tomevault-io/skills-registry - 第 128 页

git-workflow

Git best practices, branching strategies, commit conventions, and code review patterns Use when this capability is needed.

原文语言：英语

ios-swift-patterns

SwiftUI, UIKit, MVVM, Combine, async/await, Core Data, and App Store submission patterns Use when this capability is needed.

原文语言：英语

kubernetes-patterns

Pods, deployments, services, ingress, RBAC, autoscaling, and production cluster best practices Use when this capability is needed.

原文语言：英语

terraform-iac

State management, modules, workspaces, remote backends, and multi-environment strategies Use when this capability is needed.

原文语言：英语

ios-development

iOS/Swift development: SwiftUI, UIKit, Core Data, Xcode builds, simulator management, code signing, and App Store submission. Use when this capability is needed.

原文语言：英语

ai-agent-engineer

Specialist skill for AI agent engineering in the IdeaFlow codebase. Use when (1) improving agent configurations (CMZ.json, oh-my-opencode.json), (2) creating or modifying agent skills, (3) enhancing agent orchestration patterns, (4) implementing self-*…

原文语言：英语

ai-agent-engineer

AI Agent Engineering best practices for OpenX Basefly. Use when working on branch 'ai-agent-engineer', improving agent configurations, skills, or multi-model orchestration. Triggers: agent configuration changes, skill creation/updates, model selection…

原文语言：英语

concise-default

Use when the user wants concise mode to be the default for every new chat across Codex CLI, Claude Code, and Cursor. Triggers on "concise default", "default concise", "make concise the default", "concise-default on", "concise-default off", "concise-default…

原文语言：英语

mcp-server-go

Authoritative reference for building MCP (Model Context Protocol) servers in Go using the official Anthropic+Google SDK. Load when building or modifying an MCP server in this repo (currently `projects/pg-ai-stewards/cmd/stewards-mcp/`). Captures protocol…

原文语言：英语

review

| Use when this capability is needed.

原文语言：英语

create-pr

Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected services. Triggers: "create PR", "open pull request", "push the code", "ready for review Use when this capability is needed.

原文语言：英语

mcp-headless-test

Run live tests of the Ariadne MCP server using Claude Code in headless mode. Tests tool discovery, invocation, and filtering. Use when validating MCP server changes or checking integration with Claude Code. Use when this capability is needed.

原文语言：英语

create-copilot-instructions

Create a new domain-specific instruction file when current coverage gaps require file-scoped guidance Use when this capability is needed.

原文语言：英语

sp-coding-agent

Use when a coding task is vague or under-specified. Extracts missing context across 9 code-native categories before the agent executes file changes. Designed for OpenAI Codex, Anthropic Claude Code, and Google Gemini Code Assist.

原文语言：英语

langchain-agents-deepagents-code

Use when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing extra middlewares (retries, fallbacks, HITL) on top.

原文语言：英语

langchain-agents-deploy

Use when productionising or deploying a LangChain / LangGraph / DeepAgents agent. Covers durable execution (checkpointers, thread_id), the production middleware stack, three deploy targets (LangSmith Cloud, Cloud Run, Docker), secrets, scaling, and…

原文语言：英语

langchain-agents-langchain-code

Use when editing a non-agentic LCEL pipeline — composing Runnables, retrievers, embeddings, chat models, parsers, or building a RAG chain. For agents (LLM + tools loop), use the middleware skill instead.

原文语言：英语

langchain-agents-langgraph-code

Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need explicit StateGraph control (multi-graph workflows, custom routing, non-standard state schemas, parallel branches). For the common case, use…

原文语言：英语

langchain-agents-langsmith-evals

Use when authoring eval datasets, writing evaluators, running evals against a LangChain / LangGraph / DeepAgents project, comparing eval results between runs, or writing unit/integration tests for an agent.

原文语言：英语

langchain-agents-middleware

Use when building or productionising any agent — adding retries, fallbacks, summarization, human-in-the-loop, PII redaction, call limits, or custom hooks. Middleware is THE composition primitive for modern LangChain agents (v1+); covers built-ins plus the…

原文语言：英语

langchain-agents-observability

Use when debugging an agent's behaviour, reading LangSmith traces, setting up tracing in production (LangSmith + OpenTelemetry), wiring distributed tracing across services, or diagnosing common failure modes.

原文语言：英语

langchain-agents-scaffold

Use when creating a new LangChain / LangGraph / DeepAgents project from scratch. Picks the right scaffolder for graphs vs. DeepAgents vs. LCEL chains.

原文语言：英语

langchain-agents-workflow

Use when starting work on any LangChain / LangGraph / DeepAgents project. Entry point for the develop -> middleware -> evaluate -> deploy lifecycle, mapping each step to the right official tool.

原文语言：英语

github-pr-stats

Compute PR statistics (total, merged, closed, avg merge time, top contributor) from GitHub API data using Python or jq. Use when this capability is needed.

原文语言：英语

github-repo-stats

> Use when this capability is needed.

原文语言：英语

release-and-publish

> Use when this capability is needed.

原文语言：英语

release-and-publish

> Use when this capability is needed.

原文语言：英语

retrospect

This skill reviews the current chat session and GitHub Copilot instructions to identify user-reported issues that should become new lessons, detect violations of existing instructions, and update instructions accordingly to prevent future mistakes. Use when…

原文语言：英语

sqlmodel

Build SQL database integrations with SQLModel for FastAPI projects. Use when working with databases in Python, defining ORM models, creating CRUD operations, managing sessions, or integrating SQL databases with FastAPI. SQLModel combines Pydantic v2 and…

原文语言：英语

atomic-commit

Atomic git workflow - validates, commits, pushes, creates PR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure. Use when this capability is needed.

原文语言：英语

database-schema-migrations

> Use when this capability is needed.

原文语言：英语

atomic-commit

Atomic git workflow - validates, commits, pushes, creates PR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure. Use when this capability is needed.

原文语言：英语

documentation-standards

>- Use when this capability is needed.

原文语言：英语

op1-marketing-seo-experiment-stage1

Run and audit OperatorOne Stage1 marketing SEO shadow experiments across input sync, context index, keyword graph, experiment synthesis, and Ready/Hold/Drop queueing. Use when asked to run SEO experiments, execute 1/2/3 validation rounds, verify…

原文语言：英语

agent-eval

Reproducible evaluation harness for coding agents, prompts, and skills — head-to-head comparison with pass rate, cost, time, and consistency metrics captured in git worktrees. Use when comparing coding agents (Claude Code, Aider, Codex), regression-testing…

原文语言：英语

swift-ios-development

>- Use when this capability is needed.

原文语言：英语

claude-code-team

Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegram). Use when this capability is needed.

原文语言：英语

mediamtx-docs

> Use when this capability is needed.

原文语言：英语

agent-instructions

Creates or updates an AGENTS.md file for the current repository, or converts existing agent/copilot instruction files into AGENTS.md. Use when asked to "add agent instructions", "create an AGENTS.md", "set up agent context", "convert copilot instructions to…

原文语言：英语

documentation-from-code

Generate documentation from source code including README, API docs, and inline comments Use when this capability is needed.

原文语言：英语