kimi-code

Delegate multi-step repository implementation and refactoring tasks to Kimi Code CLI.

5|Updated Apr 23, 2026

Search Tags:#code generation #CLI automation #model selection #test verification #code delegation #repo refactor #long-horizon planning

Ready to run

npx skills add https://github.com/amirkiarafiei/subagent-cli-skills --skill kimi-code

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: kimi-code
Source: https://github.com/amirkiarafiei/subagent-cli-skills/tree/main/skills/kimi-code
Command: npx skills add https://github.com/amirkiarafiei/subagent-cli-skills --skill kimi-code

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It reduces context cost and fatigue when you need large, multi-step repository changes by delegating the heavy lifting to Kimi Code CLI.

Core Features & Use Cases

Long-horizon repo work: use Kimi for implementation passes, broad refactors, and deep exploration across many files.
Cognition-style context handoff: include the original goal, prior decisions, scope, constraints, and verification expectations so isolated runs stay aligned.
Guardrailed automation: run in non-interactive mode with auto-approval, enforce a verification command, and reconcile results back into the main thread.

Quick Start

Tell your agent to use the kimi-code skill to implement the feature or refactor in the specified files, including the chosen constraints and the exact test command Kimi must pass before returning.

Frequently Asked Questions about kimi-code

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate large multi-step repository refactoring across many files?▼

Large multi-step repository refactoring can be automated by delegating the implementation passes to a CLI for subagent-style execution, passing the scope and constraints via prompt context handoff. This reduces context cost and fatigue by orchestrating isolated non-interactive runs.

What is the best way to execute deep codebase exploration without exceeding my main context window?▼

Deep codebase exploration is handled by delegating the heavy lifting to a CLI in non-interactive mode with controlled output formatting. You provide the original goal, prior decisions, and verification expectations, allowing isolated runs to perform batch code edits.

How do I pass context and constraints for long-horizon planning to an autonomous CLI agent?▼

Long-horizon planning context is passed using prompt-based context handoff that includes the original goal, prior decisions, scope, constraints, and verification expectations. This cognition-style handoff ensures isolated automated runs stay aligned with the overarching repository objectives.

Can I run batch code edits in non-interactive mode with automatic approval and test verification?▼

Batch code edits can run in non-interactive mode with auto-approval by delegating repo-wide edits to a CLI. You enforce a verification command that the agent must pass before returning, ensuring guardrailed automation and reconciling results back into the main thread.

Does repo-wide code delegation support model selection for complex feature slices?▼

Repo-wide code delegation supports model selection to handle complex feature slices and migrations. It requires non-interactive programmatic CLI usage where you specify the chosen constraints and the exact test command the agent must pass.

When should I not use an orchestrator context pass for codebase migrations?▼

An orchestrator context pass is unnecessary for codebase migrations when a single pass is sufficient to cover the required changes. You should only use delegation for broad refactors and deep exploration where a single orchestrator context pass is insufficient.