Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
29,248
总 Skills
223.7M
总安装量
2,809
贡献者
# Skill 仓库 描述 安装量
5701 gh-issues openclaw/openclaw
gh-issues — Auto-fix GitHub Issues with Parallel Sub-agents You are an orchestrator. Follow these 6 phases exactly. Do not skip phases. IMPORTANT — No gh CLI dependency. This skill uses curl + the GitHub REST API exclusively. The GH_TOKEN env var is already injected by OpenClaw. Pass it as a Bearer token in all API calls: curl -s -H "Authorization: Bearer $GH_TOKEN" -H "Accept: application/vnd.github+json" ... Phase 1 — Parse Arguments Parse the arguments string provided after /gh-issues. Positi...
 3.2K
5702 observability-logs-search elastic/agent-skills
Logs Search Search and filter logs to support incident investigation. The workflow mirrors Kibana Discover: apply a time range and scope filter, then iteratively add exclusion filters (NOT) until a small, interesting subset of logs remains—either the root cause or the key document. Optionally view logs in context (preceding and following that document) or pivot to another entity and start a fresh search. Use ES|QL only ( POST /_query ); do not use Query DSL. When NOT to use Metrics or traces — u...
 3.2K
5703 apify-sdk-integration apify/agent-skills
Apify SDK Integration Add Apify Actor execution to an existing application. This skill covers the apify-client package for JS/TS and Python, plus the REST API for other languages. When to Use This Skill Adding web scraping or automation to an existing app Calling Apify Actors programmatically from application code Building a product that uses Apify as a backend service Integrating Actor results into a data pipeline Critical: Package Naming apify-client is the API client for calling Actors from y...
 3.2K
5704 archimate markdown-viewer/skills
Enterprise Architecture Diagram Generator (ArchiMate) Quick Start: Add !include <archimate/Archimate> → Declare typed elements → Connect with Rel_* macros → Group into layers with rectangle → Wrap in ```plantuml fence. ⚠️ IMPORTANT: Always use ```plantuml or ```puml code fence. NEVER use ```text — it will NOT render as a diagram. Critical Rules Every diagram starts with @startuml and ends with @enduml Must include !include <archimate/Archimate> before using any macros Element syntax: Layer_Type(...
 3.2K
5705 keyword-research eronred/aso-skills
Keyword Research This skill helps you discover, analyze, and prioritize keywords for SEO and GEO content strategies. It identifies high-value opportunities based on search volume, competition, intent, and business relevance. When to Use This Skill Starting a new content strategy or campaign Expanding into new topics or markets Finding keywords for a specific product or service Identifying long-tail keyword opportunities Understanding search intent for your industry Planning content calendars R...
 3.2K
5706 cross-linker ar9av/obsidian-wiki
Cross-Linker — Automated Wiki Cross-Referencing You are weaving the wiki's knowledge graph tighter by finding and inserting missing [[wikilinks]] between pages that should reference each other but currently don't. Follow the Retrieval Primitives table in llm-wiki/SKILL.md . Build the registry in Step 1 by grepping frontmatter only (not full pages). Reserve full Read for the unlinked-mention detection pass, and even there, only read pages whose summaries/titles make them plausible link targets. B...
 3.2K
5707 hackernews vm0-ai/vm0-skills
Hacker News API Use the official Hacker News API via direct curl calls to fetch stories, comments, and user data . Official docs: https://github.com/HackerNews/API When to Use Use this skill when you need to: Fetch top/best/new stories from Hacker News Get story details including title, URL, score, comments Retrieve comments and discussion threads Look up user profiles and their submissions Monitor trending tech topics and discussions Prerequisites No API key required! The Hacker News API is com...
 3.2K
5708 android-kotlin alinaqi/maggy
Android Kotlin Skill Project Structure Show more Installs 2.9K Repository alinaqi/maggy GitHub Stars 705 First Seen Jan 20, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Warn
 3.2K
5709 senior-data-scientist davila7/claude-code-templates
Senior Data Scientist World-class senior data scientist skill for production-grade AI/ML/Data systems. Quick Start Main Capabilities Core Tool 1 python scripts/experiment_designer.py --input data/ --output results/ Core Tool 2 python scripts/feature_engineering_pipeline.py --target project/ --analyze Core Tool 3 python scripts/model_evaluation_suite.py --config config.yaml --deploy Core Expertise This skill covers world-class capabilities in: Advanced production patterns and architec...
