kimi-use SKILL.md skillA
kimi-use from daymade/claude-code-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add daymade/claude-code-skills/kimi-use@git:20261031.1944e48Pins git:20261031.1944e48 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- daymade/claude-code-skills
- Path
kimi-use/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261031.1944e48, committed Oct 31, 2026
- First version recorded
- Sep 23, 2026
- Size
- 13,590 bytes
- Repository stars
- 1,519
- License
- MIT
Two scopes: (1) drives Kimi.app via computer-use for Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chat's built-in 深度研究 report; (2) kimi-cu macOS desktop-automation playbook — AX set_value / keyboard / click channel selection, foregrounding, AX-tree recovery, form & dialog recipes. Use for "用 Kimi 查" / "操作 Kimi 客户端" / "Kimi 插件" / "Kimi 深度研究" / driving any macOS desktop app (Electron/webview/native) via kimi-cu. Not for kimi.com browser automation (use kimi-webbridge) or…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# kimi-use — Kimi 桌面客户端的插件取数与 Chat 深度研究 ## 先选择执行分支 用 kimi-cu 操作 macOS 应用时，先读 [通用桌面操作法](references/kimi-cu-desktop-automation.md)，按当前应用自身的任务合同执行。只使用通用桌面分支的任务到该参考继续；下文 Kimi.app 的模式/模型、插件调用、计费与取数权威源复核不适用于其它应用的消息或报告读取。 需要 Kimi.app 官方插件或 Chat 深度研究时，再进入下方业务分支。 ## 在 Kimi.app 内按交付物选模式 | 要得到什么 | 客户端入口 | 结果判据 | |---|---|---| | 指定插件的字段、原始记录或接口能力 | **Work/Agent + K3 极致思考**，下文「插件取数循环」 | 实际调用插件的轨迹、带来源字段与独立权威源复核 | | 独立的长篇研究报告 | **Chat → 深度研究 + K3 极致**，见 `references/driving-kimi-app.md`「Chat 深度研究」 | 任务完成后的原始报告及附件、来源和承重断言复核 | 一次 Chat 深度研究实测产出了 Markdown 与图表 ZIP；**这不是 Work/Agent 插件取数成功的证据**。若同一任务要求两种结果，分别派发、保留各自原件和模式标签，不把报告当成插件接口回执。 ## 插件取数通道是什么 Kimi 桌面客户端（Kimi.app，`com.moonshot.kimichat`）自带一个插件生态：天眼查、同花顺 iFinD、财新数据、标普全球市场财智、恒生聚源、SEC、IMF、世界银行、学术数据库、法律数据库等。这些插件跑在**用户自己的登录态**上——不需要额外 API key，不需要爬虫，权限来自用户账号已有的订阅。**能访问不等于免费调用**：部分接口仍按次扣账户积分。 用 computer-use 驱动这个客户端的 GUI，agent 就把这一整排数据源变成了自己的取数通道。具体工具和输入方式以当前宿主加载的 API 为准，见 `references/driving-kimi-app.md`。 这个通道有两个不显而易见、且都付出过真实代价的性质，决定了本 skill 一半讲驱动、一半讲核验： …
Read the whole file at its exact version.
How to install
mdr add daymade/claude-code-skills/kimi-use@sha256:bb67931708c99ec7The line at the top of this page pins the label git:20261031.1944e48, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_jzk3duwsey63grym)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Sep 23, 2026 and Oct 31, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261031.1944e48 latest | 2026-10-31 | 1944e48 | 13,590 B | A | view · diff |
| git:20261007.27e06ab | 2026-10-07 | 27e06ab | 13,059 B | A | view · diff |
| git:20261002.e79bb41 | 2026-10-02 | e79bb41 | 13,125 B | A | view · diff |
| git:20260926.d9289a3 | 2026-09-26 | d9289a3 | 12,414 B | A | view · diff |
| git:20260925.e811e60 | 2026-09-25 | e811e60 | 11,454 B | A | view · diff |
| git:20260925.1fcf763 | 2026-09-25 | 1fcf763 | 10,409 B | A | view · diff |
| git:20260924.1aef26b | 2026-09-24 | 1aef26b | 10,460 B | A | view · diff |
| git:20260923.943df48 | 2026-09-23 | 943df48 | 10,410 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13590 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
daymade/claude-code-skills · 1,519 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jzk3duwsey63grym GET https://markdownregistry.com/api/v1/resolve?ref=daymade/claude-code-skills/kimi-use GET https://markdownregistry.com/api/v1/blob/bb67931708c99ec710c563d5b4fe066a94a6423099cb013d4a33d33844089260
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.