LLM 與 Agent

Prompt-native architecture patterns, agent orchestration, iteration loops, and state management for autonomous work.

Multi-remote git push workflow for GitHub and Azure DevOps. Use when the user says"push to github", "push to azure", "push to origin", "push to secondary", "push to devops","push to both", "sync remotes", or any variation requesting git push operations.Handles the azure-sync branch workflow that excludes .claude/, specs/, and CLAUDE.md from Azure.

Career Advisor agent for PhD application planning and career management. Helps with university research, application tracking, professor matching, and career documentation.

Comprehensive manual for Telegram Mini Apps SDK. Use when developers need guidance on creating web applications inside Telegram, working with WebApp API, managing user data, handling authentication via initData, implementing buttons and events, working with storage, and integrating with Telegram ecosystem features.

Development guide for Claude Agent SDK integration in IPA Platform.Use when:- Building autonomous AI agents with Claude- Implementing agents that need to make independent decisions- Creating agents with tool usage, MCP integration, or subagent delegation- Integrating Claude SDK with existing Microsoft Agent Framework- Working with code in backend/src/integrations/claude_sdk/Provides: query(), ClaudeSDKClient, built-in tools, hooks, MCP, subagents patterns.

This skill should be used when the user asks to "orchestrate jira", "work on issue", "complete jira ticket", "development workflow", "jira automation", "issue lifecycle", "work on story", "fix bug ticket", or needs guidance on coordinating development work through Jira with multi-agent orchestration patterns.

Systematic documentation audit that validates every documentation claim against code and identifies undocumented features - executable as a repeatable Claude Code skill (project)

Send messages and notifications to Poke (poke.com) via webhook API. Use when alerting the user, sending task completion notifications, status updates, reminders, or any message to their Poke assistant.

MUST INVOKE this skill when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc). Expert guidance for creating, configuring, and using AI agent hooks (Claude Code-specific).

Orchestre agents TEST/DOC pour validation tâche, calcule score /100, génère 3 rapports, commit auto

Generate comprehensive handoff documentation optimized for AI agent takeover by analyzing project structure, design docs, and codebase

Renders After Effects animations as lightweight JSON on web and mobile using lottie-web. Use when adding vector animations, loading indicators, or complex motion graphics without video files.

Research-driven PyIceberg development. Injects research steps for Iceberg table operations, ACID transactions, catalog integration, and schema evolution. Use when working with Iceberg table storage, time-travel queries, or data lake operations.

Fundamental reading and writing capability for the OCTAVE format. Inject this to give an agent basic structural competence without the overhead of full architectural specifications. Triggers on: octave format, write octave, octave syntax, structured output.

This skill should be used when the user asks to "explore the codebase", "understand the architecture", "find similar features", or as Phase 2 of the /dev workflow. Launches explore agents to map codebase and returns key files list.

Expert-level Google Cloud CLI (gcloud) skill for managing GCP resources. Use when workingwith "gcloud commands", "cloud run deploy", "alloydb", "cloud sql", "workload identityfederation", "iam permissions", "vpc networking", "secret manager", or "artifact registry".Covers installation, authentication, IAM, Cloud Run, Cloud Storage, VPC, AlloyDB, Firebase,and CI/CD integration with GitHub Actions and Cloud Build.

Use when creating ENT components/pages/stores or agent violates Vue 2 patterns - enforces ENT-specific rules and prevents common rationalizations about Vue 3, custom CSS, v-slot syntax, and fetch API

Optimize and analyze work items for LLM-assisted development

Guide Alfred sub-agents to actively invoke AskUserQuestion for ambiguous decisions.

Build and deploy this Next.js LangChain retrieval application with Supabase vector store. Use when building, deploying, setting up vector store, or preparing the project for production.