claude-exec
npx machina-cli add skill dceoy/ai-coding-agent-skills/claude-exec --openclawClaude Exec Skill
Use Claude Code CLI to execute development tasks that involve code modifications. This skill modifies code.
When to Use
- User asks to "add", "create", "implement", or "generate" code
- User wants to refactor existing code
- User needs to fix a bug
- User wants to create tests
- User asks to "update" or "modify" code
Prerequisites
Verify Claude Code CLI is available:
claude --version # Should display installed version
Basic Usage
Step 1: Understand the Task
Parse what needs to be done:
- What to create/modify?
- Which files are affected?
- Expected outcome?
- Constraints or requirements?
Step 2: Gather Context
Before executing, understand the current state:
git status
git diff
Read relevant files to follow existing patterns.
Step 3: Execute Claude Code
Run Claude Code with clear instructions (use -p/--print to output once and exit):
claude -p "[TASK]
Follow these guidelines:
- Follow existing code patterns and conventions
- Add appropriate error handling
- Include necessary imports
- Maintain readability and code quality
- Add comments only for complex logic
Do NOT change unrelated files."
If your CLI does not support -p, run claude and paste the prompt.
Step 4: Verify Changes
After execution:
git status
git diff
Run relevant checks or tests if available.
Step 5: Report Results
Provide:
- Files modified/created
- Summary of changes
- Verification results
- Any issues or warnings
Example Tasks
claude -p "Add email validation to ContactForm.tsx:
- Use regex: /^[^\\s@]+@[^\\s@]+\\.[^\\s@]+$/
- Show error message below input field
- Validate on blur and submit
- Prevent submission if invalid
- Style error message in red (#dc2626)
Follow existing form validation patterns."
claude -p "Refactor validation logic in src/components/LoginForm.tsx:
- Extract validation into src/utils/validation.ts
- Create validateEmail and validatePassword functions
- Keep existing behavior
- Add TypeScript types"
Best Practices
- Be specific in task descriptions (paths, requirements, constraints)
- Review all changes with
git diff - Run lint/tests when available
- Avoid auto-approving risky changes
Error Handling
- If execution fails, tighten scope and re-run
- If changes are incorrect, revert and re-run with clearer guidance
- If tests fail, fix failures before reporting success
Related Skills
claude-askfor understanding code before modifyingclaude-reviewfor reviewing changes after modification
Limitations
- Cannot run tests by itself
- May miss project-specific constraints
- Requires manual verification
Source
git clone https://github.com/dceoy/ai-coding-agent-skills/blob/main/skills/claude-exec/SKILL.mdView on GitHub Overview
Claude Exec uses the Claude Code CLI to perform code generation, refactoring, feature work, bug fixes, and test creation. It emphasizes following project patterns, adding necessary imports and error handling, and verifying changes via Git before reporting results.
How This Skill Works
When a task is provided, the agent parses the scope and affected files, checks the repo state with git status and git diff, then runs Claude Code CLI with a structured prompt using claude -p. After execution, it reviews the changes with git status/git diff, and runs relevant checks or tests if available before reporting results.
When to Use It
- User asks to add, create, implement, or generate code
- User wants to refactor existing code
- User needs to fix a bug
- User wants to create tests
- User asks to update or modify code
Quick Start
- Step 1: Understand the Task - determine what to create/modify, affected files, constraints
- Step 2: Gather Context - check repo state with git status/git diff and read relevant files
- Step 3: Execute Claude Code - run claude -p with clear task instructions and follow guidelines; if -p unsupported, run claude and paste prompt
Best Practices
- Be specific in task descriptions with file paths, requirements, and constraints
- Follow existing code patterns and conventions
- Review changes with git diff and run lint/tests when available
- Add error handling and necessary imports; maintain readability and code quality
- Verify results and be prepared to revert or re-run with clearer guidance
Example Use Cases
- Add email validation to ContactForm.tsx: use regex, show error message below input, validate on blur and submit, prevent submission if invalid, and style the error in red
- Refactor validation logic in src/components/LoginForm.tsx: extract into src/utils/validation.ts, create validateEmail and validatePassword functions, keep existing behavior, and add TypeScript types
- Generate unit tests for a module to improve coverage
- Implement a new feature by adding an API integration in a service file
- Update error handling and imports after a codebase change while preserving existing behavior
