Browse 182,820 skills across 14 categories.
Use when the answer is a picture rather than prose: the user says "show me" or "diagram this" about the current topic. E...
Use when asked to show/diagram: comparison table, data record, metric card, stepper, mockup, numeric chart, interactive...
Show the current topic visually when the user explicitly asks to explain, show, visualize, or walk through it, or when i...
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, ev...
Keep a requested TSV decision trail with reasons, evidence, and results.
Use when long-running work needs an auditable decision and evidence log.
Find the shortest path of links between two notes. Triggers on "path between", "how do X and Y connect", "connection cha...
Use when the answer is a walk through the diff rather than a review report: the user says "walk me through this review",...
Analyze all frontmatter fields used across the vault. Triggers on "frontmatter schema", "metadata fields", "what fields...
Get the content under a specific heading in a note without reading the entire file. Triggers on "extract section", "get...
Get all tasks from the vault with filtering options. Triggers on "all tasks", "task list", "show tasks", "find tasks".
Priority tasks for today — checks live sources (email, calendar) before showing stale CSV data
Use when the user asks for a flattened view of roadmaps and next actions. Returns a dependency-ordered task list with st...
Use when the user asks for a flattened view of roadmaps and next actions. Not for multi-session route planning: use wayf...
Apply Austin Kleon's sharing framework. Trigger on: "what should I share?", "build an audience", "document my creative p...
> "I never trust any feature until I've seen it running with my own eye."
Compose and publish a visual explanation of how something works — captures, diagrams, and prose on one page.
When the user wants to create, optimize, or audit a showcase or gallery page for user-generated content. Also use when t...
Deprecated compatibility entry for Showcase Page construction. This page is now maintained in Pagina; install and use pa...
Runs 2-5 parallel runners against a shared design doc in isolated git worktrees, each independently planning and generat...
Cold-read an artifact with fresh zero-context eyes and cut whatever a stranger cannot follow, answering whether it stand...
指定したプラグインの詳細情報を表示する。「プラグインの詳細」「〇〇プラグインについて教えて」「プラグインの情報」「〇〇の機能は?」「プラグインの中身を見せて」「〇〇プラグインの説明」「プラグインのコマンド一覧」などで起動。コマンド、スキル、...
Use this skill when showing what's new in Kata since the installed version, displaying changelog entries, checking for K...
Drive a headed browser to a specific state in a web app (a feature, flow, screen, or bug repro) and leave the window ope...
Generate comprehensive "Shownotes" summaries from longform articles, papers, transcripts, videos, or audio content. Use...
한국어 모션그래픽 영상(이력서용 쇼릴·홍보 영상·프로필 영상·티저·브랜드 필름·행사 홍보·제품 소개·교육 영상·메이킹 필름)을 콘셉트부터 납품까지 만드는 스킬. 정해 둔 무드나 템플릿을 고르지 않는다. 요청마다 콘셉...
Use when the user wants a video made, edited or finished: a launch or promo video, product demo, explainer, trailer or t...
Pre-execution Solana transaction streaming via Jito ShredStream, Shyft RabbitStream, and Triton Deshred
Load this skill when a feature branch works and its diff against main should shrink before review: duplication it added,...
Evidence-first binary-size optimization for Z80 and ZX Spectrum projects, including mixed ASM/C built with z88dk or SDCC...
実行計画Agent - 戦略を具体的なフェーズ別行動計画に落とし込む
中文网文爽点与打脸桥段设计。当用户要设计打脸、扮猪吃老虎、装13、逆袭、复仇、碾压反派、或抱怨剧情"不够爽/太平淡/读者说没爽点"时使用。产出三段式爽点闭环和打脸四拍,并保证爽点升级不重复。
Shuffle — pick a completely random genre and station
Shuffle repetitive JSON objects safely by validating schema consistency before randomising entries.
PM-posture skill that opens the next 宿場 Shukuba station for a project — the model writes the station for the next untick...
Park an unreached 宿場 Shukuba station and free the slot. Moves the station file into the sibling `shukuba/parked/`, where...
PM-posture skill the PM runs, in a pm session or as the pm agent, after a change unit lands or halts. It reads what the...
Scrum Master-posture skill that closes a reached 宿場 Shukuba station — halts outside a scrum-master session or the scrum-...
舒淇(演员)认知与表达框架(压缩蒸馏):性感与文艺并置、自嘲大嘴、慢热真诚 触发:文艺片、松弛感 等。非替本人编造
Implements graceful shutdown with pre_destruct hooks, handling Ctrl-C signals. Use when services need to flush queues, c...
Shutdown gracefulness analyzer: check if shutdown hooks actually drain, flush, and complete in-flight work. Read-only. T...
Evening task selection ceremony for maker work (discovery: requirements-clarity). Evaluate at requirements-clarity when...
End the workday on purpose — the ten-minute shutdown that closes open loops, stages tomorrow's start, and gives the brai...
Cleanly shut down peer Claude Code session(s). Maps project paths to the actual claude binary PIDs (NOT the hive-mcp chi...
Builds kinetic type on Canvas 2D seen through a rolling shutter, where the frame is cut into horizontal stripes that eac...
