next-task
4. Next task
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Agents & models
25,432 results
knowledge-compiler
Compiles personal books, PDF/EPUB/TXT/Markdown and long materials into an applied Claude Code skill with a source map, decision rules, playbooks,…
mindspeed-llm-env-setup
MindSpeed-LLM environment setup guide for Huawei Ascend NPU. Covers CANN environment activation, PyTorch + torch_npu installation, MindSpeed acceleration library installation, Megatron-LM core module integration, MindSpeed-LLM installation, and environment verification. When users need to set up MindSpeed-LLM on Ascend NPU...
mindspeed-llm-pipeline
MindSpeed-LLM end-to-end training deployment pipeline for Huawei Ascend NPU. It connects the complete process of environment setup, data preprocessing, weight conversion, distributed training, inference validation, evaluation, and weight export. It covers parameter consistency checks, data flow between stages, and model-specific configurations (Qwen, LLaMA, DeepSeek). Users need to complete MindSpeed-LLM on Ascend NPU...
mindspeed-llm-training
MindSpeed-LLM distributed training launch guide for Huawei Ascend NPU. Covers training launch configurations for pretraining, instruction fine-tuning (Full/LoRA/QLoRA), and preference alignment (DPO), including entry script selection, parallel strategies (TP/PP/CP), training parameters, and optional evaluation. Use when the user needs to launch a MindSpeed-LLM training task on Ascend NPU.
mindspeed-llm-weight-prep
MindSpeed-LLM weight conversion guide for Huawei Ascend NPU. Covers HuggingFace to Megatron format conversion, Megatron to HuggingFace reverse conversion, LoRA weight merging and export, and TP/PP/EP parallel sharding configuration. Supports v1 and v2 converters, suitable for…
analyse-coverage
Analyze test coverage blind spots and generate a coverage analysis report
coverage
Use when working with coverage
run-mindspeed-llm-test
Run test cases for the MindSpeed-LLM project. Invoke this skill when test cases need to be run or project code coverage needs to be scanned.
claude-in-chrome
Automates your Chrome browser to interact with web pages - clicking elements, filling forms, capturing screenshots, reading console logs, and navigating sites.…
doctor
Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data…
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify ~/.claude/keybindings.json. Examples: "rebind ctrl+s", "add…
loop
Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.
ideate
Timeboxed ideation on a topic using propose-and-critique subagent pairs. Use when the user wants to brainstorm, explore ideas, discover features, generate…
prompt-optimizer
Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using…
bmad-taskmaster-mcp-bootstrap
Bootstraps the TaskMaster MCP server and aligns it with BMAD hooks.
camino-parking-finder
Locate parking garages, lots, and street parking near your destination using Camino AI's location intelligence with AI-powered ranking.
sglang-sota-performance
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label…
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
perplexity-search
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web…
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an…
context-optimization
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency,…