AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Compose

  by @sharpdeveye

  Use when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.

• Capture

  by @sharpdeveye

  Capture a session summary — what was done, what decisions were made, and what to do next.

• Reflect

  by @sharpdeveye

  Analyze command history to identify which skills work, which fail, and where to improve.

• Recap

  by @sharpdeveye

  Quick summary of the last session — commands run, files changed, and what to do next.

• Elasticsearch Onboarding

  by @elastic

  Help developers new to Elasticsearch get from zero to a working search experience. Guide them through understanding their intent, mapping their data, and building a search experience with best practices baked in. Use this when…

• Skill Router

  by @stevesolun

  Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work…

• Caveman Compress

  by @stevesolun

  Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file.…

• Setup Matt Pocock Skills

  by @stevesolun

  Configure repository-local tracker, triage, and domain-document conventions needed by the Matt Pocock engineering skills.

• Teach

  by @stevesolun

  Teach a skill or concept at the user's current level, optionally preserving a lightweight multi-session learning record.

• Diagnosing Bugs

  by @stevesolun

  Diagnose hard bugs and performance regressions with reproducible evidence, focused hypotheses, and proportional instrumentation. Use when something is broken, failing, throwing, intermittently wrong, or unexpectedly slow.

• Codebase Design

  by @stevesolun

  Design or improve module interfaces using deep-module heuristics. Use when deciding where a seam belongs, reducing caller-facing complexity, improving testability or navigability, or comparing module designs.

• Domain Modeling

  by @stevesolun

  Clarify domain concepts, language, boundaries, and durable architectural decisions. Use when terminology is ambiguous, the user is shaping a domain model, or a design depends on resolving what concepts mean.

• Triage

  by @stevesolun

  Classify and advance issues or external pull requests through the configured triage workflow. Use explicitly to inspect queues, evaluate an item, recommend a state, or apply an authorized transition.

• Tdd

  by @stevesolun

  Apply test-driven development with small, behavior-focused feedback loops. Use when the user asks to build or fix something test-first, mentions red-green-refactor, or wants integration tests.

• Wayfinder

  by @stevesolun

  Map a large, unclear, multi-session effort as linked decisions, then advance the map until the route to the destination is clear.

• Prototype

  by @stevesolun

  Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from…

• Improve Codebase Architecture

  by @stevesolun

  Analyze a codebase for high-leverage architectural improvements and explain evidence, tradeoffs, and next steps. Use explicitly for architecture audits or deep-module refactoring opportunities.

• Code Review

  by @stevesolun

  Review a Git diff against repository standards and its originating requirements. Use for pull requests, branches, work-in-progress changes, or changes since a commit, tag, or merge-base.

• To Tickets

  by @stevesolun

  Break a plan, spec, or conversation into dependency-aware, independently verifiable tickets. Use explicitly when the user wants work sliced for local planning or an issue tracker.

• To Spec

  by @stevesolun

  Synthesize an implementation-ready spec from the current conversation and relevant repository context. Use explicitly when the user wants agreed work captured as a spec or PRD.

• Writing Great Skills

  by @stevesolun

  Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

• Ask Matt

  by @stevesolun

  Recommend the smallest Matt Pocock skill or short skill sequence that fits the user's current goal.

• Research

  by @stevesolun

  Investigate questions using high-trust primary sources and traceable citations. Use when the user asks for research, current documentation or API facts, source verification, or evidence-backed comparison.

• Resolving Merge Conflicts

  by @stevesolun

  Resolve an in-progress Git merge or rebase conflict while preserving the relevant intent of both sides. Use when conflict markers or an interrupted merge/rebase need investigation and resolution.

• Implement

  by @stevesolun

  Implement work from a spec, ticket, or agreed conversation. Use explicitly when the user wants an existing plan carried through to working code.