【书桌书柜业主必看】书桌高度定多少才不累?抽屉做多了会不会卡腿?悬空书桌到底怎么固定?满墙书架怕压抑怎么办?书柜做矮的还是做高?孩子房间书桌和书柜怎么配?衣柜转角能不能变书桌?家里没有书房书柜放哪?书桌和书柜用什么板材更环保?这里覆盖书桌定...
数字生命卡兹克(前UI/交互设计师→AI自媒体人→虚实传媒CEO→AIFUT大会发起人)的AI科技自媒体创作思维——平实直接、数据碾压、自嘲幽默、硬核输出。 触发词:「数字生命卡兹克视角」「像卡兹克那样写」「AI产品实测」「AI工具测评」「...
Execute structured TDD implementation following task documents. Use when starting, continuing, or resuming implementatio...
Short alias for /subsection-implementation. Implements a single subsection from docs/implementation-plan.md with full au...
Supernal Interface CLI for test generation, contract scanning, story system, and MCP setup. Use when: (1) scanning Next....
Navigate through the original three-world shamanic technology. Deploy when soul retrieval, power animal guidance, or jou...
Get siblings onto one team about aging parents before the crisis does it for them — a structured family meeting with an...
Bilateral SYNERGY/UPSTREAM reconciliation across sibling projects. Use when the user wants to sync sibling SYNERGY/UPSTR...
Sibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审
Sibyl Codex 写作 agent - 使用 Codex (GPT-5) 撰写论文
Sibyl 比较分析者 agent - 对标 SOTA 和同类工作,定位结果贡献
Sibyl 反对者 agent - 挑战主流假设,寻找反面证据和盲点
Sibyl 批评者 agent - 苛刻但公正的学术批评
Sibyl 编辑 agent - 整合论文各章节为完整稿件
Sibyl 实验主义者 agent - 关注可复现性、数据质量和实验设计严谨性
Sibyl 后台实验监督 agent - 持续刷新 GPU 空闲状态、动态派发排队实验、处理运行时间/状态漂移
Sibyl 实验执行 agent - 编写代码并在远程 GPU 上执行实验
Sibyl 终审 agent - NeurIPS/ICML 级别的论文终审
Sibyl pilot 验证决策 agent - 根据小实验结果决定 ADVANCE / REFINE / PIVOT
Sibyl 创新者 agent - 大胆的跨领域创新研究提案生成
Sibyl 跨学科者 agent - 从认知科学、物理、生物等领域引入类比和方法
Sibyl 飞书同步 agent - 将研究数据同步到飞书云空间
Sibyl LaTeX 排版 agent - 将论文转为 NeurIPS LaTeX 格式并编译
Sibyl 文献调研 agent - 使用 arXiv + Web 双源搜索进行系统性文献调研
Sibyl 方法论者 agent - 审查实验方法的内外部效度和可复现性
Sibyl 新颖性检查 agent - 搜索文献验证 idea 是否与已有论文撞车
Sibyl 乐观分析者 agent - 从积极角度分析实验结果
Sibyl 大纲撰写 agent - 生成论文详细大纲
Sibyl 实验规划 agent - 设计严谨可复现的实验方案
Sibyl 实用主义者 agent - 注重工程可行性的研究提案生成
Sibyl 反思 agent - 分析迭代产出,分类问题,生成改进计划
Sibyl 结果辩论综合者 agent - 综合6方结果分析形成统一判断和行动计划
Sibyl 修正主义者 agent - 基于实验结果反思假设,提出修正方向
Sibyl 章节评审 agent - 评审论文特定章节
Sibyl 章节撰写 agent - 撰写论文特定章节
Sibyl 自愈 agent - 后台自动检测修复系统错误,添加回归测试,git commit 留痕
Sibyl 顺序写作 agent - 按章节顺序写作,确保整体行文一致性
Sibyl 服务器端实验 agent - 在远程服务器上使用 Codex/Claude 本地执行实验
Sibyl 怀疑论者 agent - 以最大怀疑态度审视实验结果
Sibyl 战略顾问 agent - 从战略角度分析结果并建议下一步
Sibyl 监督审查 agent - 独立第三方质量审查
Sibyl 监督决策 agent - 分析实验结果决定 PIVOT 还是 PROCEED
Sibyl 综合决策者 agent - 综合多方观点生成最终研究提案
Sibyl 理论研究者 agent - 注重数学基础和理论保证的研究提案
- **Generic arithmetic** extensible across numeric types
SICMUtils/Emmy - Clojure library for symbolic mathematics, automatic differentiation, and classical mechanics. Bridges S...
SICP: Structure and Interpretation of Computer Programs - computational processes, abstraction, and metalinguistic desig...
Embody Sid Caesar - AI persona expert with integrated methodology skills
Set up a side business in the right order — the do-first sequence (separate money, basic terms, simple records) vs. the...
Timing attacks and other side-channel exploitation techniques
機能変更の副作用・意図しない影響を体系的に洗い出す
Side-effect ordering analyzer: map operation chains in request handlers, LLM judges if ordering is safe or an incident w...
Blast-radius predictor for a planned change: combines a static reference scan (which files mention the target's exported...
Active coordinator for building AI-powered side-gigs in 2025. Use when users want to build micro-niche products, validat...
Drafts U.S. venture capital and private equity side letter agreements that supplement a primary agreement without formal...