From craft-skills
Same as /craft but with local LLM review steps enabled. Use when you have LM Studio running and want LLM-assisted spec/plan/post-develop reviews. Preserves pre-1.1 craft behavior.
npx claudepluginhub alexiolan/craft-skills --plugin craft-skillsThis skill uses the workspace's default tool permissions.
Full design-first pipeline with LM Studio as a supplementary review agent. Identical to `/craft` except that LLM pre-exploration, spec review, plan review, and post-develop review steps all run.
Full design-first pipeline with all three AI agents: Claude (architect + UI + integration), Codex (data-layer + bulk fixes), and local LLM (LM Studio, for exploration + review). Power-user mode. Optionally runs Codex adversarial review if codex-plugin-cc is installed.
Orchestrates agentic workflow to create new Claude Code plugins from scratch: prerequisite checks, research, design verification, atomic implementation, validation, documentation.
Designs LLM-powered projects from ideation to deployment. Evaluates task-model fit for agents vs traditional code, plans batch pipelines, and guides prototyping.
Share bugs, ideas, or general feedback.
Full design-first pipeline with LM Studio as a supplementary review agent. Identical to /craft except that LLM pre-exploration, spec review, plan review, and post-develop review steps all run.
Profile: claude+llm
Pipeline: Brainstorm → Plan → Develop → Browser Test → Report (same as /craft)
This wrapper is ~1 step of delegation. The actual pipeline logic lives in skills/craft/SKILL.md. This file writes the profile marker, then instructs you to follow the craft pipeline.
echo -n "claude+llm" > .craft-profile
Read skills/craft/SKILL.md from this plugin and follow every phase exactly as written. The profile gating in that file ensures LLM steps run when profile is claude+llm.
The user input is: $ARGUMENTS
Pass the input through to the craft pipeline as if the user had invoked /craft directly.
${LLM_URL:-http://127.0.0.1:1234}/craft in exchange for deeper review