From craft-skills
Delivers cost-optimized /craft pipeline using local Qwen3.6-35B-A3B for implementation and reviews, Opus for orchestration, Sonnet fallback. Requires LM Studio; saves 45-60% API costs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/craft-skills:craft-aceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Full design-first pipeline with Qwen3.6 as the primary implementer and reviewer. Opus orchestrates and handles integration. Sonnet serves as fallback for tasks the local model can't handle.
Full design-first pipeline with Qwen3.6 as the primary implementer and reviewer. Opus orchestrates and handles integration. Sonnet serves as fallback for tasks the local model can't handle.
Profile: claude+ace
Pipeline: Brainstorm -> Plan -> Develop -> Browser Test -> Report (same as /craft)
This wrapper writes a profile marker, then delegates to the canonical craft pipeline. The claude+ace profile triggers:
echo -n "claude+ace" > .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-implement.sh instead of Claude agentsThe 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}| Activity | Savings vs /craft |
|---|---|
| Reviews (spec, plan, post-develop) | 100% (all local) |
| Data layer implementation (~40-50% LoC) | 100% (all local) |
| UI implementation (~30-40% LoC) | ~30-50% (Qwen3.6 first, Sonnet fallback) |
| Integration (~10-20% LoC) | 0% (stays on Opus) |
| Total estimated savings | ~45-60% |
npx claudepluginhub alexiolan/craft-skills --plugin craft-skillsInvokes /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.
Scaffolds CLAUDE.md and .claude/rules/ for Craft CMS projects, detecting project type (plugin, site, module, hybrid, monorepo) from composer.json and other files.
Delegates implementation and review tasks to external AI CLI tools (Codex, Gemini) with cross-model adversarial review for cost savings and improved accuracy.