ai-specialist

Ai Specialist

Provides AI application development, MCP server engineering, prompt engineering, and agent framework integration capabilities. Use when you need to build or optimize large-model-based features, workflows, or platform integrations.

Skill Index

The following index is node scripts/update-skill-index.js automatically generated, used to let Claude continue routing to the most relevant sub-skills after the top-level expert is triggered.

Claude Usage Instructions

1. First, semantically match the user's current task with each sub-skill's 触发语义 , do not just look at the directory name.
2. Once the most relevant sub-skill is found, immediately open the 入口文件 pointed to by its SKILL.md, and use it as the entry point for the next layer.
3. After entering the sub-skill, then load the references/、scripts/、assets/in the same directory as needed according to that sub-skill's own instructions; do not expand large sections of detail in advance at the top-level expert.
4. If multiple sub-skills are relevant, first load the one closest to the main goal, then supplement with other sub-skills as needed, avoiding loading too much context at once.
5. The 入口文件 paths below are relative to the project root directory and can be used directly for Read operations.

Sub-skill Index

agents-orchestrator (1)

• agents-orchestrator
  • Trigger semantics: Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
  • Entry file: .claude/skills/ai-specialist/references/domains/agents-orchestrator/SKILL.md

ai-data-remediation-engineer (1)

• ai-data-remediation-engineer
  • Trigger semantics: Specialist in self-healing data pipelines — uses air-gapped local SLMs and semantic clustering to automatically detect, classify, and fix data anomalies at scale. Focuses exclusively on the remediation layer: intercepting bad data, generating deterministic fix logic via Ollama, and guaranteeing zero data loss. Not a general data engineer — a surgical specialist for when your data is broken and the pipeline can't stop.
  • Entry file: .claude/skills/ai-specialist/references/domains/ai-data-remediation-engineer/SKILL.md

ai-engineer (1)

• ai-engineer
  • Trigger semantics: Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.
  • Entry file: .claude/skills/ai-specialist/references/domains/ai-engineer/SKILL.md

mcp-builder (1)

• mcp-builder
  • Trigger semantics: Expert Model Context Protocol developer who designs, builds, and tests MCP servers that extend AI agent capabilities with custom tools, resources, and prompts.
  • Entry file: .claude/skills/ai-specialist/references/domains/mcp-builder/SKILL.md

mcp-server-engineering (1)

• mcp-builder
  • Trigger semantics: A guide to creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
  • Entry file: .claude/skills/ai-specialist/references/domains/mcp-server-engineering/mcp-builder/SKILL.md

model-qa (1)

• model-qa-specialist
  • Trigger semantics: Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.
  • Entry file: .claude/skills/ai-specialist/references/domains/model-qa/SKILL.md

prompt-engineering (1)

• Prompt Enhancer
  • Trigger semantics: Transform vague prompts into actionable specs using intelligent analysis and session memory. Use when user input contains -e or --enhance flag.
  • Entry file: .claude/skills/ai-specialist/references/domains/prompt-engineering/prompt-enhancer/SKILL.md

Notes

• Top-level SKILL.md For index navigation only; it does not carry large amounts of detailed content.
• Detailed materials are moved down to references/domains/, organized in a tree structure.