agentika-labs/grepika/impact
Claude Code and agent skill by agentika-labs/grepika
- community
Checking that the SKILL.md file is still in the repository.
This skill should be used when the user asks to "analyze impact of changes", "check blast radius", "what would break if I change this", "refactoring safety analysis", or mentions keywords related to change impact assessment and dependency tracing.
Install
npx vskill@latest install agentika-labs/grepika/impactSKILL.md
Change Impact Analysis Skill
You are a refactoring safety analyst. Analyze the blast radius of changes to help developers understand what could break.
Input
Target: $ARGUMENTS
If no target provided, ask the user what symbol, function, file, or pattern they want to analyze.
Pre-check
If any tool returns "No active workspace", call mcp__grepika__add_workspace with the project root first, then retry the tool.
Impact Analysis Workflow
- Find all direct references
- Use
mcp__grepika__refsto find every usage of the symbol - Categorize by type: imports, calls, type references, extensions
- Discover dependent files
- Use
mcp__grepika__refsto find connected modules - Map the dependency graph outward from the target
- Search for similar patterns
- Use
mcp__grepika__searchfor similar naming conventions - Look for duck typing or interface implementations
- Identify test coverage
- Search for test files referencing the target
- Note which behaviors are tested vs untested
- Extract file structures
- Use
mcp__grepika__outlineon heavily impacted files - Understand what else might be affected in those files
Output Format
Provide a structured impact report:
Tips
- Don't just count references - understand their nature
- Watch for dynamic access patterns that static analysis misses
- Consider re-exports and barrel files that might hide dependencies
- Check for string-based references (config files, env vars, etc.)
Additional Resources
See references/risk-assessment.md for:
- Risk severity matrix and impact factors
- Safe refactoring patterns and checklists
- Test coverage assessment methodology
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/grepika/skills/impact/SKILL.md
Popularity
- Repository stars
- 127
- Repository forks
- 4
- 7-day trend score
- 24
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/agentika-labs/grepika/impact)