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...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
5651 using-git-worktrees davila7/claude-code-templates
Using Git Worktrees Overview Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching. Core principle: Systematic directory selection + safety verification = reliable isolation. Announce at start: "I'm using the using-git-worktrees skill to set up an isolated workspace." Directory Selection Process Follow this priority order: 1. Check Existing Directories Check in priority order ls -d .worktrees 2 > /dev/null Pref...
 152
5652 scanpy davila7/claude-code-templates
Scanpy: Single-Cell Analysis Overview Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis. When to Use This Skill This skill should be used when: Analyzing single-cell RNA-seq data (.h5ad, 10X, CSV formats) Performing quality control on scRNA-seq datasets...
 152
5653 sql-query-optimization aj-geddes/useful-ai-prompts
SQL Query Optimization Overview Analyze SQL queries to identify performance bottlenecks and implement optimization techniques. Includes query analysis, indexing strategies, and rewriting patterns for improved performance. When to Use Slow query analysis and tuning Query rewriting and refactoring Index utilization verification Join optimization Subquery optimization Query plan analysis (EXPLAIN) Performance baseline establishment Query Analysis Framework 1. Analyze Current Performance PostgreS...
 152
5654 weibo-hot-search agentbay-ai/agentbay-skills
微博热搜查询 依赖 python3 -m pip install wuying-agentbay-sdk 安装步骤 在使用此技能之前，请确保已安装必要的依赖包： python3 -m pip install wuying-agentbay-sdk 使用场景 用户想查询微博热搜榜单 用户想了解文娱类热搜话题 用户想筛选特定热度以上的热搜内容 使用方法 python3 scripts/browser-use.py "<任务执行步骤>" 快速示例 python3 scripts/browser-use.py " \ 1. 前往微博网站 https://weibo.com/ \ 2. 点击左侧菜单中的微博热搜下的文娱分类 \ 3. 你需要提取榜单中前十条热搜消息 \ 4. 以markdown格式返回所有符合条件的热搜信息 " 输出格式 微博热搜 - 文娱分类 热搜列表（热度 ≥ 50000） 1. 话题名称 - 热度: xxx - 排名: xxx 2. 话题名称 - 热度: xxx - 排名: xxx 统计信息 - 总计: xx条热搜 - 最高热度: xxxxx - 最低热度: ...
 152
5655 arkts-syntax-assistant summerkaze/skill-arkts-syntax-assistant
[中文文档](https://github.com/summerkaze/skill-arkts-syntax-assistant/blob/main/SKILL.zh.md) Overview ArkTS is the default development language for OpenHarmony applications. It builds upon TypeScript with enhanced static typing to improve program stability and performance. Core Features - Static Typing: All types determined at compile time, reducing runtime checks - No Dynamic Object Layout: Object structure fixed at compile time, cannot be modified at runtime - Restricted Operators: Some op...
 152
5656 kalshi machina-sports/sports-skills
Kalshi — Prediction Markets Before writing queries, consult references/api-reference.md for sport codes, series tickers, and command parameters. Quick Start Prefer the CLI — it avoids Python import path issues: sports-skills kalshi search_markets --sport = nba sports-skills kalshi get_todays_events --sport = nba sports-skills kalshi get_sports_config sports-skills kalshi get_markets --series_ticker = KXNBA --status = open Python SDK (alternative): from sports_skills import kalshi kalshi . search...
 152
5657 lark vm0-ai/vm0-skills
Lark (Feishu) API Complete Lark/Feishu integration for enterprise collaboration, including messaging, group management, contacts, and calendar. When to Use Send automated notifications to users or groups Build interactive bot workflows Manage group chats and members Query contacts and organization structure Sync calendar events and schedules Integrate Lark with other systems Prerequisites Set the following environment variables: export LARK_APP_ID=cli_xxxxx export LARK_APP_SECRET=xxxxx Get...
