chore: 1.0.1 release

CHANGELOG.md

@@ -0,0 +1,30 @@
+# 更新日志
+
+[简体中文](CHANGELOG.md) | [English](CHANGELOG_EN.md)
+
+本项目遵循 [语义化版本](https://semver.org/lang/zh-CN/)。
+
+## [1.0.1] - 2026-08-06
+
+### 新增
+
+- Skill 工作流增加 **step0 本地前置检测**：生成前检查 Node.js 18+、npm/npx、python3，并提示需要 Chromium 系浏览器
+- 导出脚本在启动时检测 **Node.js 18+** 与 **npm**；缺失或版本过低时给出明确安装指引
+- CLI（`open-kimi-ppt-skills`）启动时校验 Node.js 主版本 ≥ 18
+- 缺失 **PyYAML** 时自动 `pip install --user pyyaml`（与 Pillow / websocket-client 行为一致）
+
+### 文档
+
+- 补充多 Agent / 多模型实测截图（ChatGPT·Codex + 5.6 Luna、Reasonix + DeepSeek、WorkBuddy 等）
+- 安装说明改为「自动 / 手动二选一」，并补充 Windows 路径说明
+- README 结构与示例图更新
+
+## [1.0.0] - 2026-08-05
+
+### 新增
+
+- 首次发布 `open-kimi-ppt-skills`
+- PPTD 生成 / 编辑 / 复刻，默认同时交付可编辑 PPTD 项目与 PPTX 成品
+- 浏览器侧导出 PPTX（嵌字体、淡入淡出切换），导出前可选多模态视觉质检
+- 本地在线 PPTD 编辑器（`npx open-kimi-ppt-skills serve`）
+- CLI 安装 Skill 到 `~/.agents/skills`（可用 `--target` 指定其他 Agent 目录）

CHANGELOG_EN.md

@@ -0,0 +1,30 @@
+# Changelog
+
+[简体中文](CHANGELOG.md) | [English](CHANGELOG_EN.md)
+
+This project follows [Semantic Versioning](https://semver.org/).
+
+## [1.0.1] - 2026-08-06
+
+### Added
+
+- Skill workflow **step0 prerequisite check**: verify Node.js 18+, npm/npx, and python3 before generation; note that a Chromium-based browser is required for export
+- Export scripts check **Node.js 18+** and **npm** at startup, with clear install guidance when missing or too old
+- CLI (`open-kimi-ppt-skills`) refuses to start when the Node.js major version is below 18
+- Auto-install **PyYAML** via `pip install --user pyyaml` when missing (same pattern as Pillow / websocket-client)
+
+### Docs
+
+- Added multi-agent / multi-model example screenshots (ChatGPT·Codex + 5.6 Luna, Reasonix + DeepSeek, WorkBuddy, and more)
+- Clarified install as “automatic or manual — pick one”, with Windows path notes
+- Updated README structure and example images
+
+## [1.0.0] - 2026-08-05
+
+### Added
+
+- Initial release of `open-kimi-ppt-skills`
+- PPTD create / edit / replicate, delivering both an editable PPTD project and a PPTX by default
+- Browser-side PPTX export (embedded fonts, fade transitions) with optional multimodal visual QA before export
+- Local in-browser PPTD editor (`npx open-kimi-ppt-skills serve`)
+- CLI to install the skill into `~/.agents/skills` (or another agent directory via `--target`)

bin/open-kimi-ppt-skills.js

@@ -8,9 +8,19 @@ import { fileURLToPath } from "node:url";
 import { startEditorServer } from "../lib/editor-server.js";
 
 const SKILL_NAME = "open-kimi-ppt";
+const MIN_NODE_MAJOR = 18;
 const packageRoot = resolve(dirname(fileURLToPath(import.meta.url)), "..");
 const sourceDirectory = join(packageRoot, "skills", SKILL_NAME);
 
