← Back to Skills Marketplace
Kimi2.5skill
by
jiangwill2023
· GitHub ↗
· v1.0.0
· MIT-0
62
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install kimi2-5skill
Description
Troubleshoot and operate Kimi 2.5 / OpenClaw image understanding. Use when image recognition fails, OCR/images cannot be analyzed, `image` tool reports `Unkn...
README (SKILL.md)
kimi2.5skill
处理 OpenClaw 中 Kimi 2.5 / 识图模型的排障、恢复、验证与运维收口。
快速流程
- 先做 runtime 实测，不要只看配置文件
- 再检查：
~/.openclaw/openclaw.json~/.openclaw/agents/\x3Cagent>/agent/models.json
- 如果出现
Unknown model，优先怀疑 agent 级models.json的非法 provider 配置导致整份自定义模型注册表加载失败 - 修复后必须重启 gateway，并跑一张真实图片回归测试
参考文件
- 修复流程：
references/recovery-playbook.md - 本次事件：
references/incident-2026-04-14.md
本轮已验证结论（2026-04-14）
本轮问题的真实根因是：
agent 级
models.json中的自定义codexprovider 配置不合法，导致模型注册表加载异常，继而让imageruntime 报Unknown model。
已验证修复点：
/Users/admin-ai/.openclaw/agents/qiang/agent/models.json/Users/admin-ai/.openclaw/agents/sally-bot/agent/models.json
移除有问题的 codex provider 后，image 工具已成功返回图片描述，说明识图 runtime 恢复。
成功标准
以下同时满足才算修好：
- 不再出现
Unknown model image工具返回正常图片描述 / OCR 结果- gateway 状态正常
- 至少完成一张真实图片回归测试
收口口径
恢复后统一表述：
- 识图已恢复可用
- 根因是 agent 级
models.json非法 provider 配置污染了 image runtime 注册表 - 后续若再遇
Unknown model，优先检查~/.openclaw/agents/\x3Cagent>/agent/models.json
Usage Guidance
This is an ops playbook (no code) and it is internally consistent with its purpose. Before using it: 1) run the troubleshooting steps manually first (openclaw status, a real image test) to confirm symptoms; 2) back up any models.json files before editing; 3) inspect provider blocks for embedded credentials and handle them carefully; 4) avoid letting the agent perform edits and gateway restarts autonomously — run changes under a human operator or with appropriate access controls; 5) verify the paths referenced (they include examples like /Users/admin-ai) match your environment. If you want the agent to perform any edits automatically, restrict that to trusted, privileged agents and log all changes.
Capability Analysis
Type: OpenClaw Skill
Name: kimi2-5skill
Version: 1.0.0
The skill bundle consists of documentation and instructions for troubleshooting image recognition failures in OpenClaw. It guides the agent to inspect configuration files (e.g., ~/.openclaw/openclaw.json and agent-specific models.json) to identify and remove invalid provider blocks. The instructions are technically focused on maintenance and recovery, with no evidence of malicious intent, data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the skill is a runbook for troubleshooting image/OCR failures and directs checks of OpenClaw runtime and agent-level models.json files, restart of gateway, and regression tests — all coherent with the stated purpose.
Instruction Scope
Instructions explicitly tell the operator/agent to inspect and edit config files under ~/.openclaw and to restart the gateway and run the 'image' tool. That is expected for an ops playbook, but it does instruct reading and modifying user-specific files and performing privileged operations (restart/config edits) — these should be done under human supervision and with backups.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is written to disk or downloaded by the skill itself.
Credentials
The skill does not request environment variables or credentials. However, the referenced models.json/provider blocks could contain provider credentials in practice; the playbook's advice to remove provider blocks may expose or alter those secrets, so operators should back up files and confirm credential handling before editing.
Persistence & Privilege
always is false and the skill does not try to persist or modify other skills or global agent settings. Be cautious if the agent is allowed to invoke skills autonomously: following the playbook could involve automated edits and restarts if the agent acts without human oversight.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install kimi2-5skill - After installation, invoke the skill by name or use
/kimi2-5skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
kimi2.5skill 1.0.0
- Initial release with troubleshooting and operation guide for Kimi 2.5 / OpenClaw image understanding.
- Provides step-by-step runtime testing and configuration checks for image model failures.
- Documents recovery workflow for issues like `Unknown model` and outlines exact root cause from incident analysis.
- Includes verified resolutions, success standards, and standardized post-recovery messaging.
- Reference materials and example fixes are linked for user clarity and efficiency.
Metadata
Frequently Asked Questions
What is Kimi2.5skill?
Troubleshoot and operate Kimi 2.5 / OpenClaw image understanding. Use when image recognition fails, OCR/images cannot be analyzed, `image` tool reports `Unkn... It is an AI Agent Skill for Claude Code / OpenClaw, with 62 downloads so far.
How do I install Kimi2.5skill?
Run "/install kimi2-5skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Kimi2.5skill free?
Yes, Kimi2.5skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Kimi2.5skill support?
Kimi2.5skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Kimi2.5skill?
It is built and maintained by jiangwill2023 (@jiangwill2023); the current version is v1.0.0.
More Skills