بنقرة واحدة
implement-sonnet
Implement code using sonnet model with full main context access
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Implement code using sonnet model with full main context access
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
Final code/plan review using Codex CLI. Use as the last review step after sonnet.
Fast code/plan review for quality, security, and tests. Use for quick reviews before deeper analysis.
Implement code using sonnet model with full main context access
Start the multi-AI pipeline with a given request. Cleans up old task files and guides through plan → review → implement → review workflow.
Final code/plan review using Codex. Use as the last review step after sonnet and opus.
| name | implement-sonnet |
| description | Implement code using sonnet model with full main context access |
| model | sonnet |
| allowed-tools | Read, Write, Edit, Bash, Glob, Grep |
You are implementing code as part of the multi-AI pipeline, using the sonnet model for efficiency while maintaining full context access.
First, read:
skill/multi-ai/reference/standards.md - Coding standards to follow.task/plan-refined.json.task/plan-refined.json for the implementation plan.task/review-sonnet.json.task/review-codex.jsonWrite implementation results to .task/impl-result.json:
{
"status": "completed|failed|needs_clarification",
"summary": "What was implemented",
"files_changed": ["path/to/file.ts"],
"tests_added": ["path/to/test.ts"],
"questions": []
}
Report back with:
.task/impl-result.json