+function assertNodeVersion() {
+  const major = Number.parseInt(process.versions.node.split(".")[0], 10);
+  if (!Number.isInteger(major) || major < MIN_NODE_MAJOR) {
+    throw new Error(
+      `Node.js ${MIN_NODE_MAJOR}+ is required; found ${process.version}. Install from https://nodejs.org`,
+    );
+  }
+}
+
 function printHelp(command) {
   if (command === "serve") {
     console.log(`Start the local PPTD editor and exporter.
@@ -138,6 +148,7 @@ function installSkill({ force, target }) {
 }
 
 async function main() {
+  assertNodeVersion();
   const options = parseArguments(process.argv.slice(2));
   if (options.help) {
     printHelp(options.command);

package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-kimi-ppt-skills",
-  "version": "1.0.0",
+  "version": "1.0.1",
   "description": "Unofficial reverse-engineered Kimi Slides skill for AI coding agents with local PPTD editing and PPTX export.",
   "license": "MIT",
   "author": "binaryify",

skills/open-kimi-ppt/SKILL.md

@@ -18,6 +18,15 @@ The .pptd format is a simplified abstraction layer over OOXML that follows basic
 
 ## PPT production workflow
 
+### step0. Check local prerequisites
+Default delivery includes PPTX export (and optional `npx open-kimi-ppt-skills serve`), which need a local toolchain. **Before generating**, verify:
+
+1. **Node.js 18+**: run `node --version`. If `node` is missing or the major version is below 18, **stop immediately**, tell the user to install Node.js 18+ from https://nodejs.org (or their OS package manager), and do not continue with PPTX export / `npx` until it is available. Only continue with PPTD-only output when the user explicitly opts out of PPTX.
+2. **npm / npx**: run `npm --version`. They ship with Node.js; if missing, treat Node.js as not installed correctly and guide the user to reinstall/fix PATH.
+3. **python3**: run `python3 --version` (on Windows, `python` may be the correct command). Needed for `export_pptx.py` / `export_images.py`.
+4. **Chrome / Chromium / Edge**: needed by `agent-browser` for PPTX export and visual QA. If export later fails with a browser-launch error, ask the user to install a Chromium-based browser.
+5. Soft deps are auto-handled by the scripts when missing: **PyYAML**, **agent-browser** (≥0.33.2 via npm), and for image QA **Pillow** + **websocket-client**. Network access to `www.kimi.com` and `statics.moonshot.cn` is still required at export time.
+
 ### step1. Read the context thoroughly
 Read **all files uploaded by the user**, the provided URLs, and the pptd format guide `reference/pptd.md` to fully understand the user's requirements.
 
@@ -144,8 +153,8 @@ When generating a PPT, adopt different production approaches for different user
    A project directory may be passed instead of the manifest only when it contains exactly one `.pptd` file.
    Existing output files are not overwritten unless `--force` is passed.
 7. Local export requirements and boundaries:
-   - requires `python3`, PyYAML, `npm`, `agent-browser`, Chrome/Chromium, and network access to `www.kimi.com` plus `statics.moonshot.cn`; the image-based visual QA step additionally requires Pillow, auto-installed with `pip --user` when missing;
+   - requires **Node.js 18+** (`node` / `npm` / `npx`), `python3`, a Chromium-based browser, and network access to `www.kimi.com` plus `statics.moonshot.cn`;
-   - before browser export, `export_pptx.py` checks `agent-browser --version`; when it is missing or below `0.33.2`, it installs `agent-browser@latest` globally with npm, then verifies the resulting version before continuing;
+   - before browser export, `export_pptx.py` checks Node.js 18+ and `npm`, then checks `agent-browser --version`; when `agent-browser` is missing or below `0.33.2`, it installs `agent-browser@latest` globally with npm; **PyYAML** is auto-installed with `pip --user` when missing; the image-based visual QA step additionally auto-installs Pillow and websocket-client the same way;
    - the PPTD document itself is provided to the public editor iframe through the localhost SDK bridge, not uploaded to a server-side PPTX conversion endpoint;
    - remote images, icons, or fonts referenced by the deck may still be fetched from their respective hosts;
    - local PNG/JPEG/GIF/SVG files inside the PPTD project are supplied to the iframe as data URLs;

skills/open-kimi-ppt/scripts/export_pptx.py

@@ -28,14 +28,6 @@ from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from typing import Any, Callable, Dict, Iterable, List, Optional, Sequence, Tuple
 