 3.2K
5710 convex-functions waynesutton/convexskills
Convex Functions Master Convex functions including queries, mutations, actions, and HTTP endpoints with proper validation, error handling, and runtime considerations. Documentation Sources Before implementing, do not assume; fetch the latest documentation: Primary: https://docs.convex.dev/functions Query Functions: https://docs.convex.dev/functions/query-functions Mutation Functions: https://docs.convex.dev/functions/mutation-functions Actions: https://docs.convex.dev/functions/actions HTTP ...
 3.2K
5711 backtest marketcalls/vectorbt-backtesting-skills
Create a complete VectorBT backtest script for the user. Arguments Parse $ARGUMENTS as: strategy symbol exchange interval $0 = strategy name (e.g., ema-crossover, rsi, donchian, supertrend, macd, sda2, momentum) $1 = symbol (e.g., SBIN, RELIANCE, NIFTY). Default: SBIN $2 = exchange (e.g., NSE, NFO). Default: NSE $3 = interval (e.g., D, 1h, 5m). Default: D If no arguments, ask the user which strategy they want. Instructions Read the vectorbt-expert skill rules for reference patterns Create backte...
 3.2K
5712 hackernews okou-ai/vm0-skills
Hacker News API Use the official Hacker News API via direct curl calls to fetch stories, comments, and user data . Official docs: https://github.com/HackerNews/API When to Use Use this skill when you need to: Fetch top/best/new stories from Hacker News Get story details including title, URL, score, comments Retrieve comments and discussion threads Look up user profiles and their submissions Monitor trending tech topics and discussions Prerequisites No API key required! The Hacker News API is com...
 3.2K
5713 wiki-rebuild ar9av/obsidian-wiki
Wiki Rebuild — Archive, Rebuild, Restore You are performing a destructive operation on the wiki. Always archive first, always confirm with the user before proceeding. Before You Start Read .env to get OBSIDIAN_VAULT_PATH Read .manifest.json to understand current state Confirm the user's intent. This skill supports three modes: Archive only — snapshot current wiki, no rebuild Archive + Rebuild — snapshot, then reprocess all sources from scratch Restore — bring back a previous archive The Archive ...
 3.2K
5714 hackernews okou-ai/okou-skills
Hacker News API Use the official Hacker News API via direct curl calls to fetch stories, comments, and user data . Official docs: https://github.com/HackerNews/API When to Use Use this skill when you need to: Fetch top/best/new stories from Hacker News Get story details including title, URL, score, comments Retrieve comments and discussion threads Look up user profiles and their submissions Monitor trending tech topics and discussions Prerequisites No API key required! The Hacker News API is com...
 3.2K
5715 account-research anthropics/knowledge-work-plugins
Account Research Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data. How It Works ┌─────────────────────────────────────────────────────────────────┐ │ ACCOUNT RESEARCH │ ├─────────────────────────────────────────────────────────────────┤ │ ALWAYS (works standalone via web search) │ │ ✓ Company overview: what th...
 3.2K
5716 wiki-export ar9av/obsidian-wiki
Wiki Export — Knowledge Graph Export You are exporting the wiki's wikilink graph to structured formats so it can be used in external tools (Gephi, Neo4j, custom scripts, browser visualization). Before You Start Read .env to get OBSIDIAN_VAULT_PATH Confirm the vault has pages to export — if fewer than 5 pages exist, warn the user and stop Visibility Filter (optional) By default, all pages are exported regardless of visibility tags. This preserves existing behavior. If the user requests a filtered...
 3.2K
5717 git-fork-clone zc277584121/mygitplugin
Git Fork & Clone Fork 别人的 GitHub 仓库并 clone 到本地，自动配置 official remote。 触发条件 当用户要求 fork 别人的仓库并 clone 到本地时使用此 skill。 输入 用户需要提供目标仓库，格式为 owner/repo 。 执行步骤 Fork 仓库 ：使用 gh repo fork <owner/repo> --clone=false 将仓库 fork 到 zc277584121 账号下。 Clone 仓库 ：使用 gh repo clone zc277584121/<repo> 将 fork 后的仓库 clone 到本地。 进入项目目录 ： cd <repo> 。 添加 official remote ： git remote add official https://github.com/<original-owner>/<repo>.git ，用于跟踪上游仓库。 验证 remote 配置 ： git remote -v ，确认 origin 指向自己的 fork，official 指向原始仓库。 Show more ...
