hass-builder
A skill to build and manage Home Assistant configurations. Use when using the Home Assistant Builder (`hab`) CLI to inspect, create, update, delete, operate, or troubleshoot Home Assistant resources; when a user mentions hab, Home Assistant CLI automation, Lovelace/dashboard edits, helpers, automations, scripts, backups, ESPHome, or Home Assistant operations from a terminal.
maishou
商品价格全网对比技能，获取商品在淘宝(Taobao)、天猫(TMall)、京东(JD.com)、拼多多(PinDuoDuo)、抖音(Douyin)、快手(KaiShou)的最优价格、优惠券，当用户想购物或者获取优惠信息时使用。Get the best price, coupons for goods on Chinese e-commerce platforms, compare product prices, and use when users want to shop or get discount information.
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
mcp-duckgo
Skills for web search and content scraping via DuckDuckGo MCP Server. Used when users need online searching and web scraping.
mcp-hass
The skill for control Home Assistant smart home devices and query states using MCP protocol.
mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
mcp-vods
用于追剧/追番的技能，为AI提供搜索影视播放地址的能力，并支持在小米电视上直接播放。当用户想搜索影视、动漫、短剧、综艺等节目信息或更新进度时使用此技能。
qwen-asr
Transcribe audio files using Qwen ASR. Use when the user sends voice messages and wants them converted to text.
tianqi
查询中国地区的天气预报，支持15天及逐小时预报、各种生活指数
zai-tts
Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.
implement-type-annotations
Add comprehensive type hints to Python/TypeScript code to improve IDE support, catch errors early, and enable better AI code understanding
setup-claude-md
Create comprehensive CLAUDE.md files with tech stack, standard commands, repository structure, and boundaries to optimize repositories for AI-assisted development
adr-plan
Analyze a task and produce an Architecture Decision Record with implementation steps.
coverage-report
Generate a .NET code coverage report scoped to files changed in the current branch. Runs tests with coverage collection and produces filtered HTML reports.
dotnet-analyzers
Run dotnet format to fix code style and analyzer diagnostics (IDE0005, CA*, SA*). Use when fixing unnecessary usings, code style violations, analyzer warnings, or verifying format compliance
dotnet-dependency
This skill should be used when investigating .NET project dependencies, understanding why packages are included, listing references, or auditing for outdated/vulnerable packages.
dotnet-inspect
Query .NET APIs across NuGet packages, platform libraries, and local files. Search for types, list API surfaces, compare and diff versions, find extension methods and implementors. Use whenever you need to answer questions about .NET library contents.
dotnet-run-file
Run script-like CSharp programs using dotnet run file.cs. Use this skill when users want to execute CSharp code directly, write one-liner scripts via stdin, or learn about run file directives.
dotnet-test
This skill should be used when running .NET tests selectively with a build-first, test-targeted workflow. Use it for running tests with xUnit focus.
dotnet-verify
This skill should be used when working with Verify snapshot tests in .NET projects. Use when updating verified snapshots after intentional code changes, accepting new snapshots, discovering verify tests, or troubleshooting snapshot mismatches. Trigger phrases include "verify tests", "update snapshots", "accept snapshots", "verified files", ".verified.txt".
elasticsearch
>
git-worktree
This skill should be used when the user wants to manage Git worktrees - creating worktrees from local or remote branches, listing active worktrees with details, deleting worktrees, or switching between worktrees. Ideal for working on multiple branches simultaneously without stashing changes.
glab
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
handbook-discover
This skill should be used when users want to discover, browse, or audit cc-handbook marketplace plugins. Shows all available plugins with installation status, versions, and component breakdown (skills, agents, commands, MCP/LSP servers, hooks). Trigger phrases include "discover plugins", "list handbook plugins", "what plugins are available", "browse marketplace".
ilspy-decompile
Understand implementation details of .NET code by decompiling assemblies. Use when you want to see how a .NET API works internally, inspect NuGet package source, view framework implementation, or understand compiled .NET binaries.
