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...
24,390
总 Skills
87.2M
总安装量
2,570
贡献者
# Skill 仓库 描述 安装量
24251 fusion-skill-self-report-bug equinor/fusion-skills
Self-report Fusion Skill Bugs When to use Use this skill when a Fusion skill workflow fails and you need a consistent, triage-ready bug report draft. Treat this as the default failure handoff for any fusion-* skill execution. Typical triggers: "a fusion-* skill failed" "this skill run failed" "self-report this skill error" "create a bug from this workflow failure" "capture this automation failure for triage" When not to use Do not use this skill for: Feature requests or roadmap planning General ...
 34
24252 fluentd-config-generator jeremylongshore/claude-code-plugins-plus-skills
Fluentd Config Generator Purpose This skill provides automated assistance for fluentd config generator tasks within the DevOps Advanced domain. When to Use This skill activates automatically when you: Mention "fluentd config generator" in your request Ask about fluentd config generator patterns or best practices Need help with advanced devops skills covering kubernetes, terraform, advanced ci/cd, monitoring, and infrastructure as code. Capabilities Provides step-by-step guidance for fluentd conf...
 34
24253 claude-code-debug 0xdarkmatter/claude-mods
Claude Code Debug Troubleshoot extensions, hooks, and unexpected behavior. Quick Diagnostics Enable debug mode claude --debug Check loaded extensions /hooks View registered hooks /agents View available agents /memory View loaded memory files /config View current configuration Common Issues Symptom Quick Check Skill not activating Verify description has trigger keywords Hook not running Check chmod +x , run /hooks Agent not delegating Add "Use proactively" to description MCP connection fail...
 34
24254 plaid raintree-technology/claude-starter
PLAID — Product Led AI Development You are a product development advisor helping a founder go from idea to buildable spec. You are warm, direct, and opinionated. You treat the founder as capable and smart — you’re here to help them articulate what’s already in their head, not to lecture them. The full pipeline is: Vision → Strategy → Spec → Build. Modes PLAID has three modes. Pick the right one based on context: Starting fresh (no vision.json exists): Run the vision intake conversation. See “Vis...
 34
24255 scikit-learn eyadsibai/ltk
Scikit-learn Overview This skill provides comprehensive guidance for machine learning tasks using scikit-learn, the industry-standard Python library for classical machine learning. Use this skill for classification, regression, clustering, dimensionality reduction, preprocessing, model evaluation, and building production-ready ML pipelines. Installation Install scikit-learn using uv uv uv pip install scikit-learn Optional: Install visualization dependencies uv uv pip install matplotlib seab...
 34
24256 security travisjneuman/.claude
Security Architecture Diagram Generator Quick Start: Define trust boundaries → Place identity/encryption/firewall icons → Connect with access flows → Group into security zones → 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 Use left to right direction for access flows (User → AuthN → AuthZ → Resource) Use mxgraph.aws4.* stencil syn...
 34
24257 spec-execute zixun-github/aisdlc
spec-execute（I2：执行 / plan.md SSOT） 概览 I2 的目标是把 {FEATURE_DIR}/implementation/plan.md 中的任务 按批次执行 ，并把执行状态与最小审计信息 只回写到 plan.md （作为唯一执行清单与状态 SSOT）。 本技能是 skills/executing-plans/SKILL.md 的 Spec 实现阶段版： 重度复用其“五步执行 + 批次检查点 + 遇阻塞即停”骨架 ，但将“计划文件”的语义替换为实现阶段 SOP（见 design/aisdlc_spec_implementation.md ）的硬约束： plan.md 是 唯一 执行清单与状态来源（checkbox + 审计信息 + 验证结果摘要） 默认每批执行 前 3 个未完成任务 任何 NEEDS CLARIFICATION / 关键计划缺陷 / 阻塞： 立即停止并汇报 （禁止脑补推进） 若执行中产生决策/契约变更： 仅在 {FEATURE_DIR} 内草拟 ，并在 plan.md 追加 Merge-back 待办清单 （本阶段禁止直接更新 projec...
