AI & ML

1999azzar Bundle

Read, triage, create, and update Linear issues, projects, cycles, comments, and team workflow data. Use when the user wants help operating in Linear through MCP or equivalent connected Linear tools.

21st-dev Bundle

Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, and packages with Nia AI. Includes Oracle autonomous research, GitHub live search, dependency analysis, context sharing, and code advisor.

2233admin Bundle

Turn any CLI or MCP server into an Agent Skill. Use when you want to replace an MCP server with a zero-overhead CLI skill, or generate a skill from any command-line tool's --help output.

6551team Bundle

Auto-mirror Twitter/X content to Binance Square, or publish a new Square post directly. Supports text posts, up to 4 images, one video, and #tags. Use for requests like "mirror tweets to Binance Square", "post this image to Square", "publish this video to Square", or "run the Binance Square MCP server".

nagisanzenin Skill

Playbook for building and maintaining omni-platform agent plugins (one repo, native installs on Claude Code, Codex, OpenCode, Hermes, Antigravity, Gemini CLI, and more). Use when creating a plugin meant for more than one platform, porting an existing plugin to a new agentic platform, reviewing a platform-port PR, releasing a multi-platform plugin, or answering how another platform's plugin/skill/hook format works.

redf0x1 Bundle

CamoFox MCP Skill

robert7 Bundle

Use when the RemNote bridge has been started and the user wants to run all live RemNote integration tests for this repository through the canonical agent integration workflow.

naive000 Bundle

直接操作 DeepSeek harness(dsh,web UI 通常跑在本機某個 port,例如 http://127.0.0.1:3080/)透過 browserclaw MCP 瀏覽器,把 coding 子任務、code review、simplify(簡化清理)、翻譯/內容產出,或純研究/調查任務(上網搜尋+整理,不碰 code)分包給 DeepSeek——coding 類任務會在獨立的 git worktree 裡跑,監控進度,並獨立驗收(coding 類另外還要負責 merge)結果。「丟給 DeepSeek 跑」「分包給 DeepSeek」「叫 DeepSeek 去改」「交給 deepseek 整理/查」「outsource this to deepseek」「delegate this to deepseek」「dsh 那邊處理一下」這類說法都會觸發,即使使用者沒提到 worktree、browserclaw 或 dsh 本身。不要用在 Claude Code 自己就該做的任務。

namucoxc Bundle

组织设计交付物生成器 v2.0 — 面向中小企业组织咨询场景的 AI 副驾驶。 通过 2 轮极简对话（仅需 2 个核心输入：经营创利流程 + 行业）采集企业信息，自动产出"三张分工矩阵 + 工作分析表合集 + 组织设计预览"五件套交付物。 10 项核心特性： ① 启动时强制 RAG 关联文件夹的官方分工矩阵案例对齐格式； ② 矩阵拆为三张表（公司级 / 部门级 / 岗位级）； ③ RACI 编码本地化：部门级用「主责/参与/监督」中文，岗位级用 R/A/I 字母； ④ 每行必填「产出表单」列（从"经验治理→流程治理"的物理载体）； ⑤ 按完整创利流程顺序排列（不是按抽象主题）； ⑥ 岗位矩阵增「部门职责权限」承上启下列，确保表 1 表 2 自动一致； ⑦ 内置精品包装/外贸出口/双工厂总部+工厂等子行业模板； ⑧ 三个专项动作（客户产品流程图对接 / 外部资源转内部 / 双工厂协同）； ⑨ 支持增量迭代（v1→v2→v3 版本机制）； ⑩ 七道质量闸（RACI 完整性、A 数过载、KPI 可量化、表间一致、行业适配、产出表单完整、流程顺序对齐）。 v2.0.3 起对话流程从 10 轮简化为 5 轮融合版（默认 12-18 分钟）+ 3 轮极简版（快速通道）。 v2.0.4 起明确为「跨 AI Agent / LLM 通用工具」：原生支持 Claude Code，可移植到 Cursor / Cline / ChatGPT GPTs / 本地 LLM 等，详见 PORTABILITY.md。 v2.0.5 起**输入极简化**：核心输入仅 2 项——「经营创利流程」+「行业」，其他字段（企业简称/规模/战略/架构/岗位/事项/KPI/表单）由 RAG + 行业模板自动推导，咨询师只需一次 review 拍板。对话从 5 轮简化为 2 轮（5-10 分钟）。 触发条件：用户说"做分工矩阵""出工作分析""组织设计交付""部门分工矩阵""岗位分工矩阵""分工手册""部门职责""岗位职责书" 或在组织咨询场景下提到"分工 / 岗位 / 部门"等关键词时使用。 适用场景：中小企业（50~500 人）的组织设计、组织变革、分工梳理、职责归位项目，服务对象为咨询师本人。

