菜单
Code review from the Kent Beck Simple Design 4 Rules perspective. God Object splitting, SRP, duplication removal, naming, cyclomatic complexity. Triggered by "kent beck", "simple design", "simplify", "refactoring" ("리팩토링"), "refactor", "god object", "SRP" keywords.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | kent-beck-review |
| description | Code review from the Kent Beck Simple Design 4 Rules perspective. God Object splitting, SRP, duplication removal, naming, cyclomatic complexity. Triggered by "kent beck", "simple design", "simplify", "refactoring" ("리팩토링"), "refactor", "god object", "SRP" keywords. |
| user-invocable | false |
"Make the change easy, then make the easy change."
# Detect 500+ line files (God Object candidates)
find core/ -name "*.py" -exec wc -l {} + | sort -rn | head -20
Criteria:
cli/__init__.py (2800+ lines) splitting already in progress# Detect 50+ line functions
grep -n "def " core/ -r --include="*.py" | while read line; do
echo "$line"
done
# Detect nesting depth 4+
grep -rn "if\|for\|while\|with\|try" core/ --include="*.py" | grep -c " " # 4 indent levels
Criteria:
| Anti-pattern | Improvement |
|---|---|
def process(data) | def score_analyst_response(response) |
result = fn(x, y, z) | Use meaningful variable names |
# This function does X | Reveal through function name, remove comment |
magic number 0.7 | CONFIDENCE_THRESHOLD = 0.7 |
Detect idea-level duplication (not just copy-paste but missing abstractions):
# Repeated similar patterns
grep -rn "def _call_llm_" core/ --include="*.py" # 3 similar functions per provider
grep -rn "def _build_" core/runtime.py # 10+ similar builder patterns
Criteria:
| Unnecessary Element | Criteria |
|---|---|
| Unused parameters | Wrappers that only pass **kwargs |
| ABC with single implementation | Protocol is sufficient |
Empty __init__.py | Remove if no re-exports |
| Unused imports | Auto-detected by ruff F401 |
| Item | File | Status |
|---|---|---|
cli/__init__.py 2800+ lines | L0 | Splitting in progress (repl.py, commands.py extracted) |
agentic_loop.py 1400+ lines | L0 | _process_tool_calls 88 lines — extraction candidate |
runtime.py 1400+ lines | DI | 10+ _build_* builders — pattern unification candidate |
policy.py 430 lines | L4 | Within acceptable range |
GEODE CHANGELOG.md management rules. Version releases, change logging, scope determination, format standards. Triggers on "changelog", "release", "version", "릴리스", "변경사항", "버전".
Slack Gateway operations guide. Socket Mode credentials, config.toml bindings, serve restart, receiver debugging, reaction behavior. Triggers on "serve", "gateway", "slack", "바인딩", "binding", "소켓", "socket", "폴러", "poller", "config.toml".
GEODE evidence-first development workflow. Use for feature work, provider/model changes, GUI/computer-use work, PDF/document ingestion, observability/schema/event/state changes, verification planning, GitFlow merge prep, and requests to "follow the workflow" or "scaffold the process".
Publish and verify a released GEODE version across GitHub Release and PyPI/uv, prepare or update the separate Homebrew/core geode-agent formula, and prevent deleted custom-tap paths from returning. Use for Homebrew/core admission, brew formula work, uv/uvx distribution, stable promotions, release repair runs, and public installation-channel audits.
6-lens slop prevention audit — unused imports, dead private fns, duplicate signatures, abandoned TODOs, lint bypass markers, stale refs. Baseline-gated growth check.
Reliable progress monitoring for long-running background tasks (live audits, training, multi-step CI). Covers Monitor + tail buffering pitfalls, polling vs streaming patterns, post-mortem cat/grep, and the Petri × GEODE eval log discovery flow. Triggered by "monitor", "tail -F", "progress", "background", "live audit", "stdbuf", "buffering" keywords.