一键导入
impact-analysis
Use when modifying any existing file (excluding new standalone files) to analyze dependencies and calculate impact score.
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。
菜单
Use when modifying any existing file (excluding new standalone files) to analyze dependencies and calculate impact score.
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
Use when Ground Truth alignment finds memory contamination and the user explicitly requests scoped cleanup with /cleanse.
Use when registering, reviewing, merging, or rebuilding HXSK glossary term definitions after glossary-detect suggests a candidate or the user invokes /define.
Use when staged changes exist requiring qlty checks, logical split detection, or HXSK phase-scoped conventional commit creation.
Use when validating code for circular imports, layer violations, or design doc logic errors before merging architecture-level changes.
Use when .hxsk/.bootstrap-version is missing (fresh install) or exists (verify/update) to initialize HExoskeleton.
Use when shell scripts need linting/formatting before execution or commit to ensure code quality.
| allowed-tools | ["Read","Grep","Glob","Bash"] |
| description | Use when modifying any existing file (excluding new standalone files) to analyze dependencies and calculate impact score. |
| name | impact-analysis |
| trigger | 영향 분석, 변경 영향 범위, 의존성 분석, impact analysis, check what this affects, before modifying files, 수정 전 영향도 확인, 리그레이션 방지, 의존성 추적, 파급 효과 분석, 영향도 점수 계산, impact score, 변경 전 확인, 리팩토링 전 분석, code impact, dependency chain, affected files, 승인 필요 확인, high impact check, before code change, dependency analysis |
| version | 4.0.0 |
List the files you intend to modify.
target_files = ["src/utils.ts", "src/models.ts"]
Grep을 사용하여 의존성 체인을 분석한다.
# import/require 검색으로 의존성 추적
Grep(pattern: "from.*utils.*import|import.*utils|require.*utils", path: "src/", output_mode: "files_with_matches")
Grep(pattern: "from.*models.*import|import.*models|require.*models", path: "src/", output_mode: "files_with_matches")
# 테스트 커버리지 확인
Grep(pattern: "utils|models", path: "tests/", output_mode: "files_with_matches")
bash .hxsk/hooks/md-recall-memory.sh "utils" "." 5 compact
과거 deviation이나 root-cause가 있으면 주의 필요.
Check the following areas in the report:
| Area | What to Look For |
|---|---|
| Incoming Dependencies | Who calls these files? |
| Outgoing Dependencies | What do these files call? |
| High-Risk Warnings | Circular dependencies, core API usage |
| Test Coverage | Which tests cover this code? |
| Factor | Score |
|---|---|
| 0-2 dependents | +1 |
| 3-5 dependents | +3 |
| 6+ dependents | +5 |
| Core/shared module | +2 |
| Has test coverage | -1 |
| No test coverage | +2 |
Impact Score > 7: Require human approval before proceeding.
If high impact is detected:
.hxsk/STATE.md to include verification steps| Rule | Description |
|---|---|
| Mandatory | You MUST NOT skip this step for any file modification |
| Exception | New standalone files don't require analysis |
| Escalation | If impact score > 7, require human approval before proceeding |
=== Impact Analysis Report ===
Target: src/utils.ts
Impact Score: 5/10
Incoming Dependencies (3):
- src/api.ts:15
- src/services/auth.ts:8
- tests/test_utils.ts:1
Outgoing Dependencies (1):
- src/constants.ts
Test Coverage: YES (tests/test_utils.ts)
Recommendation: Safe to proceed with standard testing
===
NO FILE MODIFICATION WITHOUT IMPACT ANALYSIS FIRST NO PROCEEDING WITHOUT HUMAN APPROVAL FIRST WHEN IMPACT SCORE > 7 NO IMPACT ANALYSIS COMPLETE WITHOUT DEPENDENCY TRACING AND MEMORY RECALL FIRST NO SKIP OF ANALYSIS WITHOUT VERIFICATION OF STANDALONE STATUS FIRST