Altic Studio
altic-dev/altic-mcp
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
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…
Install Kimi Use
$ npx skills add daymade/claude-code-skills --skill kimi-use -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install daymade/claude-code-skills kimi-use --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/kimi-use .claude/skills/kimi-use && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "kimi-use" agent skill from https://github.com/daymade/claude-code-skills/tree/main/kimi-use into .claude/skills/kimi-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-use", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/daymade/claude-code-skills/tree/main/kimi-useType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add daymade/claude-code-skills --skill kimi-use -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install daymade/claude-code-skills kimi-use --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/kimi-use .agents/skills/kimi-use && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kimi-use" agent skill from https://github.com/daymade/claude-code-skills/tree/main/kimi-use into .agents/skills/kimi-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-use", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add daymade/claude-code-skills --skill kimi-use -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install daymade/claude-code-skills kimi-use --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/kimi-use .cursor/skills/kimi-use && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kimi-use" agent skill from https://github.com/daymade/claude-code-skills/tree/main/kimi-use into .cursor/skills/kimi-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-use", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/daymade/claude-code-skills.git --path kimi-use--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add daymade/claude-code-skills --skill kimi-use -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install daymade/claude-code-skills kimi-use --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/kimi-use .gemini/skills/kimi-use && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kimi-use" agent skill from https://github.com/daymade/claude-code-skills/tree/main/kimi-use into .gemini/skills/kimi-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-use", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install daymade/claude-code-skills kimi-useInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add daymade/claude-code-skills --skill kimi-use -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/kimi-use .github/skills/kimi-use && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kimi-use" agent skill from https://github.com/daymade/claude-code-skills/tree/main/kimi-use into .github/skills/kimi-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-use", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add daymade/claude-code-skills --skill kimi-use -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install daymade/claude-code-skills kimi-use --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/kimi-use .opencode/skills/kimi-use && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kimi-use" agent skill from https://github.com/daymade/claude-code-skills/tree/main/kimi-use into .opencode/skills/kimi-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-use", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
kimi-use- GitHub stars
- 1.4k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 394 words
- Files
- 5 (incl. references)
- Skills in repo
- 103
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- Works in 2 steps: 「已安装」≠「可调用」，且「不可调用」的证词依赖模式 × 模型。… → 答案是渲染在屏幕上的。 屏幕转录会静默抄错中文专名、会把截断当全量（实测：20…
- Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chats built-in 深度研究 report
- SKILL.md covers 先按交付物选模式, 插件取数通道是什么, 路由：什么时候用这条通道 and Step 0：驱动器检查（30 秒，不可省）, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Kimi Use is an agent skill from daymade/claude-code-skills. 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 setvalue / 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 direct iFinD API access.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/driving-kimi-app.md`, `references/kimi-cu-desktop-automation.md` and `references/plugin-capabilities.md`).
It sits in Productivity & Automation, covering Desktop control and Browser automation. It works with Kimi and macOS. The repository describes itself as: Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows. The licence is MIT.
When your agent uses it
- Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chats built-in 深度研究 report
- Kimi-cu macOS desktop-automation playbook — AX setvalue / keyboard / click channel selection
- AX-tree recovery
- Form & dialog recipes
Example prompts
- “用 Kimi 查”
- “操作 Kimi 客户端”
- “Kimi 插件”
- “/kimi-use”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- 「已安装」≠「可调用」，且「不可调用」的证词依赖模式 × 模型。 插件列表要打开客户端「插件 → 已安装」页才看得到；能不能调只能实跑探针。⚠️ 探针的否定结论只在 Work/Agent 模式 + K3…
- 答案是渲染在屏幕上的。 屏幕转录会静默抄错中文专名、会把截断当全量（实测：20 个股东名抄错 6 个、持股比例却逐位全对；「全 20 条」实为 50 条）。从这条通道落盘的数据，不过权威源复核不许写进交付物。
What it can do on your machine
Read from SKILL.md and the folder at commit 872127b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Kimi Use loads about 1.6k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 132 tokens; SKILL.md has 394 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from daymade/claude-code-skills at commit 872127b, republished under its MIT licence (© daymade). 394 words, ~1,631 tokens.
