team-shinchan:implement
npx machina-cli add skill seokan-jeong/team-shinchan/implement --openclawEXECUTE IMMEDIATELY
Step 1: Validate Input
If args is empty or only whitespace:
Ask user: "What would you like me to implement?"
STOP and wait for user response
If args length > 2000 characters:
Truncate to 2000 characters
Warn user: "Request was truncated to 2000 characters"
Step 2: Execute Task
Do not read further. Execute this Task NOW:
Task(
subagent_type="team-shinchan:bo",
model="sonnet",
prompt=`/team-shinchan:implement has been invoked.
## Implementation Request
Handle coding tasks including:
| Area | Capabilities |
|------|-------------|
| Feature Implementation | New features, functions, classes |
| Bug Fixes | Debugging, error correction |
| Code Modification | Refactoring, updates, changes |
| Utilities | Helper functions, utilities |
| Tests | Unit tests, integration tests |
## Implementation Requirements
- Read existing code first to understand patterns
- Follow project conventions
- Write clean, maintainable code
- Handle errors gracefully
- Keep functions small and focused
- Add comments only for complex logic
## Post-Implementation Verification
After writing code:
1. Run existing tests if available (detect test framework from package.json/config)
2. If tests fail, fix the issues before reporting completion
3. If no tests exist, verify the code compiles/loads without errors
## Output Format
After implementation:
- Summary of changes made
- Files modified with line references
- Test results (pass/fail/skipped)
- Any follow-up recommendations
User request: ${args || '(Please describe what to implement)'}
`
)
STOP HERE. The above Task handles everything.
Source
git clone https://github.com/seokan-jeong/team-shinchan/blob/main/skills/implement/SKILL.mdView on GitHub Overview
This skill orchestrates rapid code tasks by validating user requests, truncating overly long inputs, and delegating the actual coding to a Bo-based worker. It targets feature implementations, bug fixes, code modifications, utilities, and tests, emphasizing reading existing code and following project conventions. After work is completed, it reports the changes, test results, and any follow up recommendations.
How This Skill Works
Input is checked for emptiness and length; if empty it prompts the user and waits. If the request is longer than 2000 characters it is truncated with a warning. It then invokes a Task to run the coding work via team-shinchan:bo with model sonnet, and returns a structured output including changes, tests, and follow up recommendations.
When to Use It
- Implement a new feature or function based on a user request
- Fix a bug in existing code or a failing module
- Refactor or modify utilities to improve clarity or performance
- Add unit tests or integration tests for a component
- Update code to adapt to library or API changes
Quick Start
- Step 1: Submit your request with what to implement
- Step 2: The skill validates input, truncates if needed, and calls the Bo-based executor
- Step 3: Review the generated changes, run tests, and iterate
Best Practices
- Read existing code first to understand patterns and conventions
- Follow project conventions and style guides
- Keep functions small and focused to ease testing
- Add comments only for complex logic or essential decisions
- Verify compilation and tests after changes and report results
Example Use Cases
- Implement a new feature in a TypeScript module
- Fix a bug in a REST API handler
- Refactor a utility function for readability
- Add unit tests for a component or service
- Update a script to accommodate a library change