 34
24258 frontend-ux austintgriffith/ethskills
Frontend UX Rules What You Probably Got Wrong "The button works." Working is not the standard. Does it disable during the transaction? Does it show a spinner? Does it stay disabled until the chain confirms? Does it show an error if the user rejects? AI agents skip all of this, every time. "I used wagmi hooks." Wrong hooks. Scaffold-ETH 2 wraps wagmi with useTransactor which waits for transaction confirmation — not just wallet signing. Raw wagmi's writeContractAsync resolves the moment the user c...
 34
24259 k8s-security eyadsibai/ltk
Kubernetes Security Policies Implement defense-in-depth security for Kubernetes clusters. Pod Security Standards Restricted (Most Secure) apiVersion : v1 kind : Namespace metadata : name : restricted - ns labels : pod-security.kubernetes.io/enforce : restricted pod-security.kubernetes.io/audit : restricted pod-security.kubernetes.io/warn : restricted Secure Pod Configuration apiVersion : v1 kind : Pod metadata : name : secure - pod spec : securityContext : runAsNonRoot : true runAsUser : 1000 fs...
 34
24260 anime-story-creator tippyentertainment/skills
Provided by TippyEntertainment https://github.com/tippyentertainment/skills.git Anime Story Generator Skill Summary Generates original anime story concepts, including worldbuilding, characters, power systems, and multi‑episode arcs, tailored to the user’s preferences (genre, tone, length, target audience). This skill is designed for use on the Tasking.tech agent platform ( https://tasking.tech ) and is also compatible with assistant runtimes that accept skill-style handlers such as .claude, .ope...
 34
24261 database-design-patterns nickcrew/claude-ctx-plugin
Database Design Patterns Expert guidance for designing scalable database schemas, optimizing query performance, and implementing robust data persistence layers across relational and NoSQL databases. When to Use This Skill Designing database schemas for new applications Optimizing slow queries and database performance Choosing between normalization and denormalization strategies Implementing partitioning, sharding, or replication strategies Migrating between database technologies (SQL to NoSQL ...
 34
24262 git-commit molechowski/claude-skills
Git Commit with Conventional Commits Overview Create standardized, semantic git commits using the Conventional Commits specification. Analyze the actual diff to determine appropriate type, scope, and message. Conventional Commit Format <type>[optional scope]: <description> [optional body] [optional footer(s)] Commit Types Type Purpose feat New feature fix Bug fix docs Documentation only style Formatting/style (no logic) refactor Code refactor (no feature/fix) perf Performance improvement test Ad...
 34
24263 xint 0xnyk/xint
xint — X Intelligence CLI General-purpose agentic research over X/Twitter. Decompose any research question into targeted searches, iteratively refine, follow threads, deep-dive linked content, and synthesize into a sourced briefing. For X API details (endpoints, operators, response format): read references/x-api.md . Security Considerations This skill requires sensitive credentials. Follow these guidelines: Credentials X_BEARER_TOKEN : Required for X API. Treat as a secret - prefer exported envi...
 34
24264 dev-review-pr molechowski/claude-skills
Review PR Change-focused code review for diffs, staged changes, and GitHub PRs. Brutally honest, professionally delivered. Persona Strict tech lead with zero tolerance for sloppy changes. Focus on what CHANGED, not the entire codebase Judge changes in context of surrounding code Flag regressions and new risks introduced by the change No hedge words. Never use "might", "perhaps", "consider", "maybe" Default assumption: changes need scrutiny until proven sound Be specific: cite the diff line, expl...
 34
24265 elysia epicenterhq/epicenter
Elysia.js Patterns (v1.2+) When to Apply This Skill Use this pattern when you need to: Write or refactor Elysia handlers to use status() responses. Define per-status response schemas for Eden Treaty type safety. Migrate handlers away from set.status plus error-object returns. Compose Elysia plugins/guards for shared auth and route behavior. Choose between return status(...) and throw status(...) by control-flow context. The status() Helper (ALWAYS use this) Never use set.status + return object. ...
 34
24266 ai-discoverability-audit brianrwagner/ai-marketing-skills
AI Discoverability Audit You are an AI discoverability expert. Audit how a brand appears in AI search and recommendation systems, identify gaps, and produce an action plan with a re-audit schedule. Why This Matters: Traditional SEO optimizes for Google. AI discoverability optimizes for how LLMs understand, describe, and recommend a brand. If AI assistants can't describe you accurately, you're invisible to a growing segment of high-intent searchers. Mode Detect from context or ask: "Quick scan, f...
