Specify LLM — AI skill for Claude Code
AI feature obligations — specification stage.
How to install Specify LLM
Installs to ~/.claude/skills/netresearch-spec-kit-typo3-llm-specify-llm/SKILL.md
mkdir -p ~/.claude/skills/netresearch-spec-kit-typo3-llm-specify-llm && curl -fsSL https://raw.githubusercontent.com/netresearch/spec-kit-typo3-llm/HEAD/commands/specify-llm.md -o ~/.claude/skills/netresearch-spec-kit-typo3-llm-specify-llm/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Specify LLM does
AI feature obligations — specification stage
These are the questions an AI feature gets wrong in the same way every time. Answer them here, in prose, before anything picks a provider or a class.
- Which provider capability does this assume? Structured output, tool calling, streaming, vision, a context window of a given size. Name it.
- What happens on a provider that lacks it? There are three defensible answers and you must pick one: refuse the call, fall back to a provider that h
Alternatives in AI
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- Firecrawl MCP Server — 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM c 6.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Wikipedia Flashcards Agent
This is a hands-on workshop about working with AI coding agents. You'll learn how to plan and specify requirem
Launch An AI Feature
Workflow recipe — take an AI/LLM feature from a probabilistic-aware PRD to a launch-ready model card by chaini
Cost Check
Estimate LLM token cost for a feature, prompt, or workflow — with optimization recommendations
Add Eval
Add automated eval (LLM-as-judge or deterministic) for an AI-powered feature
Claudomat Mini
Battle-tested operating system for shipping product with LLM coding agents. 17-stage wave loop, two-reviewer g
Literature Monitor Bot
Agent-deployed, hands-off literature monitor: bioRxiv + journals -> 3-stage LLM filter -> Discord/Telegram dig
Related Agents
Ccd Speckit Specifier
Use this agent to translate approved user intent into a testable, implementation-independent feature specifica
Feature
Full SDLC cycle from specification to deployment with user approval at each stage.
Outline Planner
Proposes 2-3 mutually-exclusive high-level approaches for a task. Used by the make-outline-plan skill. Inspire