test-rate-limit教 OpenClaw 在自动化脚本、后台任务、CI/CD、无 TTY 环境等非交互场景中, 正确使用 Kimi Code CLI 的 `-p/--prompt`、`--print`、`--quiet`、`--wire` 等参数完成无头执行。 涵盖命令构造、自动审批控制、输出格式选择、会话管理、错误处理与安全护栏。
Install via ClawdBot CLI:
clawdbot install aiyouwolegequ/test-rate-limitGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 8, 2026
DevOps teams invoke `kimi -p "analyze this PR for bugs" --quiet` inside CI jobs to automatically analyze pull requests and post findings to the review thread. The headless `--quiet` flag returns a clean text result that scripts can capture directly without parsing interactive output.
Engineering teams run `kimi -w ./src -p "fix null pointer in main.py" --quiet --yolo` from a scheduled cron job to let the agent modify files and run shell commands without a TTY. The `--yolo` flag handles approvals automatically, but teams must scope it to a specific working directory and review diffs afterward.
Release managers generate changelogs by piping `kimi -p "generate CHANGELOG" --print --output-format stream-json` into a JSONL parser that extracts final content. This lets them integrate the output into release notes pipelines and other tooling that needs machine-readable results.
Tool builders launch `kimi --wire` as a long-running background server that IDE extensions and other agents connect to over the Wire protocol. This enables persistent, service-oriented access to Kimi capabilities without spawning a new process per request.
Teams use `--continue` or `--session ID` with `--print` to keep context across multiple automated refactoring steps within a build, while iterative modes like `--max-ralph-iterations` let the agent retry until a task succeeds or hits a cap.
Enterprises deploy Kimi CLI headless execution across their engineering org as a shared automation capability for code review, bug triage, and documentation generation. The skill enables consistent, scriptable invocation across many repos and pipelines.
CI/CD vendors bundle headless Kimi CLI execution as a value-added integration that automatically analyzes builds and posts structured findings. The stream-json output mode makes it easy to embed into existing pipeline dashboards.
A hosted service runs Kimi CLI in headless mode on behalf of customers for autonomous refactoring and test generation tasks in isolated sandboxes. Wire mode supports low-latency programmatic access for IDE and bot clients.
💬 Integration Tip
Always run `which kimi` and check login status before constructing commands, and default to `--quiet` unless the user explicitly needs process visibility; require explicit user confirmation before adding `--yolo` due to irreversible file and shell actions.
Scored Oct 8, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.