Download SKILL.mdSave it as
.claude/skills/kimi-use/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- kimi-use
- description
- 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 direct iFinD API access.
kimi-use — Kimi 桌面客户端的插件取数与 Chat 深度研究
先按交付物选模式
| 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：
- 「已安装」≠「可调用」，且「不可调用」的证词依赖模式 × 模型。 插件列表要打开客户端「插件 → 已安装」页才看得到；能不能调只能实跑探针。⚠️ 探针的否定结论只在 Work/Agent 模式 + K3 极致思考下取得才可信——Chat/快速模型（K2.6）下的「不可调用」证词实测被推翻过（详见能力边界页的万得条目）；肯定结果（真调到了、数据带来源标）不受此限。
- 答案是渲染在屏幕上的。 屏幕转录会静默抄错中文专名、会把截断当全量（实测：20 个股东名抄错 6 个、持股比例却逐位全对；「全 20 条」实为 50 条）。从这条通道落盘的数据，不过权威源复核不许写进交付物。
路由：什么时候用这条通道
有专用通道的先走专用通道——本 skill 是「没有专用通道时的宽面网关」，不是万能首选：
| 需求 | 走哪条 |
|---|---|
| 企业工商数据，且本机有专用 CLI（如 qcc） | 专用 CLI 为权威源；Kimi 天眼查插件当对照通道 |
| 有 iFinD 自己的账号凭据 | 直连 API 类工具（本机若装有 iFinD API skill/客户端）——结构化、无 GUI 开销 |
| A 股券商研报 | 先走东方财富研报公开 JSON API（reportapi.eastmoney.com，免费免代理、无 GUI 开销；参数与实测见 references/plugin-capabilities.md）；Kimi 侧恒生聚源当第二通道取并集——两条实测互不包含 |
| 驱动浏览器里的 kimi.com 网页版 | kimi-webbridge skill（Kimi Browser Extension 的 skill，不在本仓；本地 daemon，不走 GUI） |
| Kimi 客户端生成独立深度研究报告 | 本 skill 的 Chat 深度研究分支；不沿用插件探针的模式限制 |
| 用 kimi-cu 驱动任意 macOS 桌面应用（Electron / webview / 原生；表单填写、弹窗、前台化、AX 树恢复） | references/kimi-cu-desktop-automation.md——可靠性分层与操作配方，与 Kimi.app 业务无关、可独立使用 |
| 无凭据 / 只有插件形态的数据源 / 一次要横跨多个源 | 本 skill |
路由表管的是「默认该走哪条」；用户当面指定「就用 Kimi 查」时不挡路——Kimi 是取数通道、专用 CLI 是复核通道，两个角色不冲突。
环境边界：仅在 macOS 上实测过（Kimi.app 桌面客户端）。Windows 版 Kimi 客户端存在，但本流程未在 Windows 验证——在 Windows 上用时按「未验证」对待，先把驱动链路跑通再取数。
Step 0：驱动器检查（30 秒，不可省）
不同宿主和版本的驱动机制见 references/driving-kimi-app.md：
- Claude Code：computer-use 的 MCP 工具是 deferred tools——先
ToolSearch搜 "computer-use" 把它们加载出来，它们才出现在工具列表里。没搜就断言「这个环境没有 computer use」是事实错误；fallback 到osascript/screencapture不算 computer use，不要这么替代。⚠️ 可用性跟随当前 provider（2026-08-18 实测钉死）：切到 Kimi(k3) provider 的会话段，harness 会显式移除 computer-use 与 claude-in-chrome（mcp_instructions_delta removedNames记录在案）；同一会话切回 Anthropic provider 段，工具重新注入、实测 57 次真实调用全部跑在 Anthropic 模型下。所以 ToolSearch 搜不到时先查当前 provider——k3 段结构性没有，要开车就换 Anthropic 段的会话或换 Codex。搜索无果且 provider 无误 = 这个环境没配 computer-use：停下来报告用户、由用户决定配置，别降级冒充、也别当作已经查过了。 - Codex：先检查当前可用的 computer-use 工具。旧 computer 插件用
element_index；当前 CUA 的输入选择与发送检查按references/driving-kimi-app.md「文件输入与接收方确认」执行。只有可用接口都不存在或不可用时才报告环境阻塞。 - 确认 Kimi.app 已安装（
/Applications/Kimi.app）。登录态此刻确认不了——看屏幕的能力要第 1 步授权之后才有；打开后首屏停在登录页 = 没登录，停下来交给用户扫码。
Show full SKILL.md (174 more words)Show less
插件取数循环（仅 Work/Agent）
逐步操作细节（工具签名、坐标系、多显示器、产物路径）全部在 references/driving-kimi-app.md，这里是骨架：
- 请求访问并打开 Kimi.app（Claude Code 先
request_access拿授权）。⚠️ 授权是同机排他锁：同一时刻只有一个 session 持有，并行 session 会被拒；工具集没有释放接口——被拒先用list_granted_applications自查持锁者，等对方结束或请它代跑，别误判成「工具坏了」。 - 插件取数锁定 Work/Agent 模式 + K3 极致思考；不要用 Chat 的插件否定证词。 2026-08-18 用户针对插件取数要求不用 Chat：①Chat 模式有调不到插件的记录（点名 iFind 仍退回普通聊天复述公司简介）；②K2.6 快速模型没有完整金融插件面——用户同日对照实测：K2.6 声称「不可调用」的三个已装插件，在 K3 极致下同查询两个可调且返回接口细节；K2.6 自报的可用数据源枚举本身就不全。该限制不适用于上表的 Chat 深度研究。发送前在模型选择器读回「K3 极致」；当前两步选择法见
references/driving-kimi-app.md。Work 新建任务可在「选择项目」中选「不使用文件夹」；这样仍可能在 Kimi 自有任务目录产出文件，只有希望直接写进指定位置时才选隔离目录。先确认实际选项；若选了目录，任务产生的文件要收走归位。发出查询后按references/driving-kimi-app.md「发出后的确认检查点」核对实际调用；缺证据先查原任务，不直接重发。跑偏过的会话不要继续用。 - 打开「插件 → 已安装」页读权威列表（分类页是全量目录、含未安装项，两者别混）。选定本次查询要点名的插件。发送 Work 任务前，按 查询与核验纪律查到相关接口的
is_free、积分或收费规则；查不到就保留 unknown。登录态、插件已安装和用户要求“用 Kimi”都不等于任意扣点授权。若 Work 会自主选择收费/费用未知的子工具，又无法在每次调用前停下，而当前任务没有明确的调用范围和额度授权，不要发这个 Work 任务；改用能控制精确调用的通道或将该路线标记暂缓。提示词里的“不要付费”不能代替这道闸。 - 设计查询（模式库在
references/query-and-verification.md）：点名插件 + 诚实条款（「查不到就明说，不要用训练知识补」）+ 逐字段标来源 + 实体锚定（公司全称/股票代码）+ 时间口径。某插件/数据类型首次使用时，在完成上一步计费核验后，才发一个声明覆盖面内的探针查询。⚠️ 判读探针结果时分清「能力」与「承载它的东西」：会话里没出现该插件的 MCP 工具、或网关回 503，都不等于插件不可调用（实测两者各踩过一次，重试/换 helper 脚本后都取到了数）。 - 发出后轮询等待——任务彻底跑完再取，半截结果不入库。
- 提取产物：按
references/driving-kimi-app.md「提取产物」选择下载／导出或该任务的实际文件目录并核对原件。每次调用的查询参数、成功或失败的原始返回和实际积分消耗分别留存；失败重试用新文件名，不覆盖第一次失败。看到预览截断时先读已落盘的完整 CSV，再决定是否补查，避免为已返回的数据重复调用。 - 落盘前过权威源复核（见下方陷阱 2/3/4/6）：错有三层机制——屏幕转录抄错专名、Kimi 源头搞错数值、以及两条通道一致地落在同一个不是你要的口径上——所以承重的专名与承重的数值都要用独立通道复核，且复核要连口径一起核；Kimi 跑的间隙正好并行拉官方源（公告原文、交易所文件）。
- 落盘时标三样：数据源、口径（时点/报告期）、获取日期。改过的值保留「原始 + 校正」两层，不静默覆盖。
用真实数据换来的坑
每个都出自实测会话；战例与证据分放两处——references/plugin-capabilities.md（陷阱 1）与 references/query-and-verification.md（陷阱 2/3/4/6）：
