extraction-pipeline-patterns
Change or diagnose Xberg's core extraction orchestration, cache semantics, extractor fallback, post-processing, concurrency defaults, or format-wide quality…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Data & analytics
17,249 results
export-tweets-csv
Use when the user wants to export X (Twitter) data to CSV, JSONL, or XLSX. Covers exporting extraction results (tweets, followers, mentions, giveaway entrants)…
perfex-database
Use whenever the user writes SQL DDL for a Perfex CRM module, adds a foreign key referencing `tblcontacts`, `tblstaff`, `tblclients`, `tblinvoices`, or any…
firecrawl-scraper
Complete knowledge domain for Firecrawl v2 API - web scraping and crawling that converts websites into LLM-ready markdown or structured data. Use when:…
glmocr-formula
Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations,…
Comparable Sales Analysis
Finds and analyzes 5-10 comparable recent sales to estimate fair market value, calculate price adjustments, and score the property's value proposition
realestate-flip
Fix-and-Flip Analysis — purchase price, ARV, rehab budget breakdown, holding costs, selling costs, profit margin, ROI, timeline, and risk assessment with Flip…
flyscrape
Write and run web scraping scripts with `flyscrape`, the standalone CLI scraper with jQuery-like selectors. Use this skill when the user asks to scrape a site,…
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or…
rice-quant
RiceQuant RQData Python API - RiceQuant financial data Python interface, used to obtain China A-shares, Hong Kong stocks, futures, options, funds, bonds, macroeconomic and alternative data. Use this skill when writing quantitative trading and financial analysis Python code with rqdatac.
ar-status
Show experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going.
hologres-slow-query-analysis
Hologres slow query log analysis and diagnosis skill. Use for analyzing slow queries, failed queries, query performance diagnosis, and log management in…
company-deep-analysis
Listed company in-depth analysis skill. Use when the user requests in-depth analysis, comprehensive research, or investment value analysis of a company, including "analyze XX company", "do in-depth research on XX company", "research the investment value of XX company", "XX company in-depth analysis", "XX company comprehensive analysis", "help me do in-depth research on XX...
fund-deep-research
Conduct a comprehensive due diligence analysis of a single fund, automatically select the analysis path based on the fund type (equity/bond/hybrid/index), and output a four-dimensional diagnostic report covering performance, risk, holdings, and fund manager capability. Triggered when the user mentions analyzing a fund, how the fund is doing, whether it can be bought, fund diagnosis, fund due diligence, or whether this fund manager is reliable. Not used for portfolio holdings analysis of multiple funds (handled by portfolio-health-check).
pre-visit-credit-analysis
Pre-visit penetrating risk analysis skill. Integrates five major data dimensions: corporate business registration, judicial, public opinion, in-bank deposit and loan, and external credit reporting; identifies red-flag/yellow-flag signals and marks them one by one; generates a structured "pre-visit one-pager" to assist account managers in visiting with questions in mind and with a clear target. Used for pre-loan background investigation, pre-renewal risk assessment for existing customers, and visit preparation for non-performing early-warning customers. Trigger words include: "pre-visit analysis", "pre-visit background investigation", "pre-visit penetration", "pre-vis…
pre-visit-plan
Relationship manager pre-visit planning skill. Based on the customer's full data set (in-house systems, image archives, NFS files, risk alerts, industry information), systematically generate a pre-visit preparation report, covering customer fundamentals review, recent developments analysis, visit objective setting, material preparation checklist, communication strategy and risk alerts. Use this skill when the user requests generating a pre-visit preparation report, formulating a customer visit plan, organizing customer background materials, or planning a marketing visit strategy. Trigger words include: "pre-visit preparation...
stock-tech-analysis
Stock in-depth technical analysis skill. Professionally diagnoses the four core dimensions of trend, volume-price, support and resistance, and technical indicators, and, in combination with an individual stock's market capitalization scale (float size) and industry attributes, objectively judges the strength or weakness of stock price movements and key trading ranges. Use when users need in-depth technical diagnosis, reference buy and sell points, or analysis of trend strength.
query-optimize
Analyze and optimize SQL queries for better performance
streams
This skill should be used when the user asks about "Effect Stream", "Stream.from", "Stream.map", "Stream.filter", "Stream.run", "streaming data", "async…
tf-plan
Review a Terraform plan before applying it: destroys and replacements of data-bearing resources, secrets readable in plan output, out-of-band drift, blast…
confluent-architect
Historical publisher Agent-purpose summary: Discuss Confluent Cloud architecture,eCKU sizing,cluster linking,multi-region design,Schema Registry high availability,ksqlDB,stream governance and cost optimization. Old Skill original and install mapping are unverified.
interview-writer
AI interview-style content creation system. It is not written by a human, nor automatically written by AI, but rather AI analyzes and then interviews the person and writes in the person's style. Through Q&A, it continuously accumulates a user profile (viewpoints, writing style, thinking logic) and continuously iterates and evolves. It supports scenarios such as blogs, social media, and opinion articles.
pup
Use pup to query Datadog metrics and logs -- search, query, aggregate, list, and analyze observability data from the command line.
nvd-cve
Search the National Vulnerability Database for CVEs - find vulnerabilities by keyword or ID, get CVSS scores, weaknesses, affected configurations, and…