trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Install Codex skills into $CODEXHOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Comprehensive guide for using Claude Agent SDK to build AI agents that can read files, execute commands, edit code, and perform complex workflows. Use when (1) Building autonomous AI agents with Claude, (2) Creating agents that interact with codebases and file systems, (3) Integrating custom tools and MCP servers with…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Systematic methodology for reading and understanding large codebases efficiently. Use when (1) Understanding a new or unfamiliar codebase quickly, (2) Preparing to modify or extend existing code safely, (3) Debugging complex issues requiring deep code understanding, (4) Onboarding new team members to a codebase, (5)…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Guides developers through using cursor-agent CLI for interactive development, session management, and implementing development-verification loops. Use when working with cursor-agent, creating projects with agent supervision, managing chat sessions, or implementing agent-based development workflows.
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Guide for creating effective AGENTS.md files for Cursor. Use when (1) Creating new AGENTS.md files in project root, (2) Improving existing agent instructions, (3) Setting up project-specific coding guidelines, (4) Defining code style and architecture rules, (5) Writing simple agent instruction files as alternative to…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Browser automation in Cursor IDE using MCP protocol server cursor-ide-browser. Use when (1) Automating web interactions in Cursor IDE, (2) Navigating web pages, (3) Clicking buttons or links, (4) Filling forms or input fields, (5) Taking screenshots or capturing page snapshots, (6) Debugging web pages by checking…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Comprehensive DeepResearch methodology for conducting rigorous, traceable research projects with quality gates, structured analysis, and decision-ready deliverables. Use when (1) Conducting deep research projects requiring evidence-based analysis, (2) Managing research progress with quality gates and artifacts, (3)…
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
A short description of what this subagent specializes in.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Collection Strategist / Source Map Designer - Creates Source Maps, designs retrieval routes, controls collection costs. Uses source type complementarity, high-signal-first approach, and coverage thinking.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Devil's Advocate / Systematic Dissenter - Constructs counterfactual worlds, attacks evidence chains, identifies Kill Points. Uses adversarial intelligence assumption and failure-backward thinking.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Domain Expert / Context & Plausibility - Provides industry common sense boundaries, guides evidence priorities, identifies mechanistically wrong inferences. Uses mechanism testing and anomaly identification.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Editor / Storyliner / Decision Packaging - Packages research into usable deliverables. Uses conclusion-first structure, precise uncertainty expression, and reader bandwidth thinking.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Evidence Librarian / Sourcing & Traceability - Maintains Source Register and Evidence Table. Ensures every claim is traceable to sources with proper citations. Manages conflict evidence explicitly.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Analytic Methodologist / Reasoning Engineer - Selects and facilitates structured analