Rewrite prompts, settings, tool loops, and structured output for Kimi K3 (model id kimi-k3, OpenAI Chat Completions compatible). Use when targeting Kimi K3 and you need reasoning_effort selection (low/high/max), strict json_schema structured output, tool-call / tool_call_id loop hygiene, automatic prefix caching, or removal of unsupported sampling controls. Triggers: 'adapt this for Kimi K3', 'prompt for kimi-k3', 'kimi k3 settings / reasoning_effort / json_schema / tool loop', or $prompting-...
Installs into .claude/skills of the current project.
Are you the author of Prompting Kimi K3?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/nexuslinkproductions-prompting-kimi-k3)
---
name: prompting-kimi-k3
description: "Rewrite prompts, settings, tool loops, and structured output for Kimi K3 (model id kimi-k3, OpenAI Chat Completions compatible). Use when targeting Kimi K3 and you need reasoning_effort selection (low/high/max), strict json_schema structured output, tool-call / tool_call_id loop hygiene, automatic prefix caching, or removal of unsupported sampling controls. Triggers: 'adapt this for Kimi K3', 'prompt for kimi-k3', 'kimi k3 settings / reasoning_effort / json_schema / tool loop', or $prompting-kimi-k3."
---
<!-- GENERATED:YURI-CODEX-SKILL-ADAPTER:v1 -->
# YURI skill adapter
Authoritative source: `skills/prompting-kimi-k3/SKILL.md`
Authoritative source SHA-256: `98497a39e27ee7cbdd685bc344cf73c2658b6065eeaee56da6251806e70e8a5b`
Source class: `canonical`
Before acting, read the authoritative source file above completely from beginning to end. If the governed source is absent, run `node _SYSTEM/Scripts/skill-recall.mjs --show prompting-kimi-k3` and read its complete verified output. Follow that source as the skill body; this adapter is a non-authoritative metadata-and-pointer projection.