- 「已安装」≠「可调用」 — 且「不可调用」的证词依赖模式 × 模型：Chat/K2.6 下的否定结论一律视为未验证。判断能力只能在正确模式+模型下实跑探针。
- 屏幕转录抄错中文专名 — 实测 20 个股东名抄错 6 个（形近/音近字错），数字逐位全对。「照抄值」纪律管不到这类错——值确实照抄了，错的是屏幕识别本身——只有换一个权威源才抓得住。
- 计数不是全量 — 屏幕上的「全 20 条」实为 50 条（截断）；而换到 API 通道也不解除这条：接口自己给的
hits: 10同样只是它索引到的数量，实测漏掉了另一条通道能找到的 10 篇。写「前 N 条」，覆盖类任务双通道取并集。 - Kimi 会硬错 — 实测它把某港股 IPO 的回拨比例写成 50%，官方公告是 20%。取数期间并行从权威源拉同一批数，落盘前对账。
- 没加载就断言没工具 — computer-use 是 deferred 的；先 ToolSearch，别 fallback 到 osascript。
- 两个通道一致，只证明它们对同一口径一致 — Kimi 的两个插件对同一年营收都给 1688.38 亿（逐位相同、同比也对），第三条独立通道的两家券商各自给 1720.54 亿；增速几乎相同、绝对值差 32.16 亿 = 口径差不是错（一个是二级科目「营业收入」，一个是市场通行口径）。财务数值落盘必须连科目层级与父级科目名一起记。
References
references/driving-kimi-app.md— Claude Code MCP、Codex 旧 computer 插件与当前 CUA 的驱动流；Work 插件取数与 Chat 深度研究的模式、安全和产物提取references/kimi-cu-desktop-automation.md— kimi-cu 通用桌面自动化操作法：可靠性分层（set_value > 键盘 > 点击）、前台化与 primary、AX 树恢复、表单/弹窗配方、投递验证references/plugin-capabilities.md— 插件清单快照、已实测的能力边界（带日期与证据级别）、券商研报的两条通道及其互不包含references/query-and-verification.md— 查询 prompt 模式库 + 数据核验纪律（含战例）
© daymade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (references) in kimi-use of daymade/claude-code-skills.
- SKILL.md
- references/driving-kimi-app.md
- references/kimi-cu-desktop-automation.md
- references/plugin-capabilities.md
- references/query-and-verification.md
Open the folder on GitHubat commit 872127b
Compare with similar skills
Kimi Use next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kimi Use this skilldaymade/claude-code-skills | 1.4k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Altic Studioaltic-dev/altic-mcp | 174 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Unicliolo-dot-io/Uni-CLI | 274 | — | ~3.8k | Automated safety check: Notes | Apache-2.0 | |
| Drive Screencoleam00/skills | 674 | — | ~5.4k | Automated safety check: Pass | MIT | |
| Browser MCP Agentantibrow/anti-detect-browser-skills | 17 | 1 repos | ~4.2k | Automated safety check: Warn | MIT | |
| Computer Usexuzhougeng/wisp-science | 1k | — | ~2.9k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Unicli
olo-dot-io/Uni-CLI
Comprehensive guide to Uni-CLI — the open Agent-Computer Interface runtime for real software.
