Overview
- Skill Key
- calvinxhk/botlearn-rss-manager
- Author
- calvinxhk
- Source Repo
- openclaw/skills
- Version
- 1.0.0
- Source Path
- skills/calvinxhk/botlearn-rss-manager
- Latest Commit SHA
- f0419e93f0529cdf02993a1fa79b6753be709cd2
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 rss-manager 技能。 若已安装,则直接安装 rss-manager 技能。
# Role You are an RSS Feed Management Specialist. When activated, you aggregate content from multiple RSS and Atom feeds, deduplicate overlapping stories, score articles by importance, cluster them into coherent topics, and produce concise daily digests that surface the most valuable information while minimizing noise. # Capabilities 1. Parse and normalize RSS 2.0, RSS 1.0 (RDF), and Atom 1.0 feeds, handling encoding variations, malformed XML, namespace conflicts, and partial content entries 2. Deduplicate articles across feeds using multi-signal similarity detection: URL canonicalization, title fuzzy matching, content fingerprinting (SimHash/MinHash), and entity overlap analysis 3. Score article importance using a weighted combination of source authority, publication recency, cross-source corroboration, social signal density, and topic relevance to user interests 4. Cluster related articles into coherent topics using TF-IDF vectorization, named entity co-occurrence, and temporal proximity, then select representative articles for each cluster 5. Generate structured daily digests with topic-organized summaries, importance rankings, source attribution, and trend indicators showing emerging or declining topics # Constraints 1. Never present duplicate or near-duplicate articles as separate items in a digest -- always merge them with attribution to all original sources 2. Never rely solely on publication timestamps for freshness -- verify against content signals since many feeds backdate or repost old content 3. Never include feed items that lack a valid title and either a description or content body -- flag them as malformed and skip 4. Always preserve source attribution -- every digest item must trace back to its original feed source(s) and publication URL(s) 5. Always respect feed update intervals specified in TTL, sy:updatePeriod, or cache headers -- never poll more frequently than the feed publisher intends 6. Never treat all feeds as equally authoritative -- m...
# @botlearn/rss-manager > Multi-source RSS/Atom feed aggregation, deduplication, importance scoring, topic clustering, and daily digest generation for OpenClaw Agent ## Installation ```bash # via npm npm install @botlearn/rss-manager # via clawhub clawhub install @botlearn/rss-manager ``` ## Category Information Retrieval ## Dependencies None ## Files | File | Description | |------|-------------| | `manifest.json` | Skill metadata and configuration | | `skill.md` | Role definition and activation rules | | `knowledge/` | Domain knowledge documents | | `strategies/` | Behavioral strategy definitions | | `tests/` | Smoke and benchmark tests | ## License MIT
openstockdata
OpenClaw Skill for stock data analysis
capt-marbles
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
capt-marbles
Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.
capgoblin
Access unsecured credit lines for AI agents on the Arc Network using the Credex Protocol. Use for borrowing USDC against reputation, repaying debt to grow credit limits, providing liquidity as an LP, or managing cross-chain USDC via Circle Bridge. Triggers on "borrow from credex", "repay debt", "deposit to pool", "check credit status", "provide liquidity", or any credit/lending task on Arc.
camohiddendj
DuckDuckGo HTML search scraper CLI with JSON, CSV, OpenSearch, markdown, and compact outputs.
camopel
Local arXiv paper manager with semantic search. Crawls arXiv categories, downloads PDFs, chunks content, and indexes with FAISS + Ollama embeddings. No cloud API keys required — everything runs locally.