@ghyper9023/pi-dev-workflow 0.1.7

package/package.json

@@ -0,0 +1,40 @@
+{
+  "name": "@ghyper9023/pi-dev-workflow",
+  "version": "0.1.7",
+  "keywords": [
+    "pi-package"
+  ],
+  "description": "Developer workflow toolkit for pi: git agents, code review, Karpathy guidelines, themes",
+  "homepage": "https://github.com/cherish-ltt/pi-dev-workflow#readme",
+  "bugs": {
+    "url": "https://github.com/cherish-ltt/pi-dev-workflow/issues"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+ssh://git@github.com/cherish-ltt/pi-dev-workflow.git"
+  },
+  "license": "MIT",
+  "author": "ghyper9023",
+  "type": "commonjs",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "pi": {
+    "extensions": [
+      "./extensions"
+    ],
+    "skills": [
+      "./skills"
+    ],
+    "prompts": [
+      "./prompts"
+    ],
+    "themes": [
+      "./themes"
+    ]
+  }
+}

package/prompts/APPEND_SYSTEM.md

@@ -0,0 +1,12 @@
+## 必须严格遵守 - 全局适用
+
+### 语言
+
+- 使用**简体中文+英文专业名词**
+
+### task完成
+
+- 在完成task后不主动commit或push，但可以提醒用户：
+    1. review刚才的改动(输入/skill:review-html或1)
+    2. 提交commit，自动message(输入/git-commit或2)
+    3. 提交commit，自动message，并push(输入/git-commit-push或3)

package/prompts/review-commit.md

@@ -0,0 +1,2 @@
+Review代码，最近提交的内容(时间相差6小时以内的)，输出html，参照skill:review-html.
+Focus on: {{focus}}

package/prompts/review-diff.md

@@ -0,0 +1,2 @@
+Review代码，当前git-diff，输出html，参照skill:review-html.
+Focus on: {{focus}}

package/skills/karpathy-guidelines/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: karpathy-guidelines
+description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
+license: MIT
+---
+
+# Karpathy Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

package/skills/review-html/SKILL.md

@@ -0,0 +1,45 @@
+---
+name: review-html
+description: review 代码并输出交互式 HTML 报告。适用于代码审查，git-diff评审。
+---
+
+你是一个代码审查助手。用户要求你审查**当前代码库**的改动，具体包括：
+- `git diff` 相对于 HEAD 的所有未提交改动(未指明范围时默认行为，如diff无变动则默认最近1次commit,默认不允许探索整个代码库除非用户明确要求)
+- 最近 **2(或几个) 个 commit** 的完整改动（使用 `git log -p -n 2`）
+- 完整的整个代码库
+
+## 硬性输出要求
+
+**不要输出任何 Markdown 格式（包括代码块标记 ` ```html ` 等）**  
+**直接从 `<!DOCTYPE html>` 开始输出一个完整的、自包含的 HTML 文档。**
+**使用中文+英文专业名词**
+
+### review 的约束
+
+1. **BUG**：发现潜在bug，重要程度：最高。
+2. **敏感信息**：敏感信息泄露，敏感信息文件在gitignore忘记添加，重要程度：高。
+3. **可维护性**：代码解耦，结构清晰，冗余代码优化，重要程度：中。
+4. **规范**：代码规范，代码风格，重要程度：低。
+6. **语法糖**：适合当前语言的高阶语法帮助优化代码，维持原逻辑和无bug>性能提升大>可读性>性能提升可忽略>缩短代码行数，重要程度：低。
+7. **其他**：其他问题。
+
+### HTML 内容的约束
+
+1. **外观**：使用简单的现代 CSS（白/灰背景，清晰字体）。
+2. **交互**：如需：提供折叠/展开功能，便于快速浏览多个文件的审查意见。
+   - 默认只展示文件名称和问题数量，点击文件名可展开详细审查意见。
+3. **内容**：对于每个改动文件，至少包含：
+   - 文件路径
+   - 改动摘要（+/- 行数）
+   - 具体审查意见（潜在 bug、代码风格、可维护性等）
+4. **轻量**：不引用外部 CDN，全部内联（CSS,JS少量）。总 HTML 大小控制在 300 行以内(最大700行)，避免浪费 token。
+
+## 执行步骤
+
+1. 运行 `git diff` 获取未暂存/未提交的改动或运行 `git log -p -n 2` 获取最近 2 个 commit 的详细改动或查看完整项目。
+2. 合并上述改动，按文件分组。
+3. 对每个改动文件进行审查，并生成上述 HTML。
+
+请立即输出 HTML 文件到项目根目录的pi-review文件夹(没有则创建，同时添加文件夹到gitignore)，不要加任何解释性文字,不需要输出大量md说明，简短说明工作完成和输出文件即可。
+HTML文件名称格式：年月日时分-任务简述(极简10词以内)-index.html，有同名则index+1。
+如果review未发现必须需要修改(重要程度>=中)的问题，如果改动未提交，则html简约输出只说明改动总结即可，无需交互，并在开头附带规范的git-commit信息便于用户提交。