 34
24267 polyglot-rust-c letta-ai/skills
Polyglot Rust/C Programming This skill provides structured guidance for creating source files that compile and execute correctly as both Rust and C/C++ programs. Core Principle: Action Over Analysis The most critical lesson for polyglot tasks: start writing code immediately . Polyglot programming requires empirical validation through actual compilation. Mental reasoning alone cannot account for all syntax edge cases across languages. Recommended Workflow Phase 1: Establish Working Environment Cr...
 34
24268 leadership-stakeholder-management pluginagentmarketplace/custom-plugin-product-manager
Leadership & Stakeholder Management Skill Master the human side of product management. Align stakeholders, communicate effectively, resolve conflicts, and inspire teams toward shared vision. Stakeholder Mapping & Analysis Identify All Stakeholders ┌─────────────────┬──────────────────┐ │ DECISION │ INFLUENCE │ ← POWER │ MAKERS │ MAKERS │ │ │ │ │ CEO, Board │ VP Eng, Design │ ├─────────────────┼──────────────────┤ │ USERS...
 34
24269 ux-researcher borghei/claude-skills
UX Researcher Purpose Provides user experience research expertise specializing in qualitative and quantitative research methods to drive user-centered design. Uncovers user needs through interviews, usability testing, and data synthesis for actionable product insights. When to Use Planning and conducting user interviews or contextual inquiries Running usability tests (moderated or unmoderated) Analyzing qualitative data (thematic analysis, affinity mapping) Creating artifacts like Personas, User...
 34
24270 skill-creator aaaaqwq/claude-code-skills
Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: Decide what you want the skill to do and roughly how it should do it Write a draft of the skill Create a few test prompts and run claude-with-access-to-the-skill on them Help the user evaluate the results both qualitatively and quantitatively While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you...
 34
24271 worker yeachan-heo/oh-my-codex
Worker Skill This skill is for a Codex session that was started as an OMX Team worker (a tmux pane spawned by $team ). Identity You MUST be running with OMX_TEAM_WORKER set. It looks like: <team-name>/worker-<n> Example: alpha/worker-2 Load Worker Skill Path (Claude/Codex) When a worker inbox tells you to load this skill, resolve the first existing path: ${CODEX_HOME:-~/.codex}/skills/worker/SKILL.md ~/.codex/skills/worker/SKILL.md <leader_cwd>/.codex/skills/worker/SKILL.md <leader_cwd>/skills/w...
 34
24272 facebook-automation aaaaqwq/claude-code-skills
Facebook Automation via Rube MCP Automate Facebook operations through Composio's Facebook toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Facebook connection via RUBE_MANAGE_CONNECTIONS with toolkit facebook Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds Call RUBE_MAN...
 34
24273 openai-webhooks hookdeck/webhook-skills
OpenAI Webhooks When to Use This Skill Setting up OpenAI webhook handlers for async operations Debugging signature verification failures Handling fine-tuning job completion events Processing batch API completion notifications Handling realtime API incoming calls Essential Code (USE THIS) Express Webhook Handler const express = require ( 'express' ) ; const crypto = require ( 'crypto' ) ; const app = express ( ) ; // Standard Webhooks signature verification for OpenAI function verifyOpenAISignatu...
 34
24274 busirocket-tauri busirocket/agents-skills
Tauri Standards Tauri-specific conventions for desktop applications. Builds on busirocket-rust for language and module rules. When to Use Use this skill when: Creating or refactoring Tauri commands Registering commands in the invoke handler and permissions Structuring a Tauri project (src-tauri layout, sql, prompts) Non-Negotiables (MUST) When creating a Tauri command: (1) create command file, (2) register in invoke handler, (3) add to permissions allowlist. Rust code lives under src-tauri/src/ ...
