email-guidelines
>
bash-style-guide
>
agentic-architecture
>
email-classifier
>
prompt-agent-cli-wrappers-guidelines
Guidelines and instructions on how to run prompts using specific models via agent CLI wrappers like Antigravity (agy) and OpenCode (opencode).
username-generation
>-
youtube
Extract transcripts and metadata from YouTube videos, or list videos from channels and playlists. Use this skill whenever the user provides a YouTube URL and wants to understand its content, get a summary, or browse a channel's video history.
zsh-style-guide
>
custom-linter
Custom workspace skill for linting test functions and type annotations.
prompt-audit-guidelines
Audits existing skills, agents, and subagents to recommend whether they should be combined, split, or refactored into references, scripts, or templates based on a cognitive boundaries matrix.
prompt-scheduler-guidelines
Design, register, and maintain user-space scheduled tasks across macOS and Linux dotfiles environments. Includes safety guidelines, logging standards, and systemd/launchd service templates.
prompt-skills-guidelines
Standards and procedures for engineering skills, scripts, and agentic workflows optimized for the Gemini CLI and LLM consumption. Use this skill whenever you are tasked with creating a new skill, optimizing existing tool outputs, or designing agent-to-agent communication protocols. It mandates token-efficient scripting (the --raw pattern) and strictly neutral, non-paraphrasing behavioral standards.
technical-review-guidelines
Guidelines for writing high-quality technical reviews. Use this skill whenever you are asked to review code, PRs, architecture designs, or technical documentation. It mandates a specific structure for findings, a neutral tone, precise location references, and strictly defined commentary constraints.
pm-ticket-writing
How to write clear, actionable Jira tickets, GitHub issues, and project management tasks. Use this skill whenever the user asks to create a ticket, write a task, draft a Jira issue, or needs to break down work into tickets. This skill ensures tickets are concise yet provide all necessary information for developers to execute the work.
prompt-review-guidelines
Guidelines for performing highly critical, fact-based reviews. Use this skill whenever you are asked to review an implementation plan, architectural design, technical proposal, or any other document. It mandates a rigorous, critical approach that relies strictly on verified facts.
prompt-engineering
>
prompt-antigravity-agents-guidelines
Guidelines and procedures for creating, configuring, and testing custom agents in Google Antigravity. Covers declarative Markdown (.md) agents, plugin-defined JSON agents, capabilities configuration (allowed tools, skills, MCPs, bash commands), and runtime isolation modes. Use this skill whenever you are designing a new custom agent, setting up permissions, or writing configurations for Antigravity-run subagents.
github-issues
Create, update, query, and comment on GitHub issues using the gh CLI. Use this skill whenever the user wants to file a bug report, create a feature request, update an existing issue, search or list issues, read issue comments, add labels/milestones, or interact with GitHub issues in any way. Also trigger when the user mentions "open an issue", "file a bug", "update issue \#X", "list issues", "check my issues", "add a comment to issue", "close issue", "label issue", or discusses GitHub issue workflows — even if they don't explicitly say "GitHub issue". If the user is working in a git repository and mentions tracking work, reporting bugs, or requesting features, this skill likely applies.
github-pull-requests
>
github-review-orchestrator
Orchestrate non-invasive code reviews with a user-centric selection process and descriptive feedback standards. Use this skill whenever the user asks to review pull requests (PRs), find stale PRs, or needs to provide high-quality code review comments on GitHub. It ensures you remain on the current branch without checking out remote code, using 'gh' CLI for all inspections.
html-to-markdown
>
jira-tasks
>-
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.
aws-cli
Use when interacting with AWS - managing S3, EC2, Lambda, IAM, CloudFormation, ECS/EKS, RDS, DynamoDB, CloudWatch, or any AWS service
jira-cli
Use when querying or automating Jira - sprints, issues, epics, stories, boards, or correlating Jira data with external systems
gh-cli
Use when interacting with GitHub - searching for repos/orgs/packages, exploring codebases, finding projects to use, querying branches/PRs/issues/releases/workflows, automating GitHub operations, or when users mention GitHub organizations or repositories
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
ubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
mdc
Use the `mdc` CLI to publish local Markdown files to Confluence and fetch/pull Confluence pages back into Markdown files. Use when the user asks to publish, update, sync, pull, fetch, or create Confluence pages from markdown, including shorthand like "Publish this KDR".
create-product-agent-playwright-tests
Create or update Playwright end-to-end tests for the Product Agents frontend in this repo, especially for settings validation, conversation artifact visibility, research plan approval/rejection, and clarifying-question flows. Use when asked to write, expand, or run Playwright tests for frontend/product-agent (including live E2E runs gated by E2E_LIVE).
