Loading...
Loading...
Found 20,655 Skills
Expert GPU optimization for modern consumer GPUs (8-24GB VRAM). Use this skill when you need to optimize GPU training, speed up CUDA code, reduce OOM errors, tune XGBoost for GPU, migrate NumPy to CuPy, make a model faster, manage GPU memory, optimize VRAM usage, or benchmark PyTorch. Covers mixed precision, gradient checkpointing, XGBoost GPU acceleration, CuPy/cuDF migration, vectorization, torch.compile, and diagnostics. NVIDIA GPUs only. PyTorch, XGBoost, and RAPIDS frameworks.
Web content fetching and URL retrieval via curl and WebFetch — replaces the Fetch MCP server (fetch_html, fetch_json, fetch_markdown, fetch_txt). Use this skill when a specific URL is provided and the user wants its content. Covers HTTP GET/POST, JSON API consumption with jq, HTML retrieval, markdown conversion, plain text extraction, authenticated requests, redirects, cookies, and timeouts. Trigger phrases: "fetch this URL", "get the page content", "download HTML", "call this API", "curl this endpoint", "grab the JSON", "fetch markdown from", "retrieve web content", "hit this endpoint", "scrape this page", "read this URL", "pull data from API", "make an HTTP request", "extract page content", "get article text". NOT for web searches without a URL — use tavily for that.
Use this skill when you need guidance on which skill to use for any task. Recommends the perfect skill, creates skill combinations, and helps you discover capabilities you didn't know you had.
MCP skill for linear. Provides 31 tools: get_attachment, create_attachment, delete_attachment, list_comments, save_comment, delete_comment, list_cycles, get_document, list_documents, create_document, update_document, extract_images, get_issue, list_issues, save_issue, list_issue_statuses, get_issue_status, list_issue_labels, create_issue_label, list_projects, get_project, save_project, list_project_labels, list_milestones, get_milestone, save_milestone, list_teams, get_team, list_users, get_user, search_documentation
Use skill if you are testing a skill's instructional quality by following its workflow literally on a real task, documenting friction points, and fixing ambiguities.
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
Use when creating cloud sandboxes (microVMs) to run code, start dev servers, and generate live preview URLs. Also covers deploying AI agents, MCP servers, batch jobs, and Agent Drives (shared filesystems) on Blaxel's serverless infrastructure. Reach for this skill when you need isolated compute environments, real-time app previews, shared file storage across sandboxes, or to deploy agentic workloads.
This skill should be used when the user asks to "validate FHIR resources", "check HL7 messages", "validate healthcare data format", "parse FHIR", "HL7 v2 messages", "FHIR R5 validation", "CDA documents", "healthcare data interchange", "FHIR resource schema", "HL7 specifications", or mentions FHIR validation, HL7 message parsing, CDA validation, healthcare data format compliance, or Fast Healthcare Interoperability Resources standards.
Two-way integration channel between Feishu (Lark/Feishu) and OpenClaw. It implements message receiving and sending through Feishu bot, supporting private chat, group chat, @mention detection, card messages, and file transfer. This skill is used when you need to interact with AI assistants via Feishu, receive Feishu messages to trigger AI responses, or send messages from OpenClaw to Feishu. Difference from feishu-automation: this skill focuses on message channel integration, while feishu-automation focuses on automated operations of Feishu platform (such as multidimensional tables, documents, etc.)
DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.
Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.
Interact with Jira and Confluence via the `acli` CLI tool (Atlassian CLI). Use this skill whenever the user wants to manage Jira work items (create, edit, transition, search, comment, assign, bulk ops), manage sprints or boards, list/view Jira projects, or work with Confluence pages, blogs, and spaces — all from the terminal without opening a browser. Also trigger when the user says things like "ดู issue ของฉัน", "transition ไป In Progress", "สร้าง bug ใน Jira", "search ด้วย JQL", "ดู sprint ปัจจุบัน", "bulk transition", "ดู Confluence page", หรือ อะไรก็ตามที่ต้องการโต้ตอบกับ Atlassian products ผ่าน command line. Always use `acli` via the Bash tool — never use the Atlassian MCP for tasks this skill covers.