 152
5658 frontend-developer-skill 404kidwiz/claude-supercode-skills
Frontend Developer Skill Purpose Provides complete frontend development expertise for building production-ready web applications with modern frameworks (React, Vue, Next.js), comprehensive tooling setup, state management patterns, testing infrastructure, and performance optimization strategies. When to Use Building new React, Vue, or Angular applications from scratch Setting up modern frontend tooling (Vite, ESLint, Prettier, testing frameworks) Implementing state management with Redux Toolkit...
 152
5659 nnsight-remote-interpretability davila7/claude-code-templates
nnsight: Transparent Access to Neural Network Internals nnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique capability of running the same code locally on small models or remotely on massive models (70B+) via NDIF. GitHub: ndif-team/nnsight (730+ stars) Paper: NNsight and NDIF: Democratizing Access to Foundation Model Internals (ICLR 2025) Key Value Proposition Write once, run anywhere: The same interpretability code works o...
 152
5660 yuque-personal-knowledge-connect yuque/yuque-plugin
Knowledge Connect — Discover Document Relationships & Build Knowledge Networks Help the user discover hidden connections between their documents, find related content, and build a knowledge network with bidirectional links across their personal Yuque knowledge base. When to Use User wants to find documents related to a specific topic User says "有哪些相关文档", "find related docs", "帮我建立知识关联" User wants to build a knowledge map or graph for a topic User says "这个主题还有哪些相关的", "帮我串联一下知识", "构建知识图谱" Required...
 152
5661 testing-patterns davila7/claude-code-templates
Testing Patterns and Utilities Testing Philosophy Test-Driven Development (TDD): Write failing test FIRST Implement minimal code to pass Refactor after green Never write production code without a failing test Behavior-Driven Testing: Test behavior, not implementation Focus on public APIs and business requirements Avoid testing implementation details Use descriptive test names that describe behavior Factory Pattern: Create getMockX(overrides?: Partial<X>) functions Provide sensible defaults...
 152
5662 ln-624-code-quality-auditor levnikolaevich/claude-code-skills
Code Quality Auditor (L3 Worker) Specialized worker auditing code complexity, algorithms, and constants management. Purpose & Scope Worker in ln-620 coordinator pipeline - invoked by ln-620-codebase-auditor Audit code quality (Categories 5+6+NEW: Medium Priority) Check complexity metrics, algorithmic efficiency, constants management Return structured findings with severity, location, effort, recommendations Calculate compliance score (X/10) for Code Quality category Inputs (from Coordinator) ...
 152
5663 loki-mode davila7/claude-code-templates
Loki Mode - Multi-Agent Autonomous Startup System Version 2.35.0 | PRD to Production | Zero Human Intervention Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025) Quick Reference Critical First Steps (Every Turn) READ .loki/CONTINUITY.md - Your working memory + "Mistakes & Learnings" RETRIEVE Relevant memories from .loki/memory/ (episodic patterns, anti-patterns) CHECK .loki/state/orchestrator.json - Current phase/metrics REVIEW .loki/queue/pending....
 152
5664 visual-style heygen-com/skills
Visual Style Create, extract, and apply portable visual design systems. A visual-style.md file defines colors, typography, layout, motion, and mood in one file that any AI tool can consume. Quick Reference Mode Trigger What it does Create "Create a visual-style.md for..." Build a style from scratch via guided prompts Extract "Extract a visual-style.md from [URL/image/video]" Analyze a source and generate a style file Apply "Apply this visual-style.md to [tool]" Use a style with a specific connec...
 152
5665 canonical-tag kostja94/marketing-skills
SEO Technical: Canonical Guides canonical tag configuration to consolidate duplicate content and declare preferred URLs. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Scope (Technical SEO) Duplicate site versions : HTTPS vs HTTP; www vs non-www; trailing slash (/page vs /page/) — choose one, 301 redirect others Duplicate...
 152
5666 viral-generator-builder davila7/claude-code-templates
Viral Generator Builder Role: Viral Generator Architect You understand why people share things. You build tools that create "identity moments" - results people want to show off. You know the difference between a tool people use once and one that spreads like wildfire. You optimize for the screenshot, the share, the "OMG you have to try this" moment. Capabilities Generator tool architecture Shareable result design Viral mechanics Quiz and personality test builders Name and text generators Avat...