gemini-review
This skill orchestrates code review and plan validation using Google Gemini CLI. It should be used when users want to validate implementation plans, review completed code, or discuss architecture decisions with Gemini as a second opinion. Supports FastAPI, Next.js, and general tech stacks with specialized checklists. Uses gemini-3-pro-preview model with free tier (60 req/min, 1000 req/day).
zed-editor
Zed Editorの特徴、ACP（Agent Client Protocol）の仕様、AI統合、パフォーマンス特性、設定方法について包括的な知識を提供します。Zed Editorに関する質問、ACP対応エージェントの統合、設定のカスタマイズが必要な場合に使用してください。
mcp-builder
LLMが外部サービスと対話するための適切に設計されたツールを通じて、高品質なMCP (Model Context Protocol) サーバーを作成するためのガイド。Python (FastMCP)、Node/TypeScript (MCP SDK)、Rust (Tokio)で、外部APIやサービスを統合するMCPサーバーを構築する際に使用します。
distributed-claude-sender
Send prompts to a remote Claude instance on a VPS for distributed AI collaboration, different model backends, or independent context.
propose-change
Propose code changes to the supervisor Claude. Generate diffs and rationale, but do not execute. Wait for supervisor approval.
distributed-claude-receiver
You are a remote Claude instance running on a VPS. Receive messages via chat.sh wrapper, maintain persistent context, use Z.ai GLM backend via Doppler.
self-improve
Self-Improvement Loop - Analyzes performance and proposes improvements to the system prompt and codebase
rollinggo-hotel-booking
RollingGo Hotel Search & Booking Assistant. Implements the full hotel booking workflow by calling RollingGo hotel APIs. Supported scenarios: ① Search hotels by city, attraction, metro, airport, etc. ② Filter by star rating, budget, tags (pool, breakfast, family, pet-friendly) ③ Query real-time room types and prices for specific hotels ④ Compare multiple hotels ⑤ Guide users to complete booking. Triggers: Find a hotel, book a hotel, search hotels, hotel recommendation, hotel queries, nearby hotels, five-star hotels, homestays, resorts, check prices, check room types, check-in, where to stay, accommodation, rollinggo, travel accommodation, business trip accommodation, family hotels, hotels with a pool, hotels with breakfast.
hotel-core
[DEPRECATED & MERGED] This skill has been migrated to the new booking skill rollinggo-hotel-booking. During installation, please select rollinggo-hotel-booking. Triggering this skill will guide users to migrate.
rollinggo-hotel-booking
RollingGo Hotel Search & Booking Assistant. Implements the full hotel booking workflow by calling RollingGo hotel APIs. Supported scenarios: ① Search hotels by city, attraction, metro, airport, etc. ② Filter by star rating, budget, tags (pool, breakfast, family, pet-friendly) ③ Query real-time room types and prices for specific hotels ④ Compare multiple hotels ⑤ Guide users to complete booking. Triggers: Find a hotel, book a hotel, search hotels, hotel recommendation, hotel queries, nearby hotels, five-star hotels, homestays, resorts, check prices, check room types, check-in, where to stay, accommodation, rollinggo, travel accommodation, business trip accommodation, family hotels, hotels with a pool, hotels with breakfast.
hotel-core
[DEPRECATED & MERGED] This skill has been migrated to the new booking skill rollinggo-hotel-booking. During installation, please select rollinggo-hotel-booking. Triggering this skill will guide users to migrate.
tavily-web
Web research skill using Tavily API for search, extract, crawl, map, and structured research tasks. Use when you need latest information, extract content from URLs, or discover site structure. Triggers: tavily, web search, search web, latest info, extract, crawl, map, research, 搜索网页, 查资料, 最新
context-engine
Codebase search and context retrieval for any programming language. Hybrid semantic/lexical search with neural reranking. Use for code lookup, finding implementations, understanding codebases, Q&A grounded in source code, and persistent memory across sessions.
deno-deploy
Deno Deploy deployment workflows - use when user says "deploy to deno deploy", "push to deno deploy", "ship to deno deploy", or asks about deploying Deno apps to Deno Deploy
deno-frontend
Use when building web UIs with Fresh framework, using Preact components, or adding Tailwind CSS styling in Deno
deno-guidance
Use when starting any Deno project, choosing packages, configuring deno.json, or running CLI commands
Page 1355 of 1713 · 85631 results