-try:
-    import yaml
-except ImportError as exc:  # pragma: no cover - environment diagnostic
-    raise SystemExit(
-        "PyYAML is required. Install it with: python3 -m pip install --user pyyaml"
-    ) from exc
-
-
 SKILL_DIR = Path(__file__).resolve().parent.parent
 HOST_TEMPLATE = Path(__file__).with_name("export_host.html")
 IMAGE_MIME = {
@@ -54,6 +46,8 @@ FADE_TRANSITION_XML = (
     '<p:transition spd="fast" advClick="1"><p:fade/></p:transition>'
 )
 MIN_AGENT_BROWSER_VERSION = (0, 33, 2)
+MIN_NODE_MAJOR = 18
+NODE_INSTALL_HINT = "Install Node.js 18+ from https://nodejs.org, then retry."
 
 
 class ExportError(RuntimeError):
@@ -69,6 +63,31 @@ def log(message: str) -> None:
     print(f"[open-kimi-ppt] {message}", file=sys.stderr, flush=True)
 
 
+def ensure_pyyaml() -> Any:
+    try:
+        import yaml
+    except ImportError:
+        log("PyYAML is required; installing pyyaml with pip --user")
+        process = subprocess.run(
+            [sys.executable, "-m", "pip", "install", "--user", "pyyaml"],
+            text=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,
+            timeout=300,
+        )
+        if process.returncode != 0:
+            raise ExportError(
+                "failed to install PyYAML with pip --user:\n"
+                f"{process.stdout[-2000:]}\n"
+                "Install it manually with: python3 -m pip install --user pyyaml"
+            )
+        import yaml
+    return yaml
+
+
+yaml = ensure_pyyaml()
+
+
 def parse_version(output: str) -> Tuple[int, int, int]:
     match = re.search(r"(\d+)\.(\d+)\.(\d+)\b", output)
     if not match:
@@ -76,6 +95,13 @@ def parse_version(output: str) -> Tuple[int, int, int]:
     return tuple(int(part) for part in match.groups())
 
 
+def parse_node_version(output: str) -> Tuple[int, int, int]:
+    match = re.search(r"v?(\d+)\.(\d+)\.(\d+)\b", output)
+    if not match:
+        raise ExportError(f"could not parse Node.js version from: {output.strip()}")
+    return tuple(int(part) for part in match.groups())
+
+
 def read_agent_browser_version(executable: str) -> Tuple[int, int, int]:
     process = subprocess.run(
         [executable, "--version"],
@@ -89,7 +115,42 @@ def read_agent_browser_version(executable: str) -> Tuple[int, int, int]:
     return parse_version(process.stdout)
 
 
+def ensure_nodejs() -> str:
+    executable = shutil.which("node")
+    if not executable:
+        raise ExportError(f"Node.js is not installed or not on PATH. {NODE_INSTALL_HINT}")
+
+    process = subprocess.run(
+        [executable, "--version"],
+        text=True,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        timeout=30,
+    )
+    if process.returncode != 0:
+        raise ExportError(f"node --version failed:\n{process.stdout[-2000:]}")
+
+    version = parse_node_version(process.stdout)
+    if version[0] < MIN_NODE_MAJOR:
+        raise ExportError(
+            f"Node.js {MIN_NODE_MAJOR}+ is required; found "
+            f"{'.'.join(map(str, version))} ({process.stdout.strip()}). {NODE_INSTALL_HINT}"
+        )
+
+    npm = shutil.which("npm")
+    if not npm:
+        raise ExportError(
+            "npm is not installed or not on PATH. "
+            f"npm ships with Node.js. {NODE_INSTALL_HINT}"
+        )
+
+    log(f"Node.js version: {'.'.join(map(str, version))}")
+    return executable
+
+
 def ensure_agent_browser() -> str:
+    ensure_nodejs()
+
     executable = shutil.which("agent-browser")
     version = read_agent_browser_version(executable) if executable else None
     if version is not None and version >= MIN_AGENT_BROWSER_VERSION:
@@ -100,7 +161,8 @@ def ensure_agent_browser() -> str:
     if not npm:
         reason = "not installed" if version is None else ".".join(map(str, version))
         raise ExportError(
-            f"agent-browser {reason}; npm is required to install agent-browser@latest"
+            f"agent-browser {reason}; npm is required to install agent-browser@latest. "
+            f"npm ships with Node.js. {NODE_INSTALL_HINT}"
         )
 