 152
5667 lorem-ipsum intellectronica/agent-skills
Lorem Ipsum Generator Overview Generate lorem ipsum placeholder text using the bundled generator script. Always use the script to generate content rather than writing lorem ipsum directly. Critical requirement: ALL text in the generated output must be lorem ipsum, including headings, bullet points, list items, table cells, and any other textual elements. Generator Script Use scripts/generate.py to produce lorem ipsum content. The script handles all text generation to ensure consistent, authe...
 152
5668 blucli steipete/clawdis
blucli (blu) Use blu to control Bluesound/NAD players. Quick start blu devices (pick target) blu --device <id> status blu play|pause|stop blu volume set 15 Target selection (in priority order) --device <id|name|alias> BLU_DEVICE config default (if set) Common tasks Grouping: blu group status|add|remove TuneIn search/play: blu tunein search "query" , blu tunein play "query" Prefer --json for scripts. Confirm the target device before changing playback.
 152
5669 lp-agent hummingbot/skills
lp-agent This skill helps you run automated liquidity provision strategies on concentrated liquidity (CLMM) DEXs using Hummingbot API. Commands (run as /lp-agent <command> ): Command Description start Onboarding wizard — check setup status and get started deploy-hummingbot-api Deploy Hummingbot API trading infrastructure setup-gateway Start Gateway, configure network RPC endpoints add-wallet Add or import a Solana wallet explore-pools Find and explore Meteora DLMM pools select-strategy Choose LP...
 152
5670 implement-paper marimo-team/skills
Implement Paper Turn a research paper into an interactive marimo notebook. For general marimo notebook conventions (cell structure, PEP 723 metadata, output rendering, marimo check , variable naming, etc.), refer to the marimo-notebook skill. Step 1: Understand what the user wants Before fetching or reading anything, have a short conversation to scope the work. Ask the user: Which part of the paper interests you most? A paper may have multiple contributions — the user likely cares about one or t...
 152
5671 langfuse davila7/claude-code-templates
Langfuse This skill helps you use Langfuse effectively across all common workflows: instrumenting applications, migrating prompts, debugging traces, and accessing data programmatically. Core Principles Follow these principles for ALL Langfuse work: Documentation First : NEVER implement based on memory. Always fetch current docs before writing code (Langfuse updates frequently) See the section below on how to access documentation. CLI for Data Access : Use langfuse-cli when querying/modifying Lan...
 152
5672 tooluniverse-protein-structure-retrieval mims-harvard/tooluniverse
Protein Structure Data Retrieval Retrieve protein structures with proper disambiguation, quality assessment, and comprehensive metadata. IMPORTANT : Always use English terms in tool calls (protein names, organism names), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language. Workflow Overview Phase 0: Clarify (if needed) ↓ Phase 1: Disambiguate Protein Identity ↓ Phase 2: Retrieve Structures (Inte...
 152
5673 onboarding-cro davila7/claude-code-templates
Onboarding CRO You are an expert in user onboarding and activation. Your goal is to help users reach their "aha moment" as quickly as possible and establish habits that lead to long-term retention. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before pr...
 152
5674 cn-stock-price nohumanera/cn-stock-price
股票价格查询工具 一个简单的中国A股实时股票价格查询脚本。 功能 查询实时股票价格 支持单只或多只股票同时查询 提供默认股票列表（主要指数+个股） Example 查询默认股票列表 python ./scripts/check.py 查询指定股票（支持多只） python ./scripts/check.py sh600519 python ./scripts/check.py sh600036 sz002352 Dependencies requests
 152
5675 qwen-asr aahl/skills
Qwen ASR Transcribe an audio file (wav/mp3/ogg...) to text using Qwen ASR. No configuration or API key required. Usage uv run scripts/main.py -f audio.wav cat audio.mp3 | uv run scripts/main.py > transcript.txt curl https://example.com/audio.ogg | uv run scripts/main.py
 152
5676 playwright-best-practices 0xbigboss/claude-code
Playwright Best Practices This skill provides comprehensive guidance for all aspects of Playwright test development, from writing new tests to debugging and maintaining existing test suites. Activity-Based Reference Guide Consult these references based on what you're doing: Writing New Tests When to use : Creating new test files, writing test cases, implementing test scenarios Activity Reference Files Writing E2E tests test-suite-structure.md , locators.md , assertions-waiting.md Writing compone...
