improve changelog skills

.agents/skills/version-release/SKILL.md

@@ -147,5 +147,8 @@ All release PR bodies (both Minor and Patch) must include a user-facing changelo
 - **User-facing**: Describe changes that users can perceive, not internal implementation details
 - **Clear categories**: Group by features, models/providers, desktop, stability/fixes, etc.
 - **Highlight key items**: Use `**bold**` for important feature names
-- **Credit contributors**: Collect all committers via `git log` and list alphabetically
+- **Emoji for features, not fixes**: Add an emoji prefix to each item in feature/enhancement sections (e.g. 🤖, 🧩, 🧠). Do NOT add emojis to items in the Stability/Fixes section — keep those plain.
+- **Section title emojis**: Add an emoji to each section heading (e.g. `### ✨ New Features`, `### 🤖 Models`, `### 🏗️ Architecture`). The Stability/Fixes section title should NOT have an emoji.
+- **Link PR numbers**: Every changelog item must include linked PR numbers in the format `([#12345](https://github.com/lobehub/lobehub/pull/12345))`. Use `git log main..canary --oneline` to extract PR numbers from commit messages, and collect GitHub usernames via `gh pr view <number>`.
+- **Credit contributors**: Collect all committers via `git log` and PR authors via `gh pr view`, list GitHub usernames alphabetically (exclude bots like `lobehubbot`)
 - **Flexible categories**: Choose categories based on actual changes — no need to force-fit all categories

.agents/skills/version-release/reference/changelog-example/weekly-release.md

@@ -4,43 +4,52 @@ A real-world changelog reference for weekly patch release PR bodies.
 
 ---
 
-This release includes **82 commits** , Key updates are below.
+This release includes **90 commits**. Key updates are below.
 
-### New Features and Enhancements
+### ✨ New Features and Enhancements
 
-- Added **Agent Benchmark** support for more systematic agent performance evaluation.
-- Introduced the **video generation** feature end-to-end, including entry points, sidebar "new" badge support, and skeleton loading for topic switching.
-- Expanded memory capabilities: support for memory effort/tool permission configuration and improved timeout calculation for memory analysis tasks.
-- Added desktop editor support for image upload via file picker.
+- 🤖 Added **Discord IM bot integration** for receiving and responding to messages within Discord channels. ([#12517](https://github.com/lobehub/lobehub/pull/12517))
+- 🧩 Introduced **Agent Skills** support with progressive disclosure via `lobe-tools`, allowing agents to expose task-specific capabilities. ([#12424](https://github.com/lobehub/lobehub/pull/12424), [#12489](https://github.com/lobehub/lobehub/pull/12489))
+- 🧠 Added **Memory Settings** for configuring memory effort and tool permissions. ([#12514](https://github.com/lobehub/lobehub/pull/12514))
+- 📧 Support for **changing email address** in profile settings. ([#12549](https://github.com/lobehub/lobehub/pull/12549))
+- 🛡️ Added **unsaved changes guard** to prevent data loss on navigation. ([#12332](https://github.com/lobehub/lobehub/pull/12332))
+- 🖱️ Support **Cmd+Click to open sidebar nav in new tab**. ([#12574](https://github.com/lobehub/lobehub/pull/12574))
+- 🧮 Added **calculator builtin tool** for agents. ([#11715](https://github.com/lobehub/lobehub/pull/11715))
 
-### Models and Provider Expansion
+### 🤖 Models and Provider Expansion
 
-- Added a new provider: **Straico**.
-- Added/updated support for:
-  - Claude Sonnet 4.6
-  - Gemini 3.1 Pro Preview
-  - Qwen3.5 series
-  - Grok Imagine (`grok-imagine-image`)
-  - MiniMax 2.5
-- Added related i18n copy and model parameter adaptations.
+- 🌟 Added **Kimi K2 thinking models** (Moonshot). ([#12630](https://github.com/lobehub/lobehub/pull/12630))
+- 🍌 Added **Nano Banana 2** support. ([#12493](https://github.com/lobehub/lobehub/pull/12493), [#12496](https://github.com/lobehub/lobehub/pull/12496))
+- 🎨 Added **Seedream 5 Lite** image generation model. ([#12459](https://github.com/lobehub/lobehub/pull/12459))
+- 💨 Added **Qwen3.5 Flash** and Qwen3.5 OSS models. ([#12465](https://github.com/lobehub/lobehub/pull/12465))
+- 🔮 Added **GLM-5**, **GLM-4.6V**, and **GLM-Image** for Zhipu. ([#12272](https://github.com/lobehub/lobehub/pull/12272))
+- 📦 Batch updated model lists for AI360, Hunyuan, InternLM, Spark, StepFun, Wenxin, and Seedream. ([#12371](https://github.com/lobehub/lobehub/pull/12371))
 