 3.2K
5718 git-summarize-weekly zc277584121/mygitplugin
Git Summarize Weekly 总结本周的 GitHub 贡献，输出适合写入周报的英文摘要。 触发条件 当用户要求总结本周 GitHub 贡献、写周报或查看本周工作时使用此 skill。 执行步骤 计算日期范围 ：计算本周一的日期到今天。使用 date 命令计算。 拉取 GitHub events ： gh api users/zc277584121/events --paginate --jq '.[]' 获取用户近期的 GitHub 活动事件。 Show more Installs 430 Repository zc277584121/mygitplugin First Seen Apr 27, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Warn
 3.2K
5719 crypto-report aahl/skills
No SKILL.md available for this skill. View on GitHub
 3.2K
5720 git-get-notification zc277584121/mygitplugin
Git Get Notification Check GitHub notifications, recent Issues, and recent PRs for a set of monitored repositories. Trigger When the user asks to check notifications, see what's new, or check updates on monitored repos. Monitored Repos zilliztech/claude-context zilliztech/memsearch zilliztech/mcp-server-milvus langchain-ai/langchain-milvus milvus-io/milvus-haystack zilliztech/milvus-marketplace zilliztech/vector-graph-rag Execution Steps Show more Installs 427 Repository zc277584121/mygitplugin ...
 3.2K
5721 git-sync-main zc277584121/mygitplugin
Git Sync Main 同步最新主分支代码到本地并切换到主分支。支持两种场景：fork 的项目从 official remote 同步，自己的项目从 origin 同步。 触发条件 当用户要求同步上游代码、更新主分支、或拉取最新主分支代码时使用此 skill。 执行步骤 检查 remote 配置 ： git remote -v ，确认是否存在 official remote。 根据是否存在 official remote 分两种情况执行 ： 情况一：存在 official remote（fork 的项目） 检测主分支名称 ：通过 git remote show official 或查看本地分支，确定主分支名称（ main 或 master ）。 拉取 official 最新代码 ： git fetch official 。 Show more Installs 426 Repository zc277584121/mygitplugin First Seen Apr 27, 2026 Security Audits Gen Agent Trust Hub Pass Socket P...
 3.2K
5722 paper-audit bahayonghang/academic-writing-skills
Paper Audit Skill Unified academic paper auditing across formats and languages. Steps Parse the paper path and mode from $ARGUMENTS . If missing, confirm the target .tex , .typ , or .pdf file. Review evaluation criteria in $SKILL_DIR/references/REVIEW_CRITERIA.md and $SKILL_DIR/references/CHECKLIST.md . Run the orchestrator: python $SKILL_DIR/scripts/audit.py $ARGUMENTS . Present the MD report directly to the user. Distinguish between automated findings and LLM-judgment scores. If in review mode...
 3.2K
5723 creative-director nexu-io/open-design
creative-director Curated from @smixs. What it does AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics), 3-axis evaluation calibrated against Cannes/D&AD/HumanKind, 5-phase process from brief to presentation. Source Upstream: https://github.com/smixs/creative-director-skill Category: creative-direction How to use This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstr...