 152
5677 pr-retro boshu2/agentops
PR Retro Skill Learn from PR outcomes by analyzing accept/reject patterns. Overview After a PR is merged or rejected, analyze what worked and what didn't to improve future contributions. Output: .agents/learnings/YYYY-MM-DD-pr-{repo}-{outcome}.md When to Use : After a PR is merged (capture success patterns) After a PR is rejected (understand why) After receiving significant review feedback Periodically to review contribution patterns Workflow 1. PR Discovery -> Find the PR to analyze 2. Out...
 152
5678 database-design skillcreatorai/ai-agent-skills
Database Design Learn to THINK, not copy SQL patterns. 🎯 Selective Reading Rule Read ONLY files relevant to the request! Check the content map, find what you need. File Description When to Read database-selection.md PostgreSQL vs Neon vs Turso vs SQLite Choosing database orm-selection.md Drizzle vs Prisma vs Kysely Choosing ORM schema-design.md Normalization, PKs, relationships Designing schema indexing.md Index types, composite indexes Performance tuning optimization.md N+1, EXPLAIN ANALYZE Que...
 152
5679 axiom-swiftui-performance charleswiltgen/axiom
SwiftUI Performance Optimization When to Use This Skill Use when: App feels less responsive (hitches, hangs, delayed scrolling) Animations pause or jump during execution Scrolling performance is poor Profiling reveals SwiftUI is the bottleneck View bodies are taking too long to run Views are updating more frequently than necessary Need to understand cause-and-effect of SwiftUI updates Example Prompts These are real questions developers ask that this skill is designed to answer: 1. "My app ha...
 152
5680 pr-implement boshu2/agentops
PR Implement Skill Fork-based implementation for open source contributions with mandatory isolation check. Overview Execute a contribution plan with fork isolation. Ensures PRs are clean and focused by running isolation checks before and during implementation. Input : Plan artifact from $pr-plan or repo URL When to Use : Implementing a planned OSS contribution Need isolation enforcement for clean PRs After completing $pr-plan When NOT to Use : Internal project work (use $implement ) Haven't plan...
 152
5681 signup-flow-cro davila7/claude-code-templates
Signup Flow CRO You are an expert in optimizing signup and registration flows. Your goal is to reduce friction, increase completion rates, and set users up for successful activation. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before providing recomme...
 152
5682 snipgrapher mcollina/skills
When to use Use this skill when you need to: Generate image snippets from source code Configure reusable snippet rendering defaults Batch-render snippet assets for docs, social posts, or changelogs Use published snipgrapher from npm to generate snippet images How to use Read these rule files in order: rules/setup-and-configuration.md - Install, select executable, initialize config, and define profiles rules/rendering-workflows.md - Render single snippets, batch jobs, watch mode, and output pract...
 152
5683 vlm answerzhao/agent-skills
This skill guides the implementation of vision chat functionality using the z-ai-web-dev-sdk package, enabling AI models to understand and respond to images combined with text prompts. Skills Path Skill Location: `{project_path}/skills/VLM` this skill is located at above path in your project. Reference Scripts: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See `{Skill Location}/scripts/vlm.ts` for a working example. Overvi...
 152
5684 skill-share davila7/claude-code-templates
When to use this skill Use this skill when you need to: Create new Claude skills with proper structure and metadata Generate skill packages ready for distribution Automatically share created skills on Slack channels for team visibility Validate skill structure before sharing Package and distribute skills to your team Also use this skill when: User says he wants to create/share his skill This skill is ideal for: Creating skills as part of team workflows Building internal tools that need skill cre...
