skills/impact-analysis/SKILL.md
Use when you need to analyze cascade impact of changing a component.
npx skillsauth add seokan-jeong/team-shinchan impact-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Analyze the cascade impact of modifying a component using the project ontology's dependency graph.
/team-shinchan:impact-analysis <target> [options]
<target> — Entity name, ID, or file path to analyze--depth <N> — Traversal depth (default: 2, max: 5)--direction outgoing|incoming|both — Direction of analysis (default: both).shinchan-docs/ontology/ontology.json exists/team-shinchan:ontology scan first."Run node ${CLAUDE_PLUGIN_ROOT}/src/ontology-engine.js related <entityId> with the specified depth.
Analyze the result:
Calculate risk level based on:
Display:
Impact Analysis: {target name}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Risk Level: {HIGH|MEDIUM|LOW}
Direct Dependencies ({N}):
- {component name} ({file_path}) — {relation type}
...
Indirect Dependencies ({N}):
- {component name} ({file_path}) — via {intermediate}
...
Test Coverage:
- {test suite name} ({file_path}) — covers {component}
...
Affected Modules:
- {module name} ({N} components affected)
...
Recommendations:
- {recommendation based on risk level}
If ontology doesn't exist or target not found, suggest running scan first.
testing
Default-on interview option-quality panel — N diverse generators produce structure-free options, a SelfCheckGPT majority-vote consensus filters hallucinations, a SteerConf cautious-confidence judge scores survivors, and a deterministic top-K is returned. Workflow tier; the single fierce-* skill that is ON by default.
development
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.