 3.2K
5724 launchdarkly-metric-choose launchdarkly/ai-tooling
LaunchDarkly Metric Choose You're using a skill that helps users select the right metrics before setting up an experiment, guarded rollout, or release policy. Your job is to understand the feature context, surface what will auto-attach from existing project policies, inventory what's available and healthy, and produce a clear typed recommendation. This skill is advisory. It does not create metrics, attach them to experiments, or configure rollouts. For those tasks, see the
 3.2K
5725 goframe-v2 gogf/skills
重要规范 工程开发规范 开发完整工程类型的项目如HTTP、微服务项目时，需要先安装GoFrame CLI开发工具，并使用CLI工具创建项目骨架，对应命令为gf init，命令的具体使用方式需参考文档 项目创建-init 。 在GoFrame工程规范中，由开发工具自动维护的代码文件，如dao、do、entity等源码文件，不允许手动创建或修改。 除非用户有明确要求，否则不使用logic目录来存放业务逻辑代码，而是直接在service目录下进行业务逻辑的封装和实现。 完整工程目录、代码封装以及源码实现的示例需参考已有示例项目，如： HTTP项目最佳实践示例： user-http-service gRPC项目最佳实践示例： user-grpc-service 组件使用规范 创建新的方法或变量前要先分析是否在其它位置中已经存在，尽量引用已有的实现。 错误处理统一使用gerror组件，确保错误信息带有完整堆栈信息以提供可追踪性。 在调研使用新组件时，优先考虑引用GoFrame框架中已有组件、优先参考示例代码中的最佳实践源码。 Go开发资料 完整的GoFrame开发资料，包含各类组件的设计介绍、使...
 3.2K
5726 risk-assessment anthropics/knowledge-work-plugins
Risk Assessment Systematically identify, assess, and plan mitigations for operational risks. Risk Assessment Matrix Low Impact Medium Impact High Impact High Likelihood Medium High Critical Medium Likelihood Low Medium High Low Likelihood Low Low Medium Risk Categories Operational : Process failures, staffing gaps, system outages Financial : Budget overruns, vendor cost increases, revenue impact Compliance : Regulatory violations, audit findings, policy breaches Strategic : Market changes, compe...
 3.2K
5727 pr-review pytorch/pytorch
PyTorch PR Review Skill Review PyTorch pull requests focusing on what CI cannot check: code quality, test coverage adequacy, security vulnerabilities, and backward compatibility. Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . Instead, ask the user what they would like to review: What would you like me to review? A PR number or URL (e.g., /pr-review 12345 ) A local branch (e.g., /pr-review branch ) Local CLI Mode The user provides a PR number o...
 3.2K
5728 app-marketing-context appeeky/aso-skills
App Marketing Context You are an expert mobile app marketing strategist. Your goal is to help the user create a comprehensive context document that all other ASO and app marketing skills will reference. Initial Assessment Check if app-marketing-context.md exists in the project root or .claude/ directory. If it exists: Read it and ask if the user wants to update any section. If it doesn't exist: Walk through each section below, asking questions to build the document. Context Document Structure Cr...
 3.2K
5729 yeet openai/skills
Prerequisites Require GitHub CLI gh . Check gh --version . If missing, ask the user to install gh and stop. Require authenticated gh session. Run gh auth status . If not authenticated, ask the user to run gh auth login (and re-run gh auth status ) before continuing. Naming conventions Branch: {description} when starting from main/master/default. Commit: {description} (terse). PR title: {description} summarizing the full diff. PR template discovery Before creating the PR, resolve the repository r...
 3.2K
5730 ce-setup everyinc/compound-engineering-plugin
Contains Shell Commands This skill contains shell command directives ( !`command` ) that may execute system commands. Review carefully before installing. Compound Engineering Setup Interaction Method Ask the user each question below using the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex, ask_user in Gemini, ask_user in Pi (requires the pi-ask-user extension). Fall back...
 3.2K
5731 options-payoff himself65/finance-skills
Options Payoff Curve Skill Generates a fully interactive HTML widget (via visualize:show_widget ) showing: Expiry payoff curve (dashed gray line) — intrinsic value at expiration Theoretical value curve (solid colored line) — Black-Scholes price at current DTE/IV Dynamic sliders for all key parameters Real-time stats: max profit, max loss, breakevens, current P&L at spot Step 1: Extract Strategy From User Input When the user provides a screenshot or text, extract: Field Where to find it Default i...
 3.2K
5732 launchdarkly-metric-create launchdarkly/ai-tooling
LaunchDarkly Metric Create You're using a skill that will guide you through creating a LaunchDarkly metric. For custom metrics, getting events flowing comes first — before the metric is created. Your job is to determine the right metric kind, instrument the event if it isn't already flowing (including SDK setup and environment wiring), check for duplicates, propose a metric config, get explicit confirmation, then create and verify. Prerequisites This skill requires the remotely hosted LaunchDark...
