QianJinGuo/wiki

rss-to-wiki-pipeline

精选高价值 RSS feeds 扫描，输出到 raw/rss-inbox/ 暂存区。只保留有独立知识深度的 feed（非 digest 类），不再自动入库。包含 rss-inbox-curl-recovery.py 绕过 blogwatcher read-state 漏抓的兜底。

Source text: Mixed languages

wiki-pipeline

Meta-orchestrator that wires web-content-reviewer, llm-wiki, and wiki-evolver into a single four-phase knowledge pipeline (Triage → Gate → Store → Evolve). Use as the single entry point for all knowledge base operations. Includes a 6-URL-validated user-pasted…

newsletter-link-extractor

从 Gmail 中提取 TLDR AI 等 newsletter 的链接，写入 raw/email-inbox/candidates.md，供后续 inbox-screener 评分。只做链接不做评分，与 inbox-screener 配合使用。

wiki-status-report

Generate periodic status reports for the Obsidian wiki — gather directory stats, discover recently committed entities, extract publish metadata from raw articles, and format a deliverable report. Covers daily/weekly cron-driven automation and ad-hoc health…

we-mp-rss-troubleshooting

Diagnose and fix common we-mp-rss Docker container issues: container exited state, Docker Desktop not running, proxy misconfiguration, QR code auth failure, cookie expiry, cascade worker registration failure, ContentTaskQueue stuck (Playwright anti-bot → api…

wiki-cron-pipeline-reconciliation

Audit cron batch-script runs for silently dropped inputs.

wiki-entity-expansion

Expand thin but high-value wiki entities with deep analysis, practical insights, and verified cross-references. Use subagents for parallel expansion of multiple entities. Covers subagent prompt design, cross-reference validation, and lint safety.

llm-provider-resilience

Use when LLM provider flakiness breaks cron jobs or probes.

wiki-entity-creation

Create wiki entity pages from raw articles (verified links).

wiki-maintenance

Comprehensive wiki operations on the Obsidian wiki at ~/wiki — routine maintenance (frontmatter, tags, lint, orphans, git), content expansion (concepts, entities), batch quality sprints, and crisis repair (YAML corruption, citation gaps, duplicate…

inbox-screener

扫描 raw/ 下的 inbox 目录（rss-inbox/、wechat-inbox/、newsletter-candidates.md），对每篇候选文章调用 web-content-reviewer 评分，≥49 触发 llm-wiki 入库。统一管理所有自动抓取源的文章筛选。

Source text: Mixed languages

hermes-admin

Diagnose, maintain, and optimize Hermes Agent internals — session database, disk usage, cleanup, gateway operations, delegation config, and live desktop DOM inspection (CDP).

remote-server-deployment

将 Node.js 服务部署到远程服务器（如 HP 192.168.0.111）的模式。涵盖 rsync 同步、npm 离线安装、systemd 服务管理、Cloudflare Tunnel 暴露、网络受限环境下的镜像配置，以及已吸收的 Next.js Docker 部署与 cloudflared Tunnel 深度操作指南。

Source text: Chinese

wiki-frontmatter-fence-repair

Restore YAML frontmatter fences stripped by bulk wiki edits.

wechat-mp-interface-restriction-200013

Use when WeChat returns ret=200013. Split-test then fix.

upstream-ban-mirror-fallback

Upstream API ban (200013)? Mirror RSS + unban watchdog.

mkdocs-material-deployment

Deploy MkDocs Material sites to Docker, Cloudflare Pages, and GitHub Pages. Covers CSS loading bugs, directory flattening, nginx config, theme overrides, search index limits, multi-environment consistency, plus the wiki→book compilation pipeline…

cron-safe-git-metadata-extraction

Use when cron jobs extract new files and metadata from git.

wiki-entity-metadata-extraction

Use when extracting wiki entity vxc scores and dates.

cron-management

Comprehensive Hermes cron job management — heartbeat monitoring (detect stale jobs), prompt recovery (extract + modify + recreate), bottleneck diagnosis (why is inbox piling up), ground-truth fire verification, and error debugging (why did this cron error).…

wiki-data-file-verification

Verify wiki data-file patches: exec-load + regression.

macos-vision-ocr

Vision OCR on macOS for images, screenshots, figure panels.