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation request.
nano-banana-prompting
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.
reflect
Analyze a Claude Code session for "wrong-turn" moments (corrections, retries, waste, reversals, dead-ends) and produce an interactive HTML dashboard with copy-able recommendations (CLAUDE.md rules, docs, scripts, hooks, memory entries, sub-skills, etc.) that would help future agents reach the goal faster. Defaults to reflecting on the current in-context session; optionally accepts a session ID or JSONL path. Use when the user invokes /reflect or asks to learn from this session.
reflect-solution
Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool calls or debugging detours. Defaults to the current in-context session; optionally accepts a session ID or JSONL path. Renders directly in the reflect aesthetic — no delegation. Use when the user invokes /reflect-solution or asks for a recap deck of what changed.
reflect-tree
Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections, retries, reversals, and backtracking. Sibling to /reflect (which produces an incidents+recommendations dashboard); this one shows the journey itself. Defaults to the current in-context session; optionally accepts a session ID or JSONL path. Use when the user invokes /reflect-tree or asks to map a session as a tree/graph/journey.
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
spec-driven
Guide spec-driven development workflow (Requirements → Design → Tasks → Implementation) with approval gates between phases. Use when user wants structured feature planning or says "use spec-driven" or "follow the spec process".
structured-plan-mode
This skill should be used when planning and tracking complex feature implementations that require systematic task decomposition. Use this skill to break down large features into manageable, well-documented tasks with clear dependencies, action items, and success criteria. The skill provides a structured template and methodology for iterative planning and tracking throughout implementation.
subagent-review
Review changed code for reuse, quality, and efficiency using three parallel disposable subagents. This skill should be used when the user says "review", "simplify", "code review", or wants a one-shot code review without persistent reviewers.
team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after review.
team-stack
Analyze a task, propose an agent team composition with roles and responsibilities, and create the team after user confirmation. Use when the user says "team stack", "create a team", "set up agents for this", or describes a complex task that would benefit from multiple agents working together.
update-component-reference
This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.
version-bump
This skill automates version bumping during the release process for the Claude Code Handbook monorepo. It should be used when the user requests to bump versions, prepare a release, or increment version numbers across the repository.
visual-explainer
Generate self-contained HTML pages that visually explain technical material — systems, code changes, plans, data. Use when the user asks for any diagram or visual explanation, when they want a slide deck or a longform document (user guide, how-to, reference page), when another skill needs one rendered, or proactively in place of a terminal ASCII table (4+ rows or 3+ columns).
add-time-space
Add standardized Javadoc time and space complexity comments to LeetCode Java solutions. Use when a directory under leetcode_java/ needs its `time = O(...)` / `space = O(...)` annotations added, normalised from inline comments, or filled in by hand where the script could not infer them.
code-refactor-master
Code refactoring expert for improving code quality, readability, maintainability, and performance. Specializes in Java and Python refactoring patterns, eliminating code smells, and applying clean code principles. Use when refactoring code, improving existing implementations, or cleaning up technical debt.
l3-core
Report where the L3 core set stands and pick the next problems to drill from it. The set is Blind 75 plus the NeetCode 150 problems README marks MUST — 99 problems, held fixed in data/l3_core.json so its ok share means something month to month — and the verdict for each is the latest annotation in data/progress.txt, not README's status column. Use when asked what to practise today, how ready the core set is, how many of Blind 75 are solid, which problems keep coming back, or to refresh the set after a MUST marker or a list changed. Triggers - "/l3-core", "/l3-core next 5", "what should I drill today?", "how is the core set looking?", "which Blind 75 are still again?", "refresh the l3 core list".
lc-again
Move a problem's README status cell after a re-solve — promote AGAIN to OK when it was genuinely re-derived unaided, add a review pass when it was not, or demote OK back to AGAIN when a solid problem comes back. Keeps the trailing `*` run, which is the recorded pass count that the cost curve and the review planner both read, and refreshes data/again_problems.txt. Use when asked to mark a problem solid, to graduate an AGAIN marker, to record another failed pass, or to update the status column after drilling something. Triggers - "I finally got 128, mark it OK", "/lc-again 139", "promote 1143 to OK", "560 came back again", "refresh the again list".
lc-algo-demo
Add or edit an algorithm visualizer under algo_demo/ against the shared contract the other 36 pages already obey — colours read from the VIZ palette and never hardcoded, no re-implementation of the devicePixelRatio canvas wrapper, the step trace written in the three shapes createLogger renders as structure, the trace in its own full-width panel below the canvas, and `draw = VIZ.repaintable(draw)` for any draw() that takes arguments. Use when asked to add a visualizer, animate an algorithm, build a demo page, or change something that should look the same on every visualizer. Triggers - "add a visualizer for Dijkstra", "/lc-algo-demo trie", "animate the sliding window", "the trace is unreadable on the segment tree page".