 3.2K
5733 launchdarkly-metric-instrument launchdarkly/ai-tooling
LaunchDarkly Metric Instrument You're using a skill that will guide you through adding a track() call to a codebase so a LaunchDarkly metric can measure it. Your job is to detect the SDK in use, find the right place in code to add the call, write it correctly, and verify that events are reaching LaunchDarkly. Prerequisites This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment. Required MCP tools: list-metric-events — verify events are flowing after ...
 3.2K
5734 threejs nexu-io/open-design
threejs Curated from CloudAI-X. What it does Three.js skills for creating 3D elements and interactive experiences in the browser — scenes, materials, controls, and post-processing. Source Upstream: https://github.com/CloudAI-X/threejs-skills Category: 3d-shaders How to use This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your act...
 3.2K
5735 macos-security-bypass yaklang/hack-skills
SKILL: macOS Security Bypass — Expert Attack Playbook AI LOAD INSTRUCTION : Expert macOS security bypass techniques. Covers TCC bypass, Gatekeeper evasion, SIP restrictions, sandbox escape, and entitlement abuse. Base models miss version-specific bypass nuances and protection interaction effects. 0. RELATED ROUTING Before going deep, consider loading: macos-process-injection when you need dylib injection, XPC exploitation, or Electron abuse after achieving initial access linux-privilege-escalati...
 3.2K
5736 m07-concurrency actionbook/rust-skills
Concurrency Layer 1: Language Mechanics Core Question Is this CPU-bound or I/O-bound, and what's the sharing model? Before choosing concurrency primitives: What's the workload type? What data needs to be shared? What's the thread safety requirement? Error → Design Question Show more
 3.2K
5737 writing-prds refoundai/lenny-skills
Writing PRDs Help the user write effective product requirements documents using frameworks and insights from 11 product leaders. How to Help When the user asks for help with PRDs: Start with the why - Ask about the problem being solved and why it matters now, before features Define success upfront - Help them articulate how they'll know the feature succeeded Choose the right format - Discuss whether they need a traditional doc, a prototype, or executable evals Keep it actionable - Ensure the doc...
 3.2K
5738 localization appeeky/aso-skills
This guide covers setting up and configuring Unity Localization, including locales, String and Asset Tables, Addressables integration, and CJK font support via Asset Tables. 0. Package Installation Check Before doing anything else, verify that the Localization package is installed. Many APIs in this skill will fail silently or throw confusing errors if the package isn't present. Show more Installs 3.0K Repository unity-technolog…s/skills GitHub Stars 924 First Seen Aug 13, 2026 Security Audits G...
 3.2K
5739 memory-leak-audit microsoft/vscode
Memory Leak Audit The 1 bug category in VS Code. This skill encodes the patterns that prevent and fix leaks. When to Use Reviewing code that registers event listeners or DOM handlers Fixing reported memory leaks (listener counts growing over time) Creating objects in methods that are called repeatedly Working with model lifecycle events (onWillDispose, onDidClose) Adding event subscriptions in constructors or setup methods Audit Checklist Work through each check in order. A single missed pattern...
 3.2K
5740 ntlm-relay-coercion yaklang/hack-skills
SKILL: NTLM Relay and Authentication Coercion — Expert Attack Playbook AI LOAD INSTRUCTION : Expert NTLM relay and coercion techniques. Covers relay to SMB/LDAP/HTTP/MSSQL, signing requirements, Responder poisoning, mitm6, cross-protocol relay, WebDAV coercion, and all major coercion methods. Base models miss signing/EPA requirements and cross-protocol relay constraints. 0. RELATED ROUTING Before going deep, consider loading: active-directory-certificate-services for ESC8 (relay to ADCS enrollme...
 3.2K
5741 trading-analysis gracefullight/stock-checker
Trading Analysis & Investment Report Generator This skill generates comprehensive investment reports combining real-time market data, technical analysis, Claude AI insights, and professional visualizations. What This Skill Does Downloads real-time market data from Yahoo Finance Calculates 10+ technical indicators (RSI, MACD, Moving Averages, Bollinger Bands, etc.) Analyzes market conditions using Claude AI Generates 4 types of professional charts (price, indicators, volatility, dashboard) Crea...
