All Skills

X/Twitter API integration: posting tweets and threads, reading timelines, search endpoints, analytics retrieval, OAuth 1.0a and 2.0 auth patterns, rate limit handling, and platform-native content formatting.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform voice and format constraints. Never posts identical content cross-platform.

Idiomatic Rust patterns: ownership, borrowing, lifetimes, error handling with thiserror/anyhow, trait design, concurrency with tokio, and performance optimization for safe systems programming.

Rust testing patterns: unit tests, integration tests, async testing with tokio::test, property-based testing with proptest, mocking strategies, and coverage measurement with cargo-tarpaulin.

Library-agnostic Flutter/Dart code review checklist: widget best practices, state management patterns across BLoC/Riverpod/Provider/GetX, Dart idioms, performance optimization, accessibility, security, and clean architecture.

Build automated AI-powered data collection agents for public sources: job boards, prices, news, GitHub, sports. Schedule scraping via GitHub Actions, enrich with LLM, store in Notion/Sheets/Supabase, and learn from user feedback.

Research-before-coding workflow: search for existing tools, libraries, and patterns before writing custom code. Invokes researcher agent to prevent reinventing solutions that already exist.

Capture architectural decisions as structured ADRs during development sessions: auto-detect decision moments, record context and alternatives considered, maintain a searchable ADR log for future developers.

Write articles, guides, blog posts, tutorials, and newsletter issues in a distinctive voice derived from supplied examples or brand guidance. Structure for credibility with evidence, examples, and clear takeaways.

Analyze an unfamiliar codebase and generate a structured onboarding guide: architecture map, key entry points, naming conventions, dependency graph, and a starter CLAUDE.md for AI-assisted development.

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, and newsletters. Adapt one source asset across platforms without cross-posting identical content. Content calendar generation and repurposing workflows.

Extract cross-cutting principles from skill libraries and distill them into reusable rule files. Scan skills for repeated patterns, consolidate into rule sets, and output as appendable rule definitions.

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Market sizing, competitor comparisons, fund research, and technology scans.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and use-of-funds tables. Maintains internal consistency across multiple fundraising assets.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications. Personalized, concise messaging for angels, VCs, strategic investors, and accelerators.

Multi-source deep research using web search and retrieval MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution for any research topic.

Instinct-based learning system: observe sessions via hooks, create atomic instincts with confidence scoring, project-scoped isolation to prevent cross-project contamination, promote universal patterns to global scope, and evolve instinct clusters into full skills.

Autonomous agent loop architectures from simple to complex: sequential pipelines, infinite agentic loops with quality gates, continuous PR loops with CI gates, de-sloppify cleanup passes, and RFC-driven multi-agent DAG orchestration with merge queues.

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher task completion rates.

Agentic engineering operating model: eval-first execution, task decomposition, cost-aware model routing by complexity, and structured agent workflow patterns.

Solves the subagent context problem via 4-phase iterative retrieval: dispatch with minimal context, evaluate gaps, retrieve targeted context, and re-dispatch. Prevents context overflow and starvation in multi-agent workflows.

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management patterns for enterprise deployments.

Quality gates, eval checkpoints, and recovery controls for continuous autonomous agent loops. Patterns for safe loop operation with stall detection and intervention hooks.

MCP server construction with Node/TypeScript SDK: tool registration with Zod validation, resource and prompt handlers, stdio vs Streamable HTTP transport selection, and transport-independent server architecture.