-### Desktop Improvements
+### 🏗️ Architecture
 
-- Integrated `electron-liquid-glass` (macOS Tahoe).
-- Improved DMG background assets and desktop release workflow.
+- ⚡ **Migrated frontend from Next.js App Router to Vite SPA** — a major architectural change improving dev experience and build performance. ([#12404](https://github.com/lobehub/lobehub/pull/12404))
+- 📂 Restructured SPA routes to `src/routes` and `src/router`. ([#12542](https://github.com/lobehub/lobehub/pull/12542))
+- ♻️ Refactored client agent runtime. ([#12482](https://github.com/lobehub/lobehub/pull/12482))
+
+### 🖥️ Desktop Improvements
+
+- 🔧 Fixed better-auth client stub for Electron renderer. ([#12563](https://github.com/lobehub/lobehub/pull/12563))
 
 ### Stability, Security, and UX Fixes
 
-- Fixed multiple video generation pipeline issues: precharge refund handling, webhook token verification, pricing parameter usage, asset cleanup, and type safety.
-- Fixed `sanitizeFileName` path traversal risks and added unit tests.
-- Fixed MCP media URL generation with duplicated `APP_URL` prefix.
-- Fixed Qwen3 embedding failures caused by batch-size limits.
-- Fixed multiple UI/interaction issues, including mobile header agent selector/topic count, ChatInput scrolling behavior, and tooltip stacking context.
-- Fixed missing `@napi-rs/canvas` native bindings in Docker standalone builds.
-- Improved GitHub Copilot authentication retry behavior and response error handling in edge cases.
+- Fixed topic/thread title summarization to respect `responseLanguage` setting. ([#12627](https://github.com/lobehub/lobehub/pull/12627))
+- Fixed MCP tool install loading state. ([#12629](https://github.com/lobehub/lobehub/pull/12629))
+- Fixed mermaid rendering in notebook documents. ([#12624](https://github.com/lobehub/lobehub/pull/12624))
+- Fixed global memory setting and tool enabled logic. ([#12610](https://github.com/lobehub/lobehub/pull/12610))
+- Fixed Vertex AI 400 error caused by duplicate tool function declarations. ([#12604](https://github.com/lobehub/lobehub/pull/12604))
+- Fixed multiple Vertex AI and Moonshot runtime issues. ([#12595](https://github.com/lobehub/lobehub/pull/12595))
+- Fixed SiliconCloud model thinking mode toggle. ([#10011](https://github.com/lobehub/lobehub/pull/10011))
+- Fixed model select panel flickering and improved list implementation. ([#12485](https://github.com/lobehub/lobehub/pull/12485))
+- Fixed memory tools to run in server correctly with correct cron schedule. ([#12471](https://github.com/lobehub/lobehub/pull/12471), [#12568](https://github.com/lobehub/lobehub/pull/12568))
+- Added username and fullName length validation. ([#12614](https://github.com/lobehub/lobehub/pull/12614))
 
-### Credits
+### 🙏 Credits
 
 Huge thanks to these contributors (alphabetical):
 
-@AmAzing129 @Coooolfan @Innei @ONLY-yours @Zhouguanyang @arvinxx @eaten-cake @hezhijie0327 @nekomeowww @rdmclin2 @rivertwilight @sxjeru @tjx666
+@Innei @arvinxx @canisminor1990 @cy948 @eaten-cake @eronez @hezhijie0327 @mikelambert @nekomeowww @rdmclin2 @sxjeru @tjx666