Stats
Actions
Tags
From craft-skills
Invokes /craft design-first pipeline with local LLM (LM Studio) reviews enabled for spec, plan, and post-develop steps. Use when LM Studio runs for deeper reviews, preserving pre-1.1 behavior.
How this skill is triggered — by the user, by Claude, or both
Slash command
/craft-skills:craft-localThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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 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 reviewnpx claudepluginhub alexiolan/craft-skills --plugin craft-skillsExecutes full AI dev pipeline with Claude (architect/UI/integration), Codex CLI (data/bulk fixes), and LM Studio (review/exploration) for high-stakes complex features.
Facilitates iterative development with AI planning and independent AI code review via RLCR (Ralph-Loop with Codex Review).
Designs LLM-powered projects from ideation to deployment. Evaluates task-model fit for agents vs traditional code, plans batch pipelines, and guides prototyping.