Stats
Actions
Tags
From restruct
Manually refine a prompt through the local LLM meta-prompt pipeline. Transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. Only works when features.refinement is enabled in config.yaml.
How this skill is triggered — by the user, by Claude, or both
Slash command
/restruct:refine-restructThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. It reads project rules from agents.md/CLAUDE.md, gathers git context, and produces XML-structured output with objective, constraints, workflow, uncertainty protocol, and anti-patterns.
This skill transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. It reads project rules from agents.md/CLAUDE.md, gathers git context, and produces XML-structured output with objective, constraints, workflow, uncertainty protocol, and anti-patterns.
The binary is bundled in this plugin — always use the full path:
${CLAUDE_PLUGIN_ROOT}/bin/restruct refine
Usage:
echo '{"prompt":"your prompt here"}' | ${CLAUDE_PLUGIN_ROOT}/bin/restruct refine to refine a prompt--dry-run to preview the refined prompt to stderr without replacingThe refinement pipeline runs entirely locally — no data leaves your machine.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub thejustinwalsh/claude-plugins --plugin restruct