package/themes/claude-code-theme.json

@@ -0,0 +1,90 @@
+{
+	"$schema": "https://raw.githubusercontent.com/earendil-works/pi-mono/main/packages/coding-agent/src/modes/interactive/theme/theme-schema.json",
+	"name": "claude-code-theme",
+	"vars": {
+		"amber": "#c9a84c",
+		"amberBright": "#dbb85a",
+		"violet": "#7c3aed",
+		"violetBright": "#a78bfa",
+		"green": "#4ade80",
+		"red": "#f87171",
+		"yellow": "#fbbf24",
+		"cyan": "#22d3ee",
+		"gray": "#6b7280",
+		"dimGray": "#4b5563",
+		"darkGray": "#374151",
+		"darkerBg": "#111827",
+		"darkBg": "#1f2937",
+		"midBg": "#1e1e2e",
+		"selectedBg": "#2d2d44",
+		"userMsgBg": "#1c1c2e",
+		"toolPendingBg": "#1a1a2e",
+		"toolSuccessBg": "#1a2e1a",
+		"toolErrorBg": "#2e1a1a",
+		"customMsgBg": "#221a2e"
+	},
+	"colors": {
+		"accent": "amber",
+		"border": "violet",
+		"borderAccent": "amberBright",
+		"borderMuted": "dimGray",
+		"success": "green",
+		"error": "red",
+		"warning": "yellow",
+		"muted": "gray",
+		"dim": "dimGray",
+		"text": "",
+		"thinkingText": "gray",
+
+		"selectedBg": "selectedBg",
+		"userMessageBg": "userMsgBg",
+		"userMessageText": "",
+		"customMessageBg": "customMsgBg",
+		"customMessageText": "",
+		"customMessageLabel": "violetBright",
+		"toolPendingBg": "toolPendingBg",
+		"toolSuccessBg": "toolSuccessBg",
+		"toolErrorBg": "toolErrorBg",
+		"toolTitle": "amber",
+		"toolOutput": "",
+
+		"mdHeading": "amberBright",
+		"mdLink": "violetBright",
+		"mdLinkUrl": "gray",
+		"mdCode": "amber",
+		"mdCodeBlock": "cyan",
+		"mdCodeBlockBorder": "dimGray",
+		"mdQuote": "gray",
+		"mdQuoteBorder": "dimGray",
+		"mdHr": "dimGray",
+		"mdListBullet": "amber",
+
+		"toolDiffAdded": "green",
+		"toolDiffRemoved": "red",
+		"toolDiffContext": "gray",
+
+		"syntaxComment": "#6b7280",
+		"syntaxKeyword": "#a78bfa",
+		"syntaxFunction": "#fbbf24",
+		"syntaxVariable": "#22d3ee",
+		"syntaxString": "#4ade80",
+		"syntaxNumber": "#f87171",
+		"syntaxType": "#2dd4bf",
+		"syntaxOperator": "#e5e7eb",
+		"syntaxPunctuation": "#9ca3af",
+
+		"thinkingOff": "darkGray",
+		"thinkingMinimal": "#4b5563",
+		"thinkingLow": "#6b7280",
+		"thinkingMedium": "#7c3aed",
+		"thinkingHigh": "#a78bfa",
+		"thinkingXhigh": "#c084fc",
+
+		"bashMode": "green"
+	},
+	"export": {
+		"pageBg": "#111827",
+		"cardBg": "#1f2937",
+		"infoBg": "#2d2d44"
+	}
+}