 34
24275 remote-browser shawnpana/browser-use
Remote Browser Automation for Sandboxed Agents This skill is for agents running on sandboxed remote machines (cloud VMs, CI, coding agents) that need to control a browser. Install browser-use and drive a cloud browser — no local Chrome needed. Prerequisites Before using this skill, browser-use must be installed and configured. Run diagnostics to verify: browser-use doctor For more information, see https://github.com/browser-use/browser-use/blob/main/browser_use/skill_cli/README.md Core Workflow ...
 34
24276 search htlin222/dotfiles
Search Skill Search the web and get relevant results optimized for LLM consumption. Authentication The script uses OAuth via the Tavily MCP server. No manual setup required - on first run, it will: Check for existing tokens in ~/.mcp-auth/ If none found, automatically open your browser for OAuth authentication Note: You must have an existing Tavily account. The OAuth flow only supports login — account creation is not available through this flow. Sign up at tavily.com first if you don't have an a...
 34
24277 blink openagentsinc/openagents
Blink Skill Bitcoin Lightning wallet operations via the Blink API. Enables agents to check balances, receive payments via invoices, send payments over Lightning, swap between BTC and USD wallets, track transactions, and monitor prices. What is Blink? Blink is a custodial Bitcoin Lightning wallet with a GraphQL API. Key concepts: API Key — authentication token (format: blink_... ) with scoped permissions (Read, Receive, Write) BTC Wallet — balance denominated in satoshis USD Wallet — balance deno...
 34
24278 dart-cli-creator mono0926/skills
Dart CLI Creator Skill This skill provides guidelines and procedures for creating and improving top-quality Command-Line Interface (CLI) tools using Dart. As an agent, you must consistently follow these best practices when requested by the user to create or modify a Dart CLI. 🎯 Core Best Practices 1. Project Structure and Design bin/ directory : Place the entry point executable files for the CLI (e.g., bin/my_cli.dart ). Keep this as a thin wrapper that only calls top-level functions or classes ...
 34
24279 maplibre-mapbox-migration maplibre/maplibre-agent-skills
Mapbox to MapLibre Migration This skill guides you through migrating an application from Mapbox GL JS to MapLibre GL JS . The two libraries share a common ancestry (MapLibre forked from Mapbox GL JS v1.13 in December 2020), so the API is largely the same. The main changes are: swap the package, replace the namespace, remove the Mapbox access token, and choose a new tile source (MapLibre does not use mapbox:// styles). Primary reference: MapLibre official Mapbox migration guide . When to Use This...
 34
24280 torch-pipeline-parallelism letta-ai/skills
Torch Pipeline Parallelism Overview This skill provides guidance for implementing pipeline parallelism in PyTorch for distributed model training. Pipeline parallelism partitions a model across multiple devices/ranks, where each rank processes a subset of layers and communicates activations/gradients with neighboring ranks. Key Concepts Pipeline Parallelism Patterns AFAB (All-Forward-All-Backward) : Process all microbatch forwards first, cache activations, then process all backwards. This is the ...
 34
24281 azure-monitor-query-py sickn33/antigravity-awesome-skills
Azure Monitor Query SDK for Python Query logs and metrics from Azure Monitor and Log Analytics workspaces. Installation pip install azure-monitor-query Environment Variables Log Analytics AZURE_LOG_ANALYTICS_WORKSPACE_ID = < workspace-id > Metrics AZURE_METRICS_RESOURCE_URI = /subscriptions/ < sub > /resourceGroups/ < rg > /providers/ < provider > / < type > / < name > Authentication from azure . identity import DefaultAzureCredential credential = DefaultAzureCredential ( ) Logs Query Client B...
 34
24282 azure-mgmt-fabric-py sickn33/antigravity-awesome-skills
Azure Fabric Management SDK for Python Manage Microsoft Fabric capacities and resources programmatically. Installation pip install azure-mgmt-fabric pip install azure-identity Environment Variables AZURE_SUBSCRIPTION_ID = < your-subscription-id > AZURE_RESOURCE_GROUP = < your-resource-group > Authentication from azure . identity import DefaultAzureCredential from azure . mgmt . fabric import FabricMgmtClient import os credential = DefaultAzureCredential ( ) client = FabricMgmtClient ( credential...
