Refine GitHub learning cards for Obsidian

Author: jjjojoj

.env.example

@@ -19,6 +19,8 @@ CONTENT_PROCESSOR_ANALYSIS_TIMEOUT=60
 
 # Optional output behavior
 CONTENT_PROCESSOR_OUTPUT_MODE=auto
+# auto = use Obsidian when CONTENT_PROCESSOR_OBSIDIAN_VAULT is configured, otherwise fall back to desktop.
+# Set this to obsidian if you want vault-only output with no desktop copy.
 # Supported output targets are desktop reports and Obsidian. Feishu / Wiki upload is out of scope.
 # CONTENT_PROCESSOR_OBSIDIAN_VAULT=/absolute/path/to/your/ObsidianVault
 CONTENT_PROCESSOR_OBSIDIAN_FOLDER=Inbox/内容摘要

CHANGELOG.md

@@ -24,8 +24,10 @@ The format is inspired by Keep a Changelog, and version tags follow the reposito
 - Unit tests now cover chat-completions parsing and knowledge-card note generation
 - Coding-plan analysis now defaults to `glm-4.7`, instead of probing `glm-5` first
 - BigModel / z.ai `chat/completions` summary requests now disable `thinking` by default so `glm-4.7` returns final answer text instead of reasoning-only payloads
-- GitHub cards now use repository-specific summaries, method checkpoints, branch tags, and category links instead of generic web-page sentence ranking
+- GitHub cards now use the exact repository name as the note title, student-learning sections, repository-specific summaries, method checkpoints, branch tags, and category links instead of generic web-page sentence ranking
 - Knowledge-card notes no longer dump full raw content for high-confidence web / GitHub captures; folded evidence is only shown for lower-confidence fallback cases or transcript-style media
+- Obsidian knowledge indexes now insert new cards under the correct date heading instead of appending entries into the wrong day block
+- README and `.env.example` now clarify that Feishu is unsupported and that `auto` output switches to Obsidian as soon as a vault path is configured
 
 ## [2.4.0] - 2026-04-19
 

README.md

@@ -7,7 +7,7 @@ English | [简体中文](./README.zh-CN.md)
 [![CI](https://github.com/jjjojoj/openclaw-content-processor/actions/workflows/ci.yml/badge.svg)](https://github.com/jjjojoj/openclaw-content-processor/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
 
-`openclaw-content-processor` is an OpenClaw skill and standalone CLI tool that takes one or more share links, extracts the useful content, and saves them as local Markdown + JSON outputs. It can now write directly into an Obsidian vault as knowledge-card notes by default, with the legacy digest layout still available when needed.
+`openclaw-content-processor` is an OpenClaw skill and standalone CLI tool that takes one or more share links, extracts the useful content, and, once an Obsidian vault is configured, writes them into the vault as knowledge-card notes by default. Legacy desktop output is kept only as a compatibility path.
 
 ![Report preview](./assets/report-preview.svg)
 
@@ -24,7 +24,7 @@ English | [简体中文](./README.zh-CN.md)
 - Obsidian export is now a first-class output mode, with YAML frontmatter and one note per source.
 - Douyin handling is more resilient: saved auth -> QR-login retry -> Playwright network interception fallback.
 - Temporary mp4 files used only for transcription are deleted automatically after the transcript is produced.
-- Feishu / Feishu Wiki upload is not supported in the current release. The supported output targets are local desktop reports and Obsidian vaults.
+- Feishu / Feishu Wiki upload is not supported in the current release. When an Obsidian vault is configured, the default output target is your Obsidian vault.
 
 ## Install In OpenClaw
 
@@ -137,13 +137,13 @@ When enabled, the skill reads the local `zai` provider from `~/.openclaw/opencla
 
 ### 3. Run it
 
-Desktop / local report mode:
+Recommended Obsidian flow:
 
 ```bash
 bash scripts/run.sh "https://github.com/openai/openai-python"
 ```
 
-Obsidian mode:
+Explicit Obsidian mode:
 
 ```bash
 bash scripts/run.sh \
@@ -249,7 +249,7 @@ Default desktop output root:
 ~/Desktop/内容摘要/YYYY-MM-DD/<timestamp>/
 ```
 
