KbWen
UserGovernance-first OS for AI coding agents — structured workflows, delivery gates, engineering guardrails, and 17 professional skills for Claude Code, Cursor, Copilot, Antigravity & Codex.
Categories
Indexed Skills (21)
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
dispatching-parallel-agents
Evaluate when to dispatch parallel agents; use a 4-step pattern to split, coordinate, and integrate results.
subagent-driven-development
Decompose tasks via subagent collaboration; define interface contracts and integration checkpoints.
systematic-debugging
Use 4-phase root cause analysis (Observe, Hypothesize, Verify, Fix); avoid unverified patches.
test-driven-development
Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.
using-git-worktrees
Use Git worktrees to create parallel working directories safely; avoid branch-switch contamination.
verification-before-completion
Enforce "no evidence = no completion"; run Gate Function verification before declaring done.
executing-plans
Execute plans step-by-step with evidence at each stage; maintain rollback capability.
finishing-a-development-branch
Perform final verification on development branches; choose from 4 merge strategies.
receiving-code-review
Effectively process reviewer feedback; categorize blocking vs. advisory items.
requesting-code-review
Request code reviews at the right time with necessary context and evidence.
writing-plans
Plan before implementing; produce verifiable, rollback-safe, incrementally executable task plans.
dispatching-parallel-agents
Evaluate when to dispatch parallel agents; use a 4-step pattern to split, coordinate, and integrate results.
subagent-driven-development
Decompose tasks via subagent collaboration; define interface contracts and integration checkpoints.
systematic-debugging
Use 4-phase root cause analysis (Observe, Hypothesize, Verify, Fix); avoid unverified patches.
test-driven-development
Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.
using-git-worktrees
Use Git worktrees to create parallel working directories safely; avoid branch-switch contamination.
verification-before-completion
Enforce "no evidence = no completion"; run Gate Function verification before declaring done.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.