TechHU-GS
UserGuardrails for Claude Code. Shell hooks that actually block bad behavior — edit loops, skipped verification, destructive git — not just markdown that asks nicely.
Categories
Indexed Skills (8)
self-check
Periodic self-check — reflect on alignment, progress, and quality. Use with /loop for continuous monitoring.
commit
Smart commit — run tests, update docs and memory, then commit to ensure knowledge is not lost
evaluate
Objectively evaluate external review/advice against your actual codebase knowledge. Use when pasting suggestions from reviewers, consultants, or AI who lack project context.
finish
Drive a task to completion with the quality bar — solid, comprehensive, fully tested; "not run" never counts as done. Use when you're ready to execute to the end (standalone, or as the handoff after /think approval).
investigate
Multi-agent cross-investigation. Two modes — research (explore from scratch) and review (challenge existing proposal). Spawns parallel agents per dimension, synthesizes with dialectical cross-check.
retro
Find friction, remove friction. Quick post-task review that makes this project's workflow smoother and feeds improvements back to cc-discipline.
summary
Summarize current session context for high-quality /compact. Run before compacting to preserve what matters.
think
Stop and think before coding. Read context, ask questions, propose approaches, self-review, wait for user choice. Use when starting any non-trivial task.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.