From zie-framework
Systematic debugging — reproduce, isolate, fix, verify. Uses zie-memory to surface known failure patterns.
How this skill is triggered — by the user, by Claude, or both
Slash command
/zie-framework:debugsonnetThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Reproduce → Isolate → Fix → Verify. No guessing.
Reproduce → Isolate → Fix → Verify. No guessing.
If zie_memory_enabled=true:
mcp__plugin_zie-memory_zie-memory__recall with project=<project> domain=<failing-area> tags=[bug, debug] limit=10git log --oneline -10 — did anything change that
could cause this?make test-unitmake test-intIf zie_memory_enabled=true:
mcp__plugin_zie-memory_zie-memory__remember
with "Bug: <desc>. Root cause: <why>. Fix: <how>. Pattern: <recurring|one-off>." tags=[bug, <project>, <domain>]npx claudepluginhub zierocode/zie-plugins-claude-code --plugin zie-frameworkProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
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.