     current = "not installed" if version is None else ".".join(map(str, version))

skills/open-kimi-ppt/tests/test_export_pptx.py

@@ -22,17 +22,52 @@ class ExportPptxTests(unittest.TestCase):
     @patch.object(MODULE.subprocess, "run")
     @patch.object(MODULE.shutil, "which")
     def test_old_agent_browser_is_upgraded(self, which, run):
-        which.side_effect = ["/bin/agent-browser", "/bin/npm", "/bin/agent-browser"]
+        which.side_effect = [
+            "/bin/node",
+            "/bin/npm",
+            "/bin/agent-browser",
+            "/bin/npm",
+            "/bin/agent-browser",
+        ]
         run.side_effect = [
+            MODULE.subprocess.CompletedProcess([], 0, "v22.11.0\n"),
             MODULE.subprocess.CompletedProcess([], 0, "agent-browser 0.17.1\n"),
             MODULE.subprocess.CompletedProcess([], 0, "changed 1 package\n"),
             MODULE.subprocess.CompletedProcess([], 0, "agent-browser 0.33.2\n"),
         ]
         self.assertEqual(MODULE.ensure_agent_browser(), "/bin/agent-browser")
-        self.assertEqual(run.call_args_list[1].args[0], [
+        self.assertEqual(run.call_args_list[2].args[0], [
             "/bin/npm", "install", "-g", "agent-browser@latest"
         ])
 
+    @patch.object(MODULE.subprocess, "run")
+    @patch.object(MODULE.shutil, "which")
+    def test_missing_nodejs_raises_clear_error(self, which, run):
+        which.return_value = None
+        with self.assertRaisesRegex(MODULE.ExportError, "Node.js is not installed"):
+            MODULE.ensure_nodejs()
+        run.assert_not_called()
+
+    @patch.object(MODULE.subprocess, "run")
+    @patch.object(MODULE.shutil, "which")
+    def test_old_nodejs_raises_clear_error(self, which, run):
+        which.return_value = "/bin/node"
+        run.return_value = MODULE.subprocess.CompletedProcess([], 0, "v16.20.2\n")
+        with self.assertRaisesRegex(MODULE.ExportError, "Node.js 18\\+ is required"):
+            MODULE.ensure_nodejs()
+
+    @patch.object(MODULE.subprocess, "run")
+    @patch.object(MODULE.shutil, "which")
+    def test_missing_npm_raises_clear_error(self, which, run):
+        which.side_effect = ["/bin/node", None]
+        run.return_value = MODULE.subprocess.CompletedProcess([], 0, "v22.11.0\n")
+        with self.assertRaisesRegex(MODULE.ExportError, "npm is not installed"):
+            MODULE.ensure_nodejs()
+
+    def test_parse_node_version(self):
+        self.assertEqual(MODULE.parse_node_version("v22.11.0"), (22, 11, 0))
+        self.assertEqual(MODULE.parse_node_version("18.20.4"), (18, 20, 4))
+
     def test_fade_is_inserted_before_timing(self):
         source = (
             b'<?xml version="1.0" encoding="UTF-8"?>'