Fast Summary CLI
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md and install @user_b7e5c773/skill.
About this skill
Problem
When summarizing web pages, local documents, or YouTube videos, the workflow often fragments across browsers, file readers, transcript services, and model APIs. summary collapses that into one CLI path.
How It Works
It follows an input source → extraction/parsing → model summarization flow. Core capabilities include:
- Multiple inputs: URLs, local files, and YouTube links.
- Multi-provider models: use OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, or GEMINI_API_KEY; defaults to google/gemini-3-flash-preview when unset.
- Controlled output: --length supports short, medium, long, xl, and xxl; --max-output-tokens bounds token usage; --json returns machine-readable results.
- Extraction options: --extract-only for URLs only; --firecrawl auto|off|always enables Firecrawl fallback; --youtube auto uses Apify as a YouTube fallback when APIFY_API_TOKEN is set.
Optional configuration lives at ~/.summarize/config.json. FIRECRAWL_API_KEY can help with blocked sites, while APIFY_API_TOKEN can support YouTube extraction.
Boundaries
It fits engineering scripts, knowledge-base preprocessing, and automated summary pipelines. It is not intended for complex browser automation, logged-in sessions, paywalled deep crawling, or transcript-level video proofreading. YouTube and restricted web content depend on optional services and model context limits.
Use Cases
- Batch-extract key points from competitor blog URLs and export JSON for retrieval
- Read local Markdown docs in CI scripts and generate fixed-length summaries into reports
- Summarize YouTube tutorial links into local notes, with Firecrawl fallback for restricted pages
- Use --extract-only to pull body text from tech doc URLs, then pass to downstream LLM
Best For
- Backend engineers maintaining knowledge-base pipelines: need unified summarization of URLs and local docs into the store
- Ops engineers doing competitive analysis: need batch extraction of tech blogs and structured JSON export for BI consumption
- DevOps engineers writing CI/CD scripts: need automatic local-doc summarization written into build reports
- Technical writers doing content aggregation: need quick compression of YouTube tutorials and web articles into note material
Related Skills
Provides Bazi, Liu Yao, Qimen, Meihua, and date-selection guidance from classical references, with plain-language explanations and actionable suggestions.
Automatically classifies ideas and saves them as tagged, structured Markdown notes in a desktop inspiration library.
Manages Baidu NetDisk files under /apps/bdpan/, including uploads, downloads, sharing, search, and limited agent memory backup/restore.
Provides Evernote note creation, updates, search, clipping, notebook, and tag management via the official API for knowledge workflows.