myceldigital Bundle

create, audit, and improve high-performance /goal prompts for autonomous coding agents and long-running agent workflows. use when the user asks for a /goal prompt, goal prompt template, codex/claude code/hermes mission prompt, long-running agent prompt, multi-day autonomous execution prompt, marathon agent prompt, repo-specific autonomous task prompt, or wants to transform a vague task into a measurable, risk-bounded, verification-driven execution contract.

nank1ro Skill

Review staged code at agent-commit time with independent Opus or Sol sessions and a fresh cross-provider fallback on usage limits. Covers correctness and simplicity, adjudication, a separate fix worker, one confirmation pass, and staged-content clearance. Human commits and routine bookkeeping are exempt.

nank1ro Bundle

PRIORITY — read this skill FIRST before writing Dart code when `pubspec.yaml` declares `solid_annotations` or `solid_generator`. In these projects Flutter conventions are inverted: `lib/` is build_runner output from `source/`; editing `lib/` is destroyed on next build. Without this skill you WRITE TO THE WRONG DIRECTORY and silently lose work. Use whenever ANY of these appear: `solid_annotations`/`solid_generator` in pubspec; `@SolidState`/`@SolidEffect`/`@SolidQuery`/`@SolidEnvironment`/`.untracked` in the user's message or code; "my lib/ edits keep disappearing"; "add/scaffold a widget/page/route/model/controller" in such a project; reactive patterns (debounce, "when X changes fetch Y", "make reactive"); or installing pub packages (go_router, freezed, riverpod, drift, json_serializable) whose docs say `lib/` — substitute `source/`. Annotation contract (`@SolidQuery` no params, `@SolidEnvironment` needs `late`) is non-obvious. NOT for SolidJS/Solid.js or Flutter projects without those packages.

mycelos-ai Bundle

Run Bumblebee supply-chain inventory and exposure scans on the local machine. Use this skill whenever the user wants to check developer endpoints for compromised npm/PyPI/Go/RubyGems/Composer packages, audit installed editor or browser extensions, inspect MCP host configs, or perform supply-chain incident response on macOS/Linux. Trigger on phrases like "Bumblebee scan", "supply-chain check", "compromised package", "exposure scan", "baseline inventory", "project scan", "deep scan", "scan my machine for vulnerable packages", "check for malicious extensions", or any request involving the bumblebee CLI. Also use when the user names an advisory and wants to know if their machine is affected. The skill handles requirements checks (Go, Bumblebee), installs Bumblebee via `go install` if missing, runs the requested profile, and produces both raw NDJSON and a human-readable Markdown report.

mychaelconnolly Bundle

Use when the user asks to preserve work state for later, including "continuity", "continuity log", "log work", "save state", "continue later", "resume note", "session clearing", "history clearing", "memory clearing", or "save critical context" — or asks to pick work back up from a saved record, including "pull up <project>", "resume <project>", "resume work on <project>", "where were we", "pick up where we left off", or "continue <project>". Create concise project-local continuity records so a future agent session can resume accurately, and resume from them on request.

myersguo Bundle

Maintain a persistent, compounding LLM-maintained markdown wiki for daily AI conversations and sources. Use when the user asks to 沉淀/记录/归档/整理 AI 对话、更新或查询 llm_wiki、ingest a source into the wiki, file an answer back into the knowledge base, run wiki lint/health checks, or apply Karpathy's LLM Wiki pattern to personal/team/research notes.

nanmicoder Skill

通过 TodoCue CLI 管理本机持久化待办、今日计划、截止日期、提醒、多图片/文件附件和每日/每周重复任务。用户提到 TodoCue，或已经选择用 TodoCue 记录和管理个人任务时使用；Agent 自己的临时执行步骤不自动写入个人待办。

nanzhipro Bundle

Bootstrap and operate an LLM Wiki: a persistent Markdown knowledge base with immutable raw sources, an LLM-maintained wiki, a SCHEMA.md operating contract, thin runtime pointer files, EXTEND.md preferences, and optional local BM25 search. Use when the user asks to create or bootstrap an LLM wiki, ingest sources, query or lint a wiki, configure EXTEND.md preferences, or set up BM25/full-text search for an LLM Wiki.

