원클릭으로
qodana-review
Run Qodana static analysis. ALL issues must be fixed. No exceptions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Run Qodana static analysis. ALL issues must be fixed. No exceptions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Read-only quality scan of components. Reports problems without making changes. Uses software-base + domain profile skills.
Refactoring patterns - improving code design without changing behavior
Read-only quality scan of components. Reports problems without making changes. Uses software-base + domain profile skills.
Internal phase: independent Codex review + targeted fixes. Not user-facing.
Find duplicated code and consolidate into shared utilities. Fixes all duplicates.
Reference templates for Codex evaluation. Used by build/improve orchestrators — not executed directly.
| name | qodana-review |
| description | Run Qodana static analysis. ALL issues must be fixed. No exceptions. |
Run Qodana static analysis. ALL issues must be fixed.
No arguments? Describe this skill and stop. Do not execute.
mkdir -p .claude && echo '{"skill":"static-analysis","started":"'$(date -Iseconds)'"}' > .claude/active-workflow.json
Fix toward code a master craftsperson would be proud of.
When fixing static analysis issues, ensure the result looks like it was written by a skilled human engineer, not generated by AI.
Beyond Qodana findings, actively look for and fix:
After fixing, code should:
The goal isn't just passing the checks - it's code worth reading.
Fix ALL findings for production readiness. Every issue gets fixed. No deferring, no "backlog for next cycle," no "appropriate for MVP."
ALLOWED:
FORBIDDEN:
If a finding seems to require restructuring: fix it anyway by restructuring within the existing file. The only acceptable unfixed items are findings that require adding new external dependencies — report those with a one-line explanation.
You MUST fix EVERY issue Qodana and lint find. ALL of them. No exceptions.
If an analyzer found it, YOU FIX IT. Period.
mcp__qodana__qodana_scan
projectDir: <project path>
mcp__qodana__qodana_problems
projectDir: <project path>
npx tsc --noEmit
npm run lint
For EACH issue:
The ONLY exception: third-party library code with documented evidence.
QODANA_RESULT: called - [N] issues
ISSUES_FOUND:
[SEVERITY] description (file:line) [source: qodana/lint]
ISSUES_FIXED:
[SEVERITY] description - FIXED
UNFIXED: 0 (must be zero or phase fails)
ANALYSIS_ISSUES: N
SECURITY_REVIEW_COMPLETE: yes
After fixing all issues, record NEW findings so earlier phases learn from them.
Write to TWO files:
.claude/lessons.mdAppend the specific finding with file paths and context:
## {date} - {target path}
### Qodana Found (phase 7)
- {CATEGORY}: {specific description with file:line} → {which earlier phase should catch this and how}
.claude/universal-lessons.mdRead this file first. If the general pattern is already listed, skip. If it's a NEW general pattern not already covered, append it to the appropriate section (LOGIC Patterns, DESIGN Patterns, CODE_QUALITY Patterns, or DUPLICATION Patterns). Write the general rule, not the project-specific instance:
### {Pattern Name}
- {General description of the pattern, not tied to specific files} → {how to avoid it}
Categories: LOGIC, DESIGN, CODE_QUALITY, DUPLICATION
Common Qodana findings that indicate earlier-phase gaps:
If no new lessons were learned (already in both files), skip this step.