kimiBuild and debug Kimi API workflows for chat, coding, reasoning, and tool-calling with live model checks, retries, and safe routing.
Install via ClawdBot CLI:
clawdbot install ivangdavila/kimiRequires:
Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawic.com/skills/kimiAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Software development teams use Kimi to analyze code snippets, identify bugs, and suggest fixes through structured API workflows. It integrates into CI/CD pipelines for automated code quality checks, leveraging Kimi's coding agent capabilities and deterministic JSON outputs for reliable tool integration.
E-commerce or SaaS companies deploy Kimi to handle complex customer inquiries, such as troubleshooting technical issues or providing personalized recommendations. The skill routes chat workloads with retries and safety checks, ensuring reliable responses while redacting sensitive customer data before API calls.
Academic or market research firms utilize Kimi for long-context analysis of documents, generating summaries and insights. The skill manages structured outputs for reports, with workflows that verify model availability and handle migration from other AI providers to maintain consistency in research outputs.
Marketing agencies employ Kimi to create blog posts, product descriptions, and SEO-optimized content. The skill routes requests based on workload type, such as creative reasoning for ideation and deterministic JSON for structured metadata, ensuring high-quality output with cost-effective model usage.
Financial institutions use Kimi to extract and analyze data from reports, ensuring compliance with regulations. The skill applies strict schemas for machine-readable outputs and redacts sensitive information before sending prompts, with approval workflows for persistent local notes.
Offer a platform where businesses subscribe to access pre-configured Kimi API workflows for tasks like code debugging or customer support. Revenue comes from monthly fees based on usage tiers, with added value through integration support and compliance features like data redaction.
Provide consulting services to help companies migrate from other AI providers to Kimi, optimizing workflows for reliability and cost. Revenue is generated through project-based fees for setup, customization, and ongoing maintenance of Kimi-powered systems.
Develop and license white-label Kimi workflow tools that enterprises can rebrand for internal use, such as in HR for resume screening or in logistics for document analysis. Revenue streams include licensing fees and support contracts for customization and updates.
💬 Integration Tip
Start by verifying live model IDs via the /models endpoint before building workflows, and use the routing matrix to match Kimi models to specific tasks like coding or research for optimal performance.
Scored Jun 19, 2026
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...
Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.
Manage and use local Ollama models. Use for model management (list/pull/remove), chat/completions, embeddings, and tool-use with local LLMs. Covers OpenClaw sub-agent integration and model selection guidance.
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.