 3.2K
5742 app-analytics appeeky/aso-skills
App Analytics You are an expert in mobile app analytics and measurement strategy. Your goal is to help the user set up meaningful tracking, interpret their data, and make data-driven decisions. Initial Assessment Check for app-marketing-context.md — read it for context Ask: What analytics tools do you currently use? Ask: What are your top 3 questions about your app's performance? Ask: What decisions do you need data to make? Ask: Do you run paid acquisition? (attribution matters) Analytics Stack...
 3.2K
5743 azure-pipelines microsoft/vscode
Validating Azure Pipeline Changes When modifying Azure DevOps pipeline files (YAML files in build/azure-pipelines/ ), you can validate changes locally using the Azure CLI before committing. This avoids the slow feedback loop of pushing changes, waiting for CI, and checking results. Prerequisites Check if Azure CLI is installed : az --version If not installed, install it: macOS brew install azure-cli Windows (PowerShell as Administrator) winget install Microsoft.AzureCLI Linux (Debian/Ubuntu) ...
 3.2K
5744 humanizer daleseo/korean-skills
Humanizer: Remove AI Writing Patterns You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup. Your Task When given text to humanize: Identify AI patterns - Scan for the patterns listed below. Preserve the information, not the shape - Every claim in the original survives into the rewrite, but depth doesn't have to be uniform: co...
 3.2K
5745 mailtrap-email-integration affaan-m/ecc
Mailtrap Email Integration Patterns for adding transactional email sending to an application using Mailtrap's Email API and Sandbox, covering authentication, environment separation, and common delivery pitfalls. When to Activate Implementing a "send email" feature (signup confirmation, password reset, notifications, receipts) Debugging why emails aren't arriving in dev/staging Setting up a project's first email-sending integration Reviewing code that calls an email API directly without sandbox s...
 3.2K
5746 macos-process-injection yaklang/hack-skills
SKILL: macOS Process Injection — Expert Attack Playbook AI LOAD INSTRUCTION : Expert macOS process injection techniques. Covers DYLD_INSERT_LIBRARIES, dylib hijacking (weak/rpath/proxy), XPC PID reuse attacks, Mach port manipulation, MIG abuse, and Electron injection. Base models miss entitlement prerequisites and SIP constraints on injection vectors. 0. RELATED ROUTING Before going deep, consider loading: macos-security-bypass when you need to bypass TCC, Gatekeeper, or SIP protections blocking...
 3.2K
5747 app-launch appeeky/aso-skills
App Launch Strategy You are an expert in mobile app launches with experience across indie apps and top-charting products. Your goal is to create a comprehensive launch plan that maximizes day-one visibility and sustains momentum. Initial Assessment Check for app-marketing-context.md — read it for app context Ask: New app or major update? Ask: Launch date (or flexible?) Ask: Budget (organic only, or paid acquisition available?) Ask: Pre-existing audience? (email list, social following, existing a...
 3.2K
5748 3d-animation-short-generator minimax-ai/minimax-h3
3D Animation Short Generator Use this Skill when the user wants a complete story-first animated short workflow, from one-line idea to final edited video. The workflow must place every major artifact on the canvas in production order and pause at creative gates with user choice cards before expensive or high-impact steps. Core rule: story first, ask screen size and total duration with choice cards immediately after user intake, ordered canvas artifacts, every required confirmation via choice card...
 3.2K
5749 jupyter-to-marimo marimo-team/skills
Converting Jupyter Notebooks to Marimo IMPORTANT : When asked to translate a notebook, ALWAYS run uvx marimo convert <notebook.ipynb> -o <notebook.py> FIRST before reading any files. This saves precious tokens - reading large notebooks can consume 30k+ tokens, while the converted .py file is much smaller and easier to work with. Steps Convert using the CLI Run the marimo convert command via uvx so no install is needed: uvx marimo convert < notebook.ipynb > -o < notebook.py > This generates a mar...
 3.2K
5750 metal-kernel pytorch/pytorch
Metal Kernel Writing Guide This skill guides you through implementing Metal kernels for PyTorch operators on Apple Silicon. Important: The goal of this skill is to use native Metal capabilities via the c10/metal/ infrastructure, NOT MPSGraph. Native Metal kernels provide better control, performance, and maintainability. Overview There are two workflows covered by this skill: Adding new MPS support - Implementing a new operator from scratch Migrating from MPSGraph - Converting existing MPSGr...
 3.2K