• Caveman

  by @stevesolun

  Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when…

• Writing Shape

  by @stevesolun

  Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes)…

• Writing Beats

  by @stevesolun

  Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article…

• Writing Fragments

  by @stevesolun

  Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the…

• Caveman Commit

  by @stevesolun

  Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a…

• Ctx Verify

  by @stevesolun

  Select proportional validation for changes or reviews in the ctx repository. Use before handing off material code, workflow, migration, documentation, security, packaging, or release changes; before a PR; or when asked whether a…

• Ubiquitous Language

  by @stevesolun

  Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary,…

• Caveman Review

  by @stevesolun

  Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff",…

• Repo Stats Autoupdate

  by @stevesolun

  Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when…

• Agents Md Protocol

  by @stevesolun

  Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a…

• Ctx Dispatch

  by @stevesolun

  Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes; compute-heavy checks; or repetitive changes suited to scripts or codemods. Use for decomposition and…

• Find Skills

  by @stevesolun

  Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add/update a skill, or needs a repeatable procedure…

• No Mistakes

  by @stevesolun

  Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a…

• Lat Md Knowledge Graph

  by @stevesolun

  Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections. Use when AGENTS.md/CLAUDE.md is too flat for a large codebase or when a custom harness needs…

• Caveman Stats

  by @stevesolun

  Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself…

• Caveman Help

  by @stevesolun

  Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

• Zoom Out

  by @stevesolun

  Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

• Edit Article

  by @stevesolun

  Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

• To Prd

  by @stevesolun

  Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

• Obsidian Vault

  by @stevesolun

  Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

• Write A Skill

  by @stevesolun

  Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

• React Aria

  by @NextAdminHQ

  Build accessible UI components with React Aria Components. Use when developers mention React Aria, react-aria-components, accessible components, or need unstyled accessible primitives. Provides documentation for building custom…

• Homepage Generator

  by @wanshuiyin

  Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. Produces editable structured source files (profile.yml + publications.bib + bio.md +…

• Story Setup

  by @uu201

  网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md 等基础设施部署到用户项目目录。 触发方式：/story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」

• Story Long Write

  by @uu201

  长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。 触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」

• Story Short Write

  by @uu201

  短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。 触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」

• Story Short Analyze

  by @uu201

  短篇网文拆文。拆解爆款短篇小说（番茄短篇 / 故事会 / 知乎盐选 / 追妻 / 世情 / 重生 / 虐渣等通俗题材）的故事核、结构、情感线、反转设计、写作手法、共鸣层次。 单一全量拆解管道：跑完 Stage 2-6 产出完整拆文报告，落盘到 `拆文库/{书名}/`， 下游 `story-short-write` 同时读拆文报告 + 情节节点 + 写作手法 + 原文 + _meta.json 写下一篇。…

• Novel Genres

  by @uu201

  网文题材与子类融合引擎。当用户需要选择题材、分析流派、设计混合类型、了解某题材的市场表现与写作模板时触发。覆盖玄幻、仙侠、武侠、都市、言情、历史、军事、科幻、悬疑灵异、游戏电竞、奇幻、轻小说、同人、无限流快穿、末日废土、种田基建、灵气复苏、系统流、重生穿越等全部主流与新兴题材。

• Modal

  by @jimmc414

  Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or…

• Story Review

  by @uu201

  多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。 触发方式：/story-review、/审查、「审查一下」「帮我审一下」

• Story Long Scan

  by @uu201

  长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。 触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」

• Novel Pleasure Points

  by @uu201

  网文爽点模式大全与疲劳管理。当用户需要设计爽感、打脸桥段、逆袭高潮、金手指设定、装逼场景，或需要分析爽点心理机制、控制爽点密度、防止读者审美疲劳时触发。覆盖60+种爽点模式及其结构模板。

• Novel Commercialization

  by @uu201

  网文商业化与平台特化。当用户需要选择发布平台、了解平台风格、设计变现模式、规划签约策略时触发。覆盖起点/番茄/飞卢/晋江/七猫/新媒体文等平台详细对比，以及付费vs免费、IP改编等商业化设计。

• Story Long Analyze

  by @uu201

  长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。 单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解， 确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 `拆文库/{书名}/`。 触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」…

• Story Import

  by @uu201

  逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构， 兼容 story-long-write / story-short-write 后续写作流程。内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。 触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」

