate Bayesian models with PyMC and ArviZ, from choosing initial assumptions to checking predictions. The workflow covers sampling diagnostics, model comparison, and reports that explain results with uncertainty intervals.
Audit writing for repetitive phrases, vague praise, excessive formatting, and other patterns associated with AI text. Get a revised version with reasons for changes, or use detection mode to review flagged passages without altering the original.
Coordinate multiple agents to maintain context-mode, from sorting GitHub issues and reviewing pull requests to preparing releases and announcements. Workflows require reproduced bugs, source evidence, test-first changes, and checks across supported platforms.
World-class copywriting expertise combining the persuasive clarity of David Ogilvy, the conversational warmth of Ann Handley, and the conversion science of modern growth marketers. Copywriting is where brand voice becomes words that move people. Great copy doesn't just communicate—it persuades, connects, and converts. The best copywriters understand that every word earns its place, that benefits beat features, that clarity trumps cleverness, and that the reader's problem is the only starting point that matters. Use when "copywriting, write copy, headlines, taglines, email copy, ad copy, landing page copy, product copy, UX writing, CTAs, value proposition, microcopy, sales copy, conversion copy, writing, copy, headlines, conversion, persuasion, messaging, UX-writing, emails" mentioned.
The English summary is being prepared. Showing the original description.
Writing mode operational spec for the team lead. Returns lead identity, facilitator identity, ownership boundaries, editorial baseline, suggest-members guidance, and phase arc for writing-mode teams.
The English summary is being prepared. Showing the original description.
Define custom entities and relationships in cognee, a memory system for AI applications. This skill guides model design, identity matching, searchable fields, and troubleshooting when entities are duplicated or relationships are missing.
Apply over 240 reusable prompt templates to summarize content, extract insights, improve writing, review code, or analyze security threats. It reads each template directly and returns results in the format defined for that task.
Turn ePub books into training examples for models that reproduce an author's writing style. Covers text extraction, coherent segmentation, varied instructions, model training, and checks for copied phrases and style transfer to new scenarios.
Apply a specific set of Rails conventions to design, implementation, and code review. It keeps business logic in models, represents state changes as records, limits dependencies, and uses Minitest with fixtures, or predefined test data.
Chinese opera playwriting for the qupai (曲牌体) system — 元杂剧, 明清传奇, 昆曲, 川剧高腔, where sung text is filled into fixed tune patterns (填词) rather than built from paired lines varied by metre. Covers stage vs study (李渔 vs 吴梅/王季烈), the 清曲/剧曲 switch, the zaju branch (四折一楔子, one 宫调 and one rhyme per act, 一人主唱, 题目正名), the chuanqi branch (出, 副末开场, 南北合套, 集唐下场诗), tune-filling (格律, 前腔/换头/幺, 衬字, 务头, 尾声, 四十禁), the seventeen 宫调 and their affects, 套数, 排场 alternation, the spoken-to-sung cue, 帮腔, adaptation, and modern practice. From 李渔《闲情偶寄》, 吴梅《顾曲麈谈》《曲学通论》, 王季烈《螾庐曲谈》, 孔尚任's 凡例, 关汉卿, 汤显祖, 魏明伦. Use when writing or revising a 曲牌体 script, choosing a 宫调 for an emotion, laying out a 套数, filling one tune pattern, writing a zaju act or a chuanqi scene, cutting an old 传奇 into a playable version, writing a modern qupai opera, or judging whether a famous script's prosody may be copied. Not for 京剧/豫剧/越剧, which are the banqiang system; see sw-chinese-opera-banqiang.
The English summary is being prepared. Showing the original description.
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML). DIRECT-EDIT mode (common): the user describes a change in Chinese or English and the manuscript (LaTeX or Markdown) is edited directly through a CS-venue writing toolkit with author sign-off (use for 改这段 / 把中文想法写成 latex / polish / de-AI / translate / compress a passage). REVIEW mode (occasional, pre-submission): harden the paper through an adversarial courtroom review engine (N holistic domain reviewers / contestability routing / two-sided trial / three-way verdict / clerk-converged multi-round loop) with consensus-gated, author-signed revisions (use for review / critique / 审稿 / 评审 / mock-review). AUTO mode (unattended, opt-in via /goal): run the review-revise loop toward a verifiable goal, applying safe fixes under a drift-bounded policy and queueing risky ones. Resolves all inputs at runtime, no hardcoded paths. Not a from-scratch drafter (use ml-paper-writing) and not an official-venue rebuttal.
The English summary is being prepared. Showing the original description.
Query Microsoft Fabric and Power BI semantic models with DAX (and Fabric SQL endpoints with T-SQL) to feed a Claude Dashboard or any dashboard built from a Fabric connector or MCP server. Use this skill whenever you build, extend or debug a dashboard, KPI card, chart or table on top of a semantic model, call a tool like run_dax_query, get_model_schema or list_models, or the user asks for numbers "from Fabric", "from the model" or "from Power BI", even if they never say DAX. Covers reusing the model's measures instead of writing new ones, KPI design with a target and a trend, crossfiltering between visuals, DAX query syntax and time intelligence, and an execute-inspect-fix test loop.
The English summary is being prepared. Showing the original description.
CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling, solving, robustness, writing, compliance, and final submission review. Provides 10 stages, persistent decision state, competition-specific rules/templates, deterministic scoring helpers, numbered decisions, and Codex/Claude Code handoff. Do not trigger for generic model selection, ordinary data analysis, or non-competition paper review.
The English summary is being prepared. Showing the original description.
Use when EZ_math_model model selection is unclear after the modeling decision tree, the problem spans multiple domains, or modeler needs several candidate approaches before writing modeling_plan.md.
The English summary is being prepared. Showing the original description.
Review prose for repetitive wording, inflated language, and overly regular structure. Get an issues-only audit, a rewritten version, or targeted file edits that preserve the author's voice, existing facts, and protected quoted material.
Write or modernize C++ with guidance on C++20, C++23, and C++26 features. Review memory ownership, error handling, and template constraints, with recommendations for compiler protections and runtime checks that detect bugs.
Turn an interview about work experiences, numbers, turning points, and opinions into a reusable bank of LinkedIn post material. A focused mode develops one topic into a structured outline for a separate writing skill.
Japanese (and other non-Hollywood) screenwriting methods (日本编剧方法/原创剧本实战) — distilled from ten Japanese directors and writers in ゼロからの脚本術; Kosawa Ryota (three acts as 起承转合, speed by jumping), Uchida Kenji (beautiful structure, time-axis tricks), Miki Satoshi (small-material notebook, theme emerges later), Sono Sion, Omiya Ellie (dialogue from inner monologue), Kakei Masaya ("if + moreover"), Fukuda Yuichi (character = actor + flaw, audience as tsukkomi), Yokohama Satoko, Takahashi Izumi ("pain"), Yukisada Isao (situation-born originals); plus Arai Haruhiko (IP adaptation, "write what you're ashamed of"). Neighbours; sw-korean-french-screenwriting, ozu-screenplay-style. Use when writing an original Japanese-style script or TV drama, working from small material and fragments, choosing between structure-first and character-first methods, building a Japanese 企画書, designing comedy tsukkomi systems, or when Hollywood models feel wrong for a quiet, daily-life, non-goal-driven story.
The English summary is being prepared. Showing the original description.