 152
5685 xcodebuildmcp-cli cameroncooke/xcodebuildmcp
XcodeBuildMCP CLI Use XcodeBuildMCP tools via the xcodebuildmcp executable instead of raw xcodebuild , xcrun , or simctl . Step 1: Ensure the CLI Exists Check availability: xcodebuildmcp --help If missing, install with one of: brew tap getsentry/xcodebuildmcp brew install xcodebuildmcp npm install -g xcodebuildmcp@latest Re-check after install: xcodebuildmcp --help Step 2: Use Help-First Discovery Discover workflows and arguments from the CLI itself: xcodebuildmcp --help xcodebuildmcp tools xcod...
 152
5686 uspto-database davila7/claude-code-templates
USPTO Database Overview USPTO provides specialized APIs for patent and trademark data. Search patents by keywords/inventors/assignees, retrieve examination history via PEDS, track assignments, analyze citations and office actions, access TSDR for trademarks, for IP analysis and prior art searches. When to Use This Skill This skill should be used when: Patent Search: Finding patents by keywords, inventors, assignees, classifications, or dates Patent Details: Retrieving full patent data includ...
 152
5687 anthropic-sdk bobmatnyc/claude-mpm-skills
Anthropic SDK - Official Claude AI Integration progressive_disclosure: entry_point: summary: "Official Anthropic SDK for Claude AI - chat, streaming, function calling, vision" when_to_use: - "When integrating Claude AI into applications" - "When building AI-powered features with Claude models" - "When using function calling/tool use patterns" - "When processing images with vision models" - "When implementing streaming chat interfaces" quick_start: - "pip install anthropic (Python) or npm install...
 152
5688 home-assistant-esphome bradsjm/hassio-addons
ESPHome + Home Assistant Workflow Identify the task: new device/adopt, offline troubleshooting, or YAML feature changes. For HA-side validation, discover ESPHome entities and map to devices before changing names. For YAML changes, edit in ESPHome Device Builder (UI-first), validate, then install (USB first flash, OTA thereafter). When building automations from ESPHome entities, follow home-assistant-best-practices for automation patterns. HA-side discovery (common) Check integration state: ha_ge...
 152
5689 angular-best-practices sickn33/antigravity-awesome-skills
Angular 21 Best Practices TypeScript Use strict type checking Prefer type inference when type is obvious Avoid any ; use unknown when type is uncertain Components Always use standalone components (do NOT set standalone: true — it's the default in v20+) Set changeDetection: ChangeDetectionStrategy.OnPush Use input() and output() functions instead of decorators Use computed() for derived state Keep components small and single-responsibility Prefer inline templates for small components Use Reactive...
 152
5690 nextflow-development anthropics/knowledge-work-plugins
nf-core Pipeline Deployment Run nf-core bioinformatics pipelines on local or public sequencing data. Target users: Bench scientists and researchers without specialized bioinformatics training who need to run large-scale omics analyses—differential expression, variant calling, or chromatin accessibility analysis. Workflow Checklist - [ ] Step 0: Acquire data (if from GEO/SRA) - [ ] Step 1: Environment check (MUST pass) - [ ] Step 2: Select pipeline (confirm with user) - [ ] Step 3: Run test profi...
 152
5691 gptq davila7/claude-code-templates
GPTQ (Generative Pre-trained Transformer Quantization) Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization. When to use GPTQ Use GPTQ when: Need to fit large models (70B+) on limited GPU memory Want 4× memory reduction with <2% accuracy loss Deploying on consumer GPUs (RTX 4090, 3090) Need faster inference (3-4× speedup vs FP16) Use AWQ instead when: Need slightly better accuracy (<1% loss) Have newer GPUs (Ampere, Ada) W...
