LLM 與 Agent

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.

Expert PM validation for increment closure with 3-gate quality checks (tasks, tests, documentation). Acts as final quality gate before closing increments. Validates task completion, test coverage, documentation updates, and detects scope creep. Activates for /done command, increment closure, close increment, validate increment, completion check, quality gate, PM approval, ready to close, scope creep detection, release validation, increment validation.

Instant status commands that bypass LLM processing. Execute scripts directly for /sw:status, /sw:progress, /sw:jobs. Activates for specweave status, specweave progress, specweave jobs, increment status, show status, show progress, background jobs, job status.

Node.js/TypeScript backend developer. Builds Express.js, Fastify, NestJS APIs with Prisma ORM, TypeORM, Mongoose. Implements REST APIs, GraphQL, authentication (JWT, session, OAuth), authorization, database operations, background jobs, WebSockets, real-time features, API validation, error handling, middleware. Activates for: Node.js, NodeJS, Express, Fastify, NestJS, TypeScript backend, API, REST API, GraphQL, Prisma, TypeORM, Mongoose, MongoDB, PostgreSQL with Node, MySQL with Node, authentication backend, JWT, passport.js, bcrypt, async/await, promises, middleware, error handling, validation, Zod, class-validator, background jobs, Bull, BullMQ, Redis, WebSocket, Socket.io, real-time.

Creates and refines Claude agent skills following best practices. Use when creating new skills, improving existing ones, or learning about skill structure and conventions.

AI-powered visual content generation for Salesforce development. Generates ERD diagrams, LWC mockups, architecture visuals using Nano Banana Pro. Also provides Gemini as a parallel sub-agent for code review and research.

Update CLAUDE.md and AGENTS.md instruction files with smart merge. Preserves user customizations while updating SpecWeave sections. Use after plugin refresh, version upgrade, or when instruction files need sync. Activates for: update instructions, refresh claude.md, merge agents.md, sync instruction files, upgrade specweave config.

Expert knowledge of cloud provider pricing models for AWS, Azure, GCP covering compute, storage, database, networking, and serverless services. Includes 2025 pricing data, regional differences, free tiers, pricing calculators, and cost comparison across providers. Activates for cloud pricing, how much does it cost, price comparison, AWS vs Azure vs GCP pricing, pricing calculator, estimate costs, regional pricing, free tier, what's cheaper.

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.

Generate configuration reference documentation from conclaude-schema.json using src/bin/generate-docs.rs.USE WHEN the schema file changes, configuration options are added/modified, or documentation needs to be regenerated for the website.

Check Zed editor logs for banjo/agent errors. Use when user says "check zed logs", "zed errors", or "what's the zed error".

Creates Agentforce agents using Agent Script syntax with 100-point scoring. Use when building AI agents, defining topics and actions, or deploying AiAuthoringBundle (v65+) or GenAiPlannerBundle (v65+) metadata.

Comprehensive Salesforce testing skill with test execution, code coverage analysis, and agentic test-fix loops. Run Apex tests, analyze coverage, generate test patterns, and automatically fix failing tests with 120-point scoring.

Expert Claude Code plugin development covering plugin structure, slash commands, auto-activating skills, sub-agents, plugin.json configuration, YAML frontmatter, activation keywords, directory structure, and plugin best practices. Activates for plugin development, create plugin, claude plugin, slash command, skill activation, SKILL.md, plugin.json, claude code plugin, how to make plugin.

Explains how SpecWeave achieves context efficiency through Claude's native progressive disclosure mechanism and sub-agent parallelization. Skills load only when relevant, sub-agents isolate context. Activates when users ask about context loading, token usage, or how SpecWeave scales. Keywords: context loading, progressive disclosure, token efficiency, sub-agents, context management.

Sync SpecWeave increments with JIRA epics/stories. Content flows SpecWeave→JIRA, status flows JIRA→SpecWeave. Activates ONLY when user asks questions about JIRA integration or needs help configuring JIRA sync. Does NOT activate for slash commands. For syncing, use /sw-jira:sync command instead. Coordinates with jira-mapper agent.

Expert Claude Code marketplace publishing covering npm publishing, GitHub releases, semantic versioning, plugin packaging, README documentation, CHANGELOG management, marketplace submission, and plugin distribution. Activates for publish plugin, npm publish, marketplace, release plugin, semantic versioning, semver, plugin distribution, publish to npm, github release.

LLM-native translation skill for SpecWeave content. Activates when translation is needed for CLI messages, templates, documentation, or living docs. Uses the current LLM session for zero-cost translation. Keywords: translate, translation, language, multilingual, i18n, internationalization, Russian, Spanish, Chinese, German, French, localization, translate to.

Guide for using git worktrees to parallelize development with coding agents. Use this skill when the user requests to work in a new worktree or wants to work on a separate feature in isolation (e.g., "Work in a new worktree", "Create a worktree for feature X").

Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.