• Novel Language Style

  by @uu201

  网文语言与文风光谱。当用户需要调整文风、选择叙述视角、运用修辞技法、植入玩梗、增强画面感时触发。覆盖白描/华丽/口语化/文艺/中二/翻译腔/新媒体风等文风类型，以及特写/慢镜头/蒙太奇/空镜头/长镜头等画面感技术。

• Novel Character Design

  by @uu201

  网文人设与群像工程。当用户需要设计主角性格、塑造配角功能、构建反派魅力、设计人物关系、规划人物弧光时触发。覆盖60+主角性格标签、30+配角功能模型、20+反派塑造模板，以及人物关系范式与弧光设计方法。

• Novel Pacing

  by @uu201

  网文节奏与结构工程。当用户需要设计开篇、规划章节结构、编排高潮、设置断章钩子、控制字数节奏时触发。覆盖黄金三章/黄金一章模板、30+种断章钩子技法、多幕式结构、高潮编排与密度控制。

• Geniml

  by @jimmc414

  This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus…

• Deepchem

  by @jimmc414

  Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

• Novel Tools

  by @uu201

  网文创作工具与生产流程。当用户需要使用AI辅助写作工具、设计提示词模板、规划写作工作流、选择码字工具、制定发布与数据分析策略时触发。覆盖DeepSeek/ChatGPT/Claude/豆包等AI工具应用、提示词工程、工作流设计、发布运营。

• Novel Anti Detection

  by @uu201

  网文反AI检测与风控。当用户需要了解AIGC检测原理、降低AI文本被识别率、了解平台AI检测政策、设计混合创作模式时触发。覆盖检测技术原理、绕过策略、平台政策、混合创作模式（AI+人工改写双盲测试仅29%识别率）。

• Novel Emotion

  by @uu201

  网文情绪与代入感设计。当用户需要设计情绪曲线、增强代入感、触发共情、管理读者期待、营造沉浸感时触发。覆盖情绪色彩轮盘、20+共情触发器、期待感管理、先抑后扬阶梯式情绪曲线、感官细节沉浸技术。

• Novel Innovation

  by @uu201

  网文创新、反套路与融合引擎。当用户需要创新写法、设计反套路、融合多种题材、植入热梗、规避AI写作陷阱时触发。覆盖类型融合相容性矩阵、30+反套路设计、2026网文趋势、AI辅助写作常见陷阱。

• Novel Polishing

  by @uu201

  网文润色与去AI味。当用户需要润色AI生成的文本、去除AIGC痕迹、改写机械句式、增加口语化表达、注入个人风格时触发。覆盖去AI化核心策略、润色指令模板、风格增强技术、前后对比案例。

• Novel Compliance

  by @uu201

  网文敏感词规避与合规。当用户需要了解平台审核规则、规避敏感词、确保内容合规、了解违规判定标准时触发。覆盖各平台审核规则、敏感词库、违规内容判定、章节审核流程、2026年法规要求。

• Novel Worldbuilding

  by @uu201

  网文世界观与设定体系。当用户需要构建力量体系、设计地图与势力格局、建立经济体系、维护设定一致性、铺设悬念与谜题时触发。覆盖修仙/玄幻/科幻/都市等各类世界观模板与设定管理方法。

• Esm

  by @jimmc414

  Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when…

• Story Short Scan

  by @uu201

  短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。 触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」

• Story Deslop

  by @uu201

  网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。 触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」

• Cellxgene Census

  by @jimmc414

  Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis.

• Hypogenic

  by @jimmc414

  Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against…

• Story Cover

  by @uu201

  小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 直接生成含标题和署名的专业级网文封面。 触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」

• Humanizer Zh

  by @uu201

  中文小说AI内容人性化润色系统v2.0。专为网文/小说场景设计的去AI味工具， 包含23条禁止模式、148条短语替换、105条词汇替换、19条口语化替换， 以及完整的格式规范化规则（引号/省略号/数字）。

• Style Fingerprint

  by @uu201

  作者风格指纹提取。从小说样本文本（3-10万字）中提取可复现500+章节的量化风格DNA， 覆盖叙事架构、语言签名、对话系统、描写协议、禁忌模式和主题执行六大维度。