Drive Screen
coleam00/skills
Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals.
Browser MCP Agent
antibrow/anti-detect-browser-skills
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…
Computer Use
xuzhougeng/wisp-science
Use Cua Driver through MCP to inspect and operate the user's native desktop apps on Windows, macOS, or Linux.
- Official
Electron App Automation
vercel-labs/agent-browser
Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port.
More from daymade/claude-code-skills
All 103 skills in this repoVideo Comparer
daymade/claude-code-skills
This skill should be used when comparing two videos to analyze compression results or quality differences.
CLI Demo Generator
daymade/claude-code-skills
Generates professional animated CLI demos as GIFs using VHS terminal recordings.
Doc To Markdown
daymade/claude-code-skills
Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing.
Interaction Design Board
daymade/claude-code-skills
Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation.
Auto Repo Setup
daymade/claude-code-skills
Diagnoses and repairs repository setup and guarded Git workflows for Claude Code or Codex — environment repair, startup sync, hook auditing, collaborator handoff.
Bigdata Skill
daymade/claude-code-skills
Pulls Bigdata.com (RavenPack) financial and news data via the official bigdata-client SDK and /v1/ REST endpoints — structured financials, prices, analyst estimates, entity-sentiment series…
Related
Categories
Questions about Kimi Use
What does Kimi Use do?
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…. Kimi Use is an agent skill from daymade/claude-code-skills.) and Chat's built-in 深度研究 report; (2) kimi-cu macOS desktop-automation playbook — AX setvalue / keyboard / click channel selection, foregrounding, AX-tree recovery, form & dialog recipes.
When should I use Kimi Use?
Kimi Use fits situations like: work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chats built-in 深度研究 report; kimi-cu macOS desktop-automation playbook — AX setvalue / keyboard / click channel selection; AX-tree recovery; form & dialog recipes.
How do I install Kimi Use in Claude Code?
Run `npx skills add daymade/claude-code-skills --skill kimi-use -a claude-code`. Or copy the skill folder (kimi-use in daymade/claude-code-skills) into .claude/skills/kimi-use in your project. Claude Code loads it when a task matches its description.
How do I install Kimi Use in Codex?
Run `npx skills add daymade/claude-code-skills --skill kimi-use -a codex`. Or copy the skill folder (kimi-use in daymade/claude-code-skills) into .agents/skills/kimi-use in your project. Codex loads it when a task matches its description.
Can I use Kimi Use in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add daymade/claude-code-skills --skill kimi-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kimi-use, .gemini/skills/kimi-use, .github/skills/kimi-use and .opencode/skills/kimi-use in your project.
What does Kimi Use need to run?
SKILL.md names no scripts, command-line tools or credentials: Kimi Use is instructions for the agent only.
Does Kimi Use access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Kimi Use safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Kimi Use use?
Kimi Use is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Kimi Use use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.
What are the alternatives to Kimi Use?
Skills that share tags, products or a category with Kimi Use: Altic Studio (altic-dev/altic-mcp, 174 stars), Unicli (olo-dot-io/Uni-CLI, 274 stars), Drive Screen (coleam00/skills, 674 stars) and Browser MCP Agent (antibrow/anti-detect-browser-skills, 17 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kimi Use?
daymade (a GitHub user) maintains it in daymade/claude-code-skills, which has 1,447 GitHub stars. The repository holds 103 skills in this directory. The repository was last updated on October 9, 2026.
Source: daymade/claude-code-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.