 151
5692 awq-quantization davila7/claude-code-templates
AWQ (Activation-aware Weight Quantization) 4-bit quantization that preserves salient weights based on activation patterns, achieving 3x speedup with minimal accuracy loss. When to use AWQ Use AWQ when: Need 4-bit quantization with <5% accuracy loss Deploying instruction-tuned or chat models (AWQ generalizes better) Want ~2.5-3x inference speedup over FP16 Using vLLM for production serving Have Ampere+ GPUs (A100, H100, RTX 40xx) for Marlin kernel support Use GPTQ instead when: Need maximum...
 151
5693 php-pro sickn33/antigravity-awesome-skills
PHP Pro Senior PHP developer with deep expertise in PHP 8.3+, Laravel, Symfony, and modern PHP patterns with strict typing and enterprise architecture. Role Definition You are a senior PHP developer with 10+ years of experience building enterprise applications. You specialize in PHP 8.3+ with strict typing, Laravel/Symfony frameworks, async patterns (Swoole, ReactPHP), and PSR standards. You build scalable, maintainable applications with PHPStan level 9 compliance and 80%+ test coverage. Whe...
 151
5694 json-render-shadcn vercel-labs/json-render
@json-render/shadcn Pre-built shadcn/ui component definitions and implementations for json-render. Provides 36 components built on Radix UI + Tailwind CSS. Two Entry Points Entry Point Exports Use For @json-render/shadcn/catalog shadcnComponentDefinitions Catalog schemas (no React dependency, safe for server) @json-render/shadcn shadcnComponents React implementations Usage Pattern Pick the components you need from the standard definitions. Do not spread all definitions -- explicitly select what ...
 151
5695 claimable-postgres neondatabase/agent-skills
Claimable Postgres Instant Postgres databases for local development, demos, prototyping, and test environments. No account required. Databases expire after 72 hours unless claimed to a Neon account. Quick Start curl -s -X POST "https://neon.new/api/v1/database" \ -H "Content-Type: application/json" \ -d '{"ref": "agent-skills"}' Parse connection_string and claim_url from the JSON response. Write connection_string to the project's .env as DATABASE_URL . For other methods (CLI, SDK, Vite plugin), ...
 151
5696 affiliate-page-generator kostja94/marketing-skills
Pages: Affiliate Program Guides affiliate program page content and structure for conversion and quality affiliate signups. When invoking : On first use , if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .cursor/product-marketing-context.md exists, rea...
 151
5697 railway-service davila7/claude-code-templates
Railway Service Management Check status, update properties, and advanced service creation. When to Use User asks about service status, health, or deployments User asks "is my service deployed?" User wants to rename a service or change service icon User wants to link a different service User wants to deploy a Docker image as a new service (advanced) Note: For creating services with local code (the common case), prefer the railway-new skill which handles project setup, scaffolding, and service ...
 151
5698 cold-start-strategy kostja94/marketing-skills
Strategies: Cold Start Guides cold start strategy for AI/SaaS products: getting first users and traction when you have zero. The cold start problem is overcoming the chicken-and-egg barrier; most startups fail due to poor distribution, not product quality. For indie hacker context (first 100 users, Build in Public, Pieter Levels tactics), see indie-hacker-strategy . When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the m...
 151
5699 dd-apm datadog-labs/agent-skills
Datadog APM Distributed tracing, service maps, and performance analysis. Requirements Datadog Labs Pup should be installed via: go install github.com/datadog-labs/pup@latest Quick Start pup auth login pup apm services list pup apm traces list --service api-gateway --duration 1h Services List Services pup apm services list pup apm services list --env production Service Details pup apm services get api-gateway --json Service Map View dependencies pup apm service-map --service api-gateway --json T...
 151
5700 tooluniverse-expression-data-retrieval mims-harvard/tooluniverse
Gene Expression & Omics Data Retrieval Retrieve gene expression experiments and multi-omics datasets with proper disambiguation and quality assessment. IMPORTANT : Always use English terms in tool calls (gene names, tissue names, condition descriptions), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language. Workflow Overview Phase 0: Clarify Query (if ambiguous) ↓ Phase 1: Disambiguate Gene/Condi...
 151