 34
24283 lambda-function-generator jeremylongshore/claude-code-plugins-plus-skills
Lambda Function Generator Purpose This skill provides automated assistance for lambda function generator tasks within the AWS Skills domain. When to Use This skill activates automatically when you: Mention "lambda function generator" in your request Ask about lambda function generator patterns or best practices Need help with amazon web services skills covering compute, storage, networking, serverless, and aws-specific best practices. Capabilities Provides step-by-step guidance for lambda functi...
 34
24284 rag-pipeline-builder patricio0312rev/skills
RAG Pipeline Builder Design end-to-end RAG pipelines for accurate document retrieval and generation. Pipeline Architecture Documents → Chunking → Embedding → Vector Store → Retrieval → Reranking → Generation Chunking Strategy Semantic chunking (recommended) from langchain.text_splitter import RecursiveCharacterTextSplitter splitter = RecursiveCharacterTextSplitter( chunk_size=1000, Characters per chunk chunk_overlap=200, Overlap between chunks separators=["\n\n", "...
 34
24285 cert-manager-setup jeremylongshore/claude-code-plugins-plus-skills
Cert Manager Setup Purpose This skill provides automated assistance for cert manager setup tasks within the DevOps Advanced domain. When to Use This skill activates automatically when you: Mention "cert manager setup" in your request Ask about cert manager setup patterns or best practices Need help with advanced devops skills covering kubernetes, terraform, advanced ci/cd, monitoring, and infrastructure as code. Capabilities Provides step-by-step guidance for cert manager setup Follows industry ...
 34
24286 skills-discovery kamalnrf/claude-plugins
Skills Discovery You can extend your capabilities by discovering and installing Agent Skills from the claude-plugins.dev registry. Skills provide specialized knowledge, tools, and techniques for specific technologies, frameworks, and domains. When to search for skills First, check if an installed skill matches the task. If not, search the registry—specialized skills may exist that you haven't installed yet. Before starting any non-trivial task, ask yourself: Do I have a skill for this? → Use it ...
 34
24287 video-explorer cygnusfear/agent-skills
Video Explorer Analyze video content through hierarchical frame extraction. Start wide, identify interesting regions, zoom in. Workflow 1. Overview First Extract quick thumbnails to see the video timeline: ./skills/video-explorer/scripts/videx overview < video > This creates small frames (320px) at 10-second intervals in ./videx-out/<name>/overview/ . Read all overview frames to understand video structure: ls ./videx-out/ < name > /overview/ Then use the Read tool on the jpg files to see them. ⚠...
 34
24288 review yeachan-heo/oh-my-codex
Review Two-axis review of the diff between HEAD and a fixed point the user supplies: Standards — does the code conform to this repo's documented coding standards? Spec — does the code faithfully implement the originating issue / PRD / spec? Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings. The issue tracker should have been provided to you — run /setup-matt-pocock-skills if docs/agents/issue-tracker.md is missing. Process ...
 34
24289 syncable-entity-testing twentyhq/twenty
Syncable Entity: Integration Testing (Step 6/6 - MANDATORY) Purpose : Create comprehensive test suite covering all validation scenarios, input transpilation exceptions, and successful use cases. When to use : After completing Steps 1-5. Integration tests are REQUIRED for all syncable entities. Quick Start Tests must cover: Failing scenarios - All validator exceptions and input transpilation errors Successful scenarios - All CRUD operations and edge cases Test utilities - Reusable query factories...
 34
24290 plans-kanban duc01226/easyplatform
[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip. Quick Summary Goal: Visual dashboard server for viewing plan directories with progress tracking and timeline visualization. Workflow: Start Server — Point at a plans directory with CLI options Browse Dashboard — View plan cards with progress bars, phase status, activity heatmap Inspect P...
 34
24291 web-scraper sickn33/antigravity-awesome-skills
Web Scraper Extract structured data from websites using BeautifulSoup and requests - turn any webpage into usable data. When to Use This Skill Competitor research - Scrape pricing, features, positioning Lead generation - Extract contact info from directories Content audit - Pull headings, links, meta data Price monitoring - Track competitor pricing changes Data collection - Gather research data from multiple sources What Claude Does vs What You Decide Claude Does You Decide Structures analysis f...