mykaro Skill

Idiomatic guide for Flet 1.0 applications. Covers declarative UI, hooks, observable state, services, async execution model, and breaking API changes from v0.x. Use this skill to write modern Flet code, migrate imperative apps to reactive patterns, apply breaking changes correctly, and avoid common pitfalls.

nanzhipro Bundle

Set up a Phase-Contract long-running workflow that drives an AI agent to work continuously for 5+ hours on a single project. Use when the user wants to plan a large migration, new product build, big refactor, long-form writing project, compliance remediation, or any multi-phase task that exceeds a single context window. Triggers: '让 AI 连续工作', '长任务规划', '分阶段执行', 'phase 规划', 'plan 规划', '多阶段迁移', '大型重构规划', 'long-running AI workflow', 'phase-contract', 'planctl', 'manifest + execution 双文档', '拆 phase', '规划压缩恢复', '给 AI 写 plan', '项目分阶段', '续跑规划', '合同链规划', '长任务续跑工作流'. Scaffolds plan/manifest.yaml, plan/common.md, plan/phases/, plan/execution/, a planctl scheduler script, plus an AGENTS.md agent instruction file (with CLAUDE.md symlinked to it) so phase state is externalized and AI work can survive context compression across agents.

nanzhipro Bundle

Set up a disk-backed Phase-Fiction workflow for long-form fiction projects. Use when the user wants to plan, continue, or revise a novel, novella, serial fiction project, multi-book arc, story bible, scene matrix, or full-manuscript rewrite across many sessions. Triggers: '写小说', '长篇小说规划', '续写长篇', '分阶段写小说', '故事 bible', '人物弧光规划', '章节矩阵', '修订轮次', 'serial fiction workflow', 'novel planning', 'story phase', 'scene matrix', 'revision pass', 'manuscript recovery', 'phase-fiction'. Scaffolds plan/manifest.yaml, plan/common.md, phase and execution contracts, a planctl scheduler script, synchronized agent instruction files, and a final story/README.md index after creation completes.

mystenlabs Bundle

Walrus Memory SDK — portable agent memory that works across apps, sessions, and workflows. Use when users say: - "add memory to my app" - "portable agent memory" - "integrate Walrus Memory" - "AI agent memory" - "memory across agents" - "Walrus memory storage" - "setup Walrus Memory" - "recall memories"

mystenlabs Bundle

Answer questions about the Walrus Training Program course content. Uses multi-agent search and AskUserQuestion for question refinement. Provides citations for all claims. Only uses course content as source. Use when: user asks about Walrus concepts, CLI, SDK, architecture, storage, epochs, quilts, performance, failure handling, or any topic covered in the 14-module training program.

mysticaltech Bundle

Compile plain-language work into concise, host-aware, verifiable agent goals. Use when drafting, rewriting, tightening, auditing, or deciding whether to use a /goal-style contract for Codex, Claude Code, Cursor, OpenClaw, GitHub Copilot, orchestrators, CI agents, background workers, coding agents, review agents, research agents, migrations, debugging, refactors, audits, long-running tasks, or any multi-step work that needs explicit done criteria, proof, stop policy, anti-gaming constraints, review depth, and a completion receipt.

mz038197 Bundle

Clone python-cli-project from GitHub, customize it with user parameters, remove git remotes, and validate that all tests pass. Use this when an agent needs to create a new customized Python CLI project based on the template.

n-shadloo Bundle

Authors and executes git work end to end — Conventional Commits messages, pull-request content, release notes, and pull-request review, plus the repository operations an engineer runs daily: branching, rebasing, squashing, cherry-picking, reverting, merge-conflict resolution, stashes, tags, remotes, and recovery through the reflog. Use whenever the user is about to commit, asks for a commit message, exact commands, or file selection, mentions staged changes, asks for a pull-request title or description, a release note or a changelog entry, asks the agent to stage, commit, and push, asks for help reviewing, approving, rejecting, or merging someone else's pull request, and whenever the user asks how to branch, rebase, squash, split, revert, cherry-pick, resolve a conflict, undo or amend a commit, move work between branches, recover lost commits, or clean up history before review. Adds co-author, sign-off, or AI or agent attribution only when the user asks for it in the session, and never by default.

