Menu
Skills in this repository
SkillsMP has collected 106 skills from QianJinGuo/wiki. Open a skill to review its source and details.
QianJinGuo/wikiShowing 26 of 106 collected skills.
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…
Use when a scheduled poller/job currently advances a pipeline but never re-checks the artifacts it has already produced, and you need to add a read-only audit step that surfaces drift / structural problems / AI-taste regressions without mutating any files.
Execute plans via delegate_task subagents (2-stage review).
4-phase root cause debugging: understand bugs before fixing.
Write implementation plans: bite-sized tasks, paths, code.
Diagnose why wechat-mp-rss-extractor produces 0 new files - deleted articles (status=1000), slug collisions, and API refresh failures
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…
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…
Original design style library for anti-AI-taste HTML/PPT generation. 15,144 style seeds across 7 tiers (combinatorial expansion of 55 base movements × regions × media × moods × textures), each with DESIGN.md tokens + reference HTML + 8-dim rubric validation…
Author/validate/export Google's DESIGN.md token spec files. Includes a verified data-sources table for design-system evidence, a working rules-engine (Dieter Rams' Ten Principles) that scores HTML output against named design principles to catch AI-taste, AND…
Scan AWS China Blog historical articles beyond the 10-item RSS limit using HTML pagination. Covers 6+ months via /page/N/ URLs.
Source text: Chinese
Access Sapiens AI's multimodal models (Agnes AI platform) via OpenAI-compatible API. Covers agnes-2.0-flash (text), agnes-image-2.0-flash (image generation/editing), agnes-video-v2.0 (video generation), and agnes-image-2.1-flash.
Use Docker to reproduce GitHub Actions ubuntu-latest failures on a macOS dev machine, including Node version mismatches, shell-specific signal behavior (dash vs bash), native module mismatches, and pnpm strict install behavior. Validates fixes locally before…
Extract text from PDFs on macOS — tools, failure modes, and fallbacks for image-based, linearized, and xref-corrupted PDFs. Includes verification-first triage for ingestion decisions when extraction fails.
在代理环境下通过 browser OAuth 完成 rclone Google Drive 授权
Source text: Chinese
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
smolagents v2: lightweight Hugging Face agent framework for building LLMs with tool use, code execution, and multi-agent workflows.
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
Create, read, edit .pptx decks, slides, notes, templates.
实证对比 Jina Reader、Playwright、Obscura 在文章抓取场景下的表现。结论：Jina 最适合 cron 任务，Obscura 尚未成熟。
Source text: Chinese
Use when building AI systems with algorithmic rigor: treat prompts, agents, and pipelines as defined algorithms with inputs, outputs, invariants, and measurable correctness criteria.
Use when integrating OpenRouter API, optimizing LLM routing, managing API costs, or troubleshooting OpenRouter requests.
Use before any creative work - creating features, building components, adding functionality, or modifying behavior - guides through exploration, questioning, design proposal, and spec documentation before any implementation
Source text: Chinese
Use when generating architecture/concept diagrams for entities in ~/wiki/entities/. Produces Excalidraw files (.excalidraw), Mermaid diagrams, and optional AI-generated cover images. Scans entities to score visualizability, lets the user pick candidates, then…
Evolve a mature Markdown wiki into a research and practice engine. Use for frontier mapping, paper/practice backlog generation, dashboard updates, and repeated knowledge-vault improvement loops on top of llm-wiki.
Review candidate queue for wiki-pipeline Phase 1B gate — stores scored article candidates in ~/.wiki-review-queue.json with content dedup, TTL expiry, and reject cache. CLI: review-queue.mjs.