• Style Fusion

  by @uu201

  风格迁移融合创作指南生成。将作者风格指纹精确映射到新作品， 生成可执行500+章的融合创作规则集+初始故事状态机（人物/伏笔/关系/细纲）。

• Story

  by @uu201

  网络小说工具箱主入口。根据用户需求自动路由到对应 skill。 触发方式：/story、/网文、「我想写小说」「帮我写书」「写网文」 当用户意图不明确时触发此 skill，由路由逻辑分发到具体的扫榜/拆文/写作/去AI味/封面 skill。

• Shopify Functions

  by @Shopify

  Shopify Functions allow developers to customize the backend logic that powers parts of Shopify. Available APIs: Discount, Cart and Checkout Validation, Cart Transform, Pickup Point Delivery Option Generator, Delivery…

• Ui Aesthetics

  by @pdsuwwz

  Raise frontend visual judgment for web interfaces with a bias toward refined product-grade composition, precise component craftsmanship, disciplined interaction states, controlled motion, and coherent depth systems. Use when…

• Chatbot Mvp Distillation

  by @pdsuwwz

  Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories. Use when designing or implementing streaming chatbot UIs, SSE/fetch response pipelines,…

• Chatbot Mvp Distillation Zh

  by @pdsuwwz

  将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品，包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示，以及从本 Vue 3 MVP 迁移到其他项目的方案规划。

• Uncodixfy

  by @pdsuwwz

  Prevents generic AI/Codex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear,…

• Awesome Jev

  by @AbdelStark

  Discover and compare Jev and TypeSafe SDKs, integrations, applications, and evaluations. Use when selecting public resources for a typed-decision workflow or checking what evidence exists for a Jev claim.

• Memory

  by @memvid

  Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file

• Mind

  by @memvid

  Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file

• Uloop Pause Point

  by @hatayama

  Breakpoint-like: pause Unity at a source file:line without editing code or recompiling, and get the locals, parameters, and fields there. Use to check values or confirm a code path ran.

• Uloop Hot Reload

  by @hatayama

  Apply C# edits to the running Editor without a compile or domain reload, keeping Play Mode state. Use instead of compile after editing method bodies or adding methods, fields, or new classes.

• Uloop Execute Dynamic Code

  by @hatayama

  Execute C# with Unity APIs when existing uloop tools cannot inspect or edit enough. Use for reachable scene/component state, scene/prefab/menu automation, and PlayMode checks

• Uloop Run Tests

  by @hatayama

  Run Unity Test Runner and report detailed results. Use for EditMode/PlayMode tests, change verification, or failure diagnosis.

• V3 Cli Invocation Migration

  by @hatayama

  Migrate only uloop V2 CLI option syntax in agent skills, Markdown, POSIX shell scripts, and PowerShell scripts to V3 syntax. Use when updating first-party or third-party uloop command examples that contain V2-style boolean…

• Uloop Simulate Keyboard

  by @hatayama

  Simulate keyboard input in PlayMode through Unity Input System. Use for key presses, holds (via Press --duration or KeyDown/KeyUp), releases, and game controls such as WASD or Space. Requires the Input System package…

• Uloop Simulate Mouse Input

  by @hatayama

  Simulate mouse clicks, long-press, movement, and scroll in PlayMode through the Input System. Use for gameplay mouse input; --dry-run checks what a Game View point hits. Use simulate-mouse-ui for UI.

• Uloop Control Play Mode

  by @hatayama

  Control Unity Editor Play Mode. Use to Play (or Resume, its alias), Stop, Pause, or Step Play Mode, or query Status without side effects, for runtime behavior checks and frame inspection.

• Uloop Screenshot

  by @hatayama

  Capture Unity Editor windows or Game View rendering as PNG. Use for visual checks, debugging, documentation, or annotated UI element coordinates.

• Uloop Simulate Mouse Ui

  by @hatayama

  Simulate PlayMode EventSystem UI mouse actions using screen coordinates. Use for UI clicks, long-presses, or drags from annotated screenshots.