nataliapc Bundle

Control and automate the openMSX emulator for MSX / MSX2 retro development. Covers Z80 and R800 assembly debugging, Z80 CPU inspection, VDP (V9938/V9958) programming, PSG sound, MSX-BASIC development, ROM/disk/tape media management, screen capture, breakpoints, memory inspection, and SDCC C development workflows. Use when direct openMSX emulator interaction is required or MSX technical information is needed.

nataliapc Bundle

Technical reference for the DAAD (Disenador de Aventuras AD) text adventure authoring system. Use when working with DAAD interpreters, compilers, game databases, or adventure source code. Covers: DDB binary file format, all 128 condacts, system flags (0-63), object model, DSF source format, DRC compiler, MALUVA extensions, engine architecture (parser, process tables, game loop, indirection, windows, save/load). Use for: (1) implementing or modifying a DAAD interpreter, (2) writing or debugging DAAD adventures in DSF, (3) understanding DDB binary layout, (4) looking up condact behavior or system flag semantics, (5) working with DRC compiler or MALUVA extensions.

natebjones-projects Skill

Orchestrator playbook and routing rules for Ringer, the verified-swarm delegation tool (ringer.py). TRIGGER — load BEFORE acting, not after — whenever: you are about to run ANY script or command that calls a model or drives a conversational/eval harness (probe, smoke test, simulation, grader, persona conversation) outside a live Ringer run; you are about to start an edit→test→edit loop or a batch of similar edits across files; you are about to do a "quick check" that spawns a model or a CLI agent; you are reviewing or diagnosing failed worker or model output; you catch yourself thinking a task is "small enough to just do myself" — that thought IS the trigger (a single task is a one-task manifest, and a bounded read-only question is `ringer.py ask`); or you are writing or reviewing a manifest, choosing a swarm pattern (review swarm, fix swarm, focus group, bakeoff, research-with-proof), picking a worker engine, or debugging a failed run. SKIP only for: reading or searching files, git operations, a one-file few

nattergabriel Skill

How to use reseed to manage agent skills in a project. Use when the user mentions reseed, agent skills, SKILL.md, .agents/skills/, or .claude/skills/, or wants to install, add, remove, sync, or list skills.

nemovideo Bundle

AI video creation and editing — generate videos from text descriptions, edit with background music, sound effects, titles, transitions, and export finished MP4 videos directly in chat. No GUI needed. Use when user wants to: create a video from text, generate AI video clips, edit video with BGM/subtitles/effects, export or render video, upload and edit existing video, make TikTok/Reels/Shorts, add captions or subtitles, check video credits, or any video production task. Supports mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac. Free trial with 100 credits. 关键词：AI视频制作、视频剪辑、文字生成视频、短视频制作、视频导出、添加字幕、添加背景音乐。

neoli00 Skill

Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.

nerdstalker Bundle

Advise on and critique UI/UX design work through the lens of Luke Wroblewski's published principles, using his MCP archive to retrieve relevant writings, presentations, videos, and other source material for each task. Use this skill whenever the user asks for a design review, UX critique, or feedback on a screen, page, form, sign-up flow, checkout, mobile layout, navigation scheme, or AI/agent interface — or asks "what would LukeW say," mentions Luke Wroblewski, or wants design advice grounded in established best practices rather than taste. Also use it when the user asks to fix or improve a UI and wants the changes justified by recognized principles.

nerveband Bundle

Manage Craft.do documents, blocks, folders, tasks, collections, whiteboards, comments, uploads, search, REST profiles, and Craft MCP connections from a JSON-first CLI.

nativ3ai Bundle

Transcribe a video/audio URL into timestamped JSON using yt-dlp + ffmpeg + faster-whisper. Use when an agent needs platform-agnostic URL-to-transcript ingestion for downstream analysis.

natllian Skill

Multi-agent collaboration powered by OpenClaw cron jobs and the clawion CLI.

ndisisnd Bundle

Rewrite, improve, or enhance a prompt. Runs on /wdym, on any request to improve/enhance/rewrite a prompt, and on a UserPromptSubmit <prompt-detect> block. Detects prompt type (code, question, text-gen) and rewrites using 2–3 matched principles; flash mode rewrites immediately, comprehensive mode presents the rewrite and waits for approval. Manage with /wdym --init, --status, --set-mode, --help.