-Desktop mode produces:
+Legacy desktop mode can still produce:
 
 ```text
 report.md

README.zh-CN.md

@@ -7,7 +7,7 @@
 [![CI](https://github.com/jjjojoj/openclaw-content-processor/actions/workflows/ci.yml/badge.svg)](https://github.com/jjjojoj/openclaw-content-processor/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
 
-`openclaw-content-processor` 是一个 OpenClaw skill，也是一个可独立运行的命令行工具。它会接收一个或多个分享链接，按来源类型自动抓取、清洗、归纳，并输出本地 Markdown + JSON 结果。现在也支持直接写入 Obsidian Vault，默认生成 knowledge-card 单卡片笔记，同时保留 legacy digest 布局作为兼容模式。
+`openclaw-content-processor` 是一个 OpenClaw skill，也是一个可独立运行的命令行工具。它会接收一个或多个分享链接，按来源类型自动抓取、清洗、归纳，并在配置好 Obsidian Vault 后默认直接写入 Vault，生成 knowledge-card 单卡片笔记。桌面输出只保留为兼容路径。
 
 ![报告预览](./assets/report-preview.svg)
 
@@ -24,7 +24,7 @@
 - Obsidian 导出正式升为一级输出模式，支持 YAML frontmatter 和逐来源独立笔记。
 - 抖音链路更稳了：已有认证 -> 扫码登录重试 -> Playwright 网络拦截下载兜底。
 - 仅用于转写的临时 mp4 会在转写完成后自动清理，不再堆在输出目录里。
-- 飞书 / 飞书知识库上传不属于当前版本支持范围，当前支持的输出目标只有本地桌面报告和 Obsidian Vault。
+- 飞书 / 飞书知识库上传不属于当前版本支持范围；当你配置好 Obsidian Vault 后，默认输出目标就是 Obsidian Vault。
 
 ## 用 OpenClaw 安装
 
@@ -137,13 +137,13 @@ CONTENT_PROCESSOR_OPENCLAW_MODEL_REF=zai/glm-4.7
 
 ### 3. 直接运行
 
-桌面 / 本地报告模式：
+推荐的 Obsidian 工作流：
 
 ```bash
 bash scripts/run.sh "https://github.com/openai/openai-python"
 ```
 
-Obsidian 模式：
+显式 Obsidian 模式：
 
 ```bash
 bash scripts/run.sh \
@@ -249,7 +249,7 @@ python scripts/run_regression.py --preset core
 ~/Desktop/内容摘要/YYYY-MM-DD/<timestamp>/
 ```
 
-桌面模式会生成：
+兼容性的桌面模式仍然会生成：
 
 ```text
 report.md

SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: content-processor
 version: 2.4.0
-description: 处理用户分享的网页、公众号、知乎、CSDN、头条、YouTube、B站、抖音、小红书、微博、X/Twitter 等链接。当用户提到分享链接、多平台链接、内容摘要、汇总报告、整理链接、保存到 Obsidian、保存到桌面时触发。自动抽取内容并生成本地 Markdown + JSON 汇总结果，支持直接写入 Obsidian Vault。
+description: 处理用户分享的网页、公众号、知乎、CSDN、头条、YouTube、B站、抖音、小红书、微博、X/Twitter 等链接。当用户提到分享链接、多平台链接、内容摘要、汇总报告、整理链接、保存到 Obsidian 时触发。自动抽取内容并生成写入 Obsidian Vault 的 Markdown + JSON 结果。
 metadata:
   clawdbot:
     emoji: "🧾"
@@ -22,7 +22,7 @@ metadata:
 
 # Content Processor
 
-把用户给出的一个或多个分享链接整理成本地笔记。这个 skill 的主路径是本地落地：先抓取内容，再生成 Markdown + JSON 结果；如果配置了 Obsidian Vault，就直接写成 Obsidian 友好的 frontmatter 笔记。
+把用户给出的一个或多个分享链接整理成 Obsidian 笔记。这个 skill 的主路径是直接落到 Obsidian Vault：先抓取内容，再生成 Markdown + JSON 结果，并写成 Obsidian 友好的 frontmatter 笔记。
 
 当前正式发布版：`v2.4.0`