life-screener

wiki-life 专用 inbox 筛选与评分入库。扫描 raw/inbox/{rss,newsletter,wechat}/，对每篇候选做 life 领域红线过滤 + DeepSeek 评分（v×c≥45）+ 领域相关性检查，过线则入库 raw/articles/+entities/concepts+index.md+log.md 并 git commit。区别于 wiki/inbox-screener（AI/ML 领域、v×c≥49）。

Source text: Chinese

chrome-mcp-server

Setup and configure Chrome MCP Server (hangwin/mcp-chrome) for browser automation via MCP

wechat-article-processor

从 Feishu / Chat 中接收 URL（单条或批量），拉取全文，生成 Wiki 实体。支持批量 URL 串行处理 + 即时进度反馈。微信双路径抓取：用户粘贴→Chrome MCP (CDP) → Hermes 内置浏览器兜底 → Playwright Profile；inbox 扫描→Jina→TinyFish→Playwright→curl 兜底。小红书：Chrome MCP 提取文字区 ✅ → Jina Reader 兜底（Chrome MCP 断连 + 浏览器 IP 拦截时） → GitHub…

Source text: Chinese

wiki-book-gh-pages-deploy

Use when wiki-book 的 GitHub Pages 部署失败或 push 后无 run.

Source text: Chinese

manual-article-ingestion

Process a single URL into the wiki from start to finish.

claude-code

Delegate coding to CLI coding agents — Claude Code, Codex, OpenCode (features, PRs, review). Print/interactive orchestration, PTY dialog handling, session control, worktree parallelism, per-agent reference guides.

hermes-agent

Configure, extend, or contribute to Hermes Agent — CLI reference, slash commands, config keys, security toggles, contributor guide, and in-repo skill authoring (SKILL.md conventions + validator).

systematic-debugging

4-phase root cause debugging methodology (understand bugs before fixing) plus tool-specific guides: Python (pdb/debugpy/DAP), Node.js (--inspect/CDP), and CI/monorepo failure patterns.

gemini-2-5-pro-preview-analysis

Use Google's gemini-2-5-pro-preview model for deep analysis tasks including document analysis, code review, research synthesis, data interpretation, and multi-modal analysis. Trigger on requests like "analyze this", "deep dive", "research synthesis",…

skill-os-learning-skill-curation-self-evolving-agents

Use when implementing agent skill curation, self-evolving agent systems, or RL-based skill management. SkillOS framework for autonomous skill library optimization.

smtp-via-proxy

Send email via Gmail SMTP and read email via Gmail IMAP through HTTP CONNECT proxy (xray/v2rayN)

wechat-mp-rss-extractor

扫描 we-mp-rss 本地服务（localhost:8001）的全部微信订阅号 RSS feed，提取全文文章到 raw/wechat-inbox/。Plan A: Chrome CDP（真实登录浏览器）→ Plan B: API/Playwright fallback → 占位文件。

Source text: Mixed languages

llm-wiki

Karpathy's LLM Wiki — build and maintain a persistent, interlinked Markdown knowledge base. Use for wiki ingest, query, lint, structural optimization, index/log repair, review queues, and durable synthesis pages.

wiki-audit-and-repair

Systematically audit and repair an Obsidian wiki/index: fix frontmatter drift, missing index entries, broken wikilinks, log rotation, and SCHEMA.md drift.

hermes-tool-corruption-pitfalls

Known Hermes tool corruption modes and their workarounds. Covers: execute_code read_file caching that returns stale placeholder content, write_file doubling line numbers, patch requiring 'path' parameter, terminal tool filename corruption from trailing…

content-fetching

Fetch and clean web content for the wiki — RSS discovery, HTML-to-markdown extraction, login-session browser (Playwright Profile + iPhone UA), Playwright Stealth headless (init_script patches), and cloud anti-detection browser (TinyFish). Five techniques…

wiki-auto-pipeline-recipes

实战经验集：wiki-inbox-scan cron 的全自动流水线调试记录。Tirith pipe_to_interpreter / lookalike_tld 双拦截；sibling subagent 竞态；Jina Reader mid-session outage 检测；MiniMax-M3 兼容性；send-report 587 fallback；re-serialization drift forensic；steady-state count delta；URL regex 锚定陷阱等。

Source text: Mixed languages

openmaic-deployment

UMBRELLA: Deploy, batch-generate, and maintain OpenMAIC (Next.js interactive classroom platform) — Docker local, Cloudflare Pages static, batch generation pipeline, build troubleshooting, TTS, subtitle overlay, video export, and the openmaic-pages static…