发现 Skills

Encodes technical requirements for rsyslog modules, including concurrency, metadata, and initialization.

Intelligent web scraping with a tiered approach: use requests for static pages, Playwright for dynamic pages, and Bright Data API as a paid last-resort anti-bot bypass. Use when the user needs to: (1) scrape/crawl web pages, (2) extract content from URLs, (3) download articles or web content, (4) convert web pages to PDF, (5) handle blocked or protected websites. Triggers: "crawl", "scrape", "fetch URL", "get content from".

Dynamic Epistemic Logic–based Theory-of-Mind (ToM) prompting skill, grounded in MindGames (EMNLP 2023 Findings) for structured epistemic updates and reasoning.

Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.

Help users upload local files to Runway for use as inputs to generation models

Analyze Go REST API projects using Echo, Gin, Chi, Fiber, or the standard net/http. Use when onboarding to Go web APIs, understanding routing patterns, analyzing middleware chains, reviewing handler implementations, examining request/response handling, identifying authentication patterns, and generating API endpoint documentation.

Analyze websites and domains using SimilarWeb traffic data. Get traffic metrics, engagement stats, global rankings, traffic sources, and geographic distribution for comprehensive website research.

Use when the GM needs quick in-play generation for Fate of Eberron — stat blocks, scene aspects, compel ideas, NPC names, complications, chase zones, or countdown clocks. Output only, no file writes.

Standards for managing server state (TanStack Query) and local client state (Zustand), and how they interoperate.

Calculates token usage and estimated API costs for Claude tasks by analysing prompt structure, context size, and expected output length — then checks against context window limits and suggests optimisations to reduce cost. Use whenever a user says "how much will this cost", "estimate tokens for my prompt", "is this too long for the context window", "optimise my prompt for cost", or "how do I reduce Claude API costs".

Map the blast radius before editing files in a JS/TS codebase. Use when about to edit files in an existing JS/TS project — especially unfamiliar files or files with many dependents. Do not use for new projects with no existing code, non-JS/TS codebases (Python, Go, Rust), or after changes have already been made (use vibe-check instead).

../../../engineering/helm-chart-builder/SKILL.md

You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.

Elite content marketing strategist specializing in AI-powered content creation, omnichannel distribution, SEO optimization, and data-driven performance marketing. Masters modern content tools, social media automation, and conversion optimization with 2024/2025 best practices. Use PROACTIVELY for comprehensive content marketing.

Observe and troubleshoot WhatsApp in Kapso: debug message delivery, inspect webhook deliveries/retries, triage API errors, and run health checks. Use when investigating production issues, message failures, or webhook delivery problems.

Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.

Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code generation, code review from different perspective. Actions: query, search, analyze, generate, review with Gemini. Keywords: Gemini CLI, second opinion, cross-validation, Google Search, web research, current information, parallel AI, code review, architecture analysis, gemini prompt, AI comparison, real-time search, alternative perspective, code generation. Use when: needing second AI opinion, searching current web information, analyzing codebase architecture, generating code in parallel, getting alternative code review, researching current events/docs.

When to use which senior-developer skill; senior engineer mindset index

Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Use when scraping Indian government portals, property tax systems, land records, ArcGIS services, ASP.NET WebForms sites, or any large-scale web data collection. Covers requests, Playwright, aiohttp, CAPTCHA solving, proxy rotation, resumable pipelines, and anti-detection. Triggers on: scrape, crawl, download portal data, extract records, bulk download, government website, CAPTCHA, ViewState, ArcGIS REST.

Create SEO-driven pages at scale using templates and data. Directory pages, location pages, comparison pages.

Fetches a GitHub issue, implements the fix, and verifies it. Use when user wants to fix an issue, implement issue changes, or resolve a bug.

Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle development — build, debug, test, optimize, ship. CLI-focused workflow. Use when building macOS apps, adding features, debugging, testing, or optimizing Mac applications.