lc-cheatsheet
File a LeetCode problem into the cheatsheets under doc/cheatsheet/ the way the existing sections are written — find the sheet whose Scope line owns the topic, file it under the pattern it belongs to (a worked example, a variation on an existing template, a new pattern section, or a new sheet), smoke-test every snippet, fix the heading anchors the edit moved, and re-translate the 中文 sections it invalidated. Use when asked to add or update a cheatsheet, to document a pattern just learned, to add an LC example or a template variation to a sheet, or to start a new cheatsheet. Triggers - "add LC 1650 to binary_tree as a variation", "/lc-cheatsheet 239 into sliding_window", "document the monotonic stack pattern", "update the LCA part of the binary tree cheatsheet".
lc-coach
FAANG coding-interview coach. Scores a solution the way an interviewer does on the six-point scale (SH/H/LH/LNH/NH/SNH), writes the debrief packet from the interviewer's side of the table, teaches the DSA fundamentals underneath, dry-runs code out loud, names the one line that blocks the optimal complexity, and recommends the sibling problems to drill next. Use when preparing for or debriefing a LeetCode-style SWE interview — "review my solution", "would this pass?", "what's my verdict?", "how would an interviewer see this?", "why is this O(n^2)?", "mock interview me", "what should I do after LC 239?".
lc-discussion
Search recent LeetCode Discuss posts (leetcode.com/discuss/) by keyword — a company, a level, a round — read the ones that describe real interview questions, map each question to an LC number, check every one against README and the practice log, and write the result as a 繁體中文 summary doc under doc/ws/. Use when asked what a company has been asking lately, to scan LC discuss for interview experiences, to turn recent posts into a drill list, or to summarise discussion threads into a doc. Triggers - "/lc-discussion google", "/lc-discussion meta e4 --days 30", "scan LC discuss for recent Google L3 questions", "what is Amazon asking lately?", "summarise the latest interview posts into a doc".
lc-faq-add
File an interview question and answer into doc/faq/ in the shape the other 49 FAQs use — the sheet its Scope line owns, the numbered section it belongs under, tagged code fences — and write the matching 繁體中文 overlay section in the same pass, because that tree is 100% translated and a new English answer leaves a hole the moment it lands. Use when asked to add an FAQ entry, document an interview question, answer a backend/Java/SQL/Kafka question into the notes, or start a new FAQ file. Triggers - "add a question about virtual threads to the java FAQ", "/lc-faq-add kafka rebalancing", "document this interview question", "start a FAQ for gRPC".
lc-java
File a LeetCode **Java** solution into this repo the way the existing ones are filed — put it in the package its pattern owns, write the file-level javadoc header (`<number>. <Title>` then difficulty then the statement), mark the solution blocks `// V0` / `// V0-1` / `// V1-1` so the markers match the method names, add the `time =` / `space =` javadoc, compile and run it, write every block as the standard, readable approach with explanatory comments and no clever syntactic sugar, file each other good approach as `// V1`, `// V2`, …, then add the `[Java]` link to the README row the problem already has. Use when asked to "add LC <number> in Java", to file a draft out of `ws/Workspace26.java`, to port an existing Python solution to Java, or to close part of the Java coverage gap. Triggers - "add LC 25 to LinkedList in java", "/lc-java 239 SlideWindow", "file my workspace draft", "port LC 207 to java".
lc-log
Append today's practice session to data/progress.txt — the daily log that is the only source for the review plan. Writes the day's line in the log's own shape (the YYYYMMDD date, the bucket labels, the `|` session separators), carries forward the buckets still open from yesterday, and gets the annotations right, because `again` / `again!!!` / `ok` / `ok*` / `todo` are what the whole spaced-repetition schedule keys on. Use when asked to log practice, record what was solved today, update the progress file, or mark a problem as done or still shaky. Triggers - "log today's practice", "/lc-log 23 ok, 24 again!!", "record that I did 141 and 142 clean", "update progress".
Page 540 of 1707 · 85303 results