 34
24292 openspec-apply partme-ai/openspec-skills
OpenSpec Apply Skill Use /opsx:apply to implement tasks from a change. The agent reads tasks.md , works through tasks one by one, writes code, creates files, runs tests as needed, and checks off completed items with [x] . When to Use All planning artifacts are complete and the user wants to implement. The user says "implement", "apply", "start coding", "execute tasks". Resuming implementation after an interruption. Prerequisites Planning artifacts complete — at minimum tasks.md exists (created v...
 34
24293 http-client-config jeremylongshore/claude-code-plugins-plus-skills
Http Client Config Purpose This skill provides automated assistance for http client config tasks within the API Integration domain. When to Use This skill activates automatically when you: Mention "http client config" in your request Ask about http client config patterns or best practices Need help with api integration skills covering third-party apis, webhooks, sdk generation, and integration patterns. Capabilities Provides step-by-step guidance for http client config Follows industry best prac...
 34
24294 nginx-c-module-perf pproenca/dot-skills
nginx.org C Module Performance & Reliability Best Practices Comprehensive performance optimization and reliability guide for nginx C modules, derived from the official nginx development documentation and production engineering experience. Contains 43 rules across 8 categories, prioritized by impact to guide automated optimization and resilience improvements. Companion skill : This skill complements nginx-c-modules which covers correctness (memory safety, request lifecycle, configuration). This s...
 34
24295 powerplatform robdtaylor/personal-ai-infrastructure
PowerPlatform - Flow Generation Skill Generate Power Automate flows from natural language descriptions using connector schemas exported from your work environment. Examples Example: Simple notification flow User: "Create a flow that sends me a Teams message when I get an email with 'urgent' in the subject" -> Reads Office365/Teams connector schemas -> Generates flow JSON with email trigger + Teams action -> Outputs solution ZIP to work repo Example: Approval workflow User: "Make a flow fo...
 34
24296 llm-training eyadsibai/ltk
LLM Training Frameworks and techniques for training and finetuning large language models. Framework Comparison Framework Best For Multi-GPU Memory Efficient Accelerate Simple distributed Yes Basic DeepSpeed Large models, ZeRO Yes Excellent PyTorch Lightning Clean training loops Yes Good Ray Train Scalable, multi-node Yes Good TRL RLHF, reward modeling Yes Good Unsloth Fast LoRA finetuning Limited Excellent Accelerate (HuggingFace) Minimal wrapper for distributed training. Run accelerate config f...
 34
24297 bug-hunter sickn33/antigravity-awesome-skills
Bug Hunt - Adversarial Bug Finding Run a sequential-first adversarial bug hunt on your codebase. Use parallelism only for read-only triage and independent verification tasks. Table of Contents Usage Target Context Budget Execution Steps Step 7: Present the Final Report Self-Test Mode Error handling Phase 1 — Find & Verify: Recon (map) --> Hunter (deep scan) --> Skeptic (challenge) --> Referee (final verdict) ^ (optional read-only dual-lens triage can run here) | state + chunk che...
 34
24298 laravel-dtos leeovery/claude-laravel
Laravel DTOs Never pass multiple primitive values. Always wrap data in Data objects. Related guides: dto-transformers.md - Transform external data into DTOs test-factories.md - Create hydrated DTOs for tests Philosophy DTOs provide: Type safety and IDE autocomplete Clear contracts between layers Test factories for easy test data generation Validation integration Transformation from requests to domain objects Spatie Laravel Data Package Uses Spatie Laravel Data . Refer to official docs for packag...
 34
24299 social-media aitytech/agentkits-marketing
Social Media Content Skill This skill provides guidelines for creating engaging social media content that drives engagement and shares. When to Use This Skill Use this skill when asked to: Write a LinkedIn post Create a Twitter/X thread Draft social media announcements Repurpose blog content for social Research First (Required) Before writing any social media content, you MUST delegate research: Use the task tool with subagent_type: "researcher" In the description, specify BOTH the topic A...
 34
24300 skills inference-sh/skills
inference.sh Run 150+ AI apps in the cloud with a simple CLI. No GPU required. Install CLI curl -fsSL https://cli.inference.sh | sh infsh login Quick Examples Generate an image infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}' Generate a video infsh app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}' Call Claude infsh app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}' Web search infsh app run tavily/search-assist...
 34