load-template
Load an AI agent instruction template into the current project. Use when you need structured instructions for a specific role like technical planning.
list-templates
List available AI agent instruction templates from the repository. Use to discover what templates can be loaded.
discover-package-skills
>
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
web-verify
Analyze code changes, derive test scenarios, and verify them on a live deployment via browser automation. Use when user wants to verify changes work in the browser, test a deployment, or says /web-verify.
maintainer-orchestrator
Coordinate recurring maintainer orchestration in Codex across the fixed /Users/mark/src repos. Use for heartbeat/control-plane work, canonical repository worker threads, cross-repo queue monitoring, decision-ready owner briefs, live-proof gates, and release gating for ai, sleephub-android, hue-ble-android, listener-ai, healthdrop, actions, and internal-skills.
a2a-agents
AI agent and chatbot patterns including personas, pipelines, and messaging integrations. Use when building conversational agents, creating AI personas, designing insight pipelines, or integrating with Slack/Kakao platforms.
issue
Create GitHub issue. Use when user asks to create issue, file bug, request feature, or says /issue.
voice-realtime
Real-time voice AI knowledge including STT and TTS providers, LiveKit Agents plugins, and voice pipeline patterns. Use when working with speech-to-text, text-to-speech, voice agents, LiveKit, or any voice-related infrastructure.
sleep-domain
Sleep science and Asleep sleep tracking knowledge. Use when working with sleep data, hypnograms, sleep stages, sleep insights, sleep metrics, or any sleepstar/agent-a/backend sleep-related code.
self-enhance
Framework for improving Claude configuration (skills, agents, commands). Use when analyzing work patterns, proposing new skills, identifying knowledge gaps, reviewing Claude setup, or when user asks to improve how Claude helps them.
wrap
Pre-commit session analysis. Triages trivial vs substantive changes, checks commit scope, and for substantive sessions proposes docs/permissions/automations updates. Use when user is finishing work, about to commit, or says /wrap.
review
Review local changes, a PR, or an issue for quality, correctness, security. Use when user asks for review, wants feedback on changes, or says /review.
ble-protocol
BLE protocol debugging -- HCI snoop capture, tshark packet analysis, GATT handle reverse engineering, SMP pairing troubleshooting. Use when debugging BLE bonding failures, analyzing BLE traffic, reverse engineering BLE device protocols, or working with Android BLE stack issues.
research
Research topics via codebase exploration or external documentation. Use when user asks to research, explore, investigate, or says /research.
react-native-patterns
React Native mobile development patterns for authentication, platform-specific issues, navigation, and SDK integration. Use when debugging React Native apps, fixing iOS/Android issues, handling auth flows, or integrating native SDKs.
commit
Prepare git commit with review. Use when user asks to commit, review changes for commit, or says /commit.
compare-standards
Compare implementation against internal standards. Use when comparing thresholds, checking compliance, or says /compare-standards.
config-bump
Atomic config change with version bump and commit. Use when updating config values, changing thresholds, or says /config-bump.
debug
Debug issues systematically, especially mobile/platform-specific. Use when user asks to debug, diagnose, troubleshoot, or says /debug.
enhance
Analyze work patterns and improve Claude configuration. Use when user asks to improve Claude setup, optimize workflow, or says /enhance.
feature-dev
Develop features end-to-end from planning to PR. Use when user asks to implement feature, build functionality, or says /feature-dev.
github-project-triage
Triage GitHub issues, pull requests, CI, releases, blockers, proof state, and next actions. Use for maintainer queue mapping, URL-first issue/PR cards, autonomous-vs-owner classification, PR readiness checks, and decision-ready briefs inside the fixed /Users/mark/src repository workflow.
pr
Create GitHub pull request. Use when user asks to create PR, open pull request, or says /pr.
pressbeat
Order guaranteed press articles for your brand. Standard ($500, DR30+) or Premium ($2,000, DR50+) with 90-day money-back guarantee. Use when the user wants PR coverage, backlinks, press articles, or media mentions.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
llms-txt-crawler
Fetch and crawl llms.txt files from websites. Parses the llms.txt format to extract page URLs and downloads all listed content. Use when you need to gather documentation or content from a website that provides an llms.txt file.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
polaris-design
Apply Shopify Polaris Design System principles to create professional admin interfaces and dashboards. Use when building React admin panels, data-heavy interfaces, e-commerce dashboards, or when optimizing existing UIs for better usability and data density. Provides color tokens, typography scales, spacing system, and component patterns following Polaris guidelines.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Codebase Safety & Exploration
Guide for safely navigating and modifying an existing codebase. Use this skill when: (1) Onboarding to a new project or context, (2) Planning complex changes that might have side effects, (3) Ensuring modifications don't break existing functionality across different languages and frameworks.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
dev-workflow
Enforces the standard development workflow for the fund-portfolio-bot project: read docs first, propose a small scoped design, respect version scope, and limit code changes. Use when implementing, modifying, or refactoring functionality in this repository.
multi-model-orchestrator
|
naming
命名规范 / Naming conventions。在创建类、函数、变量，或重命名、检查命名时使用。核心原则：简洁优先，上下文消歧义，类型提示已提供足够信息。Use when naming classes/functions/variables, renaming code, or reviewing names. Prioritizes brevity over self-documentation.
roadmap-guide
在编写、更新、维护 roadmap.md 的时候触发
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
geb-protocol
|
architecture
分层架构规范 / Architecture and layering rules (v0.3.1)。在设计新组件、修改导入、检查分层时使用。核心约束：cli → flows → data，core 向内不向外。Use when designing components, changing imports, or reviewing layering decisions. Enforces cli/flows/core/data separation.
code-flow-viz
用于梳理和可视化代码流程，生成清晰的 ASCII 流程图、数据流图和表格分析。适用于已有代码的梳理、新功能设计的说明、以及技术文档的编写。
code-style
代码风格规范 / Code style conventions。在编写、编辑、评审 Python 代码时使用。包括类型注解、Decimal 精度、Docstring、模块组织等规范。Use when writing, editing, or reviewing Python code. Enforces type hints, Decimal precision, docstrings, and module organization.
outside-in-testing-ios-apps
Test iOS apps running in Simulator from the outside in. Use PROACTIVELY when you need to verify an iOS app works, run acceptance tests, check UI behavior, perform outside-in testing, end-to-end testing, functional testing, exploratory testing, or smoke testing of iOS apps. Covers launching test flows, verifying screens, interacting with UI elements, and diagnosing failures. Triggers on: test my app, verify the app, check the UI, does this work, acceptance test, outside-in test, e2e test, functional test, smoke test, exploratory test.
agents-commands-creator
Create Claude Code agents and commands with proper markdown structure, YAML frontmatter, and plugin.json arrays. Use when creating commands, slash commands, agents, autonomous assistants, and command-line utilities for Claude Code plugins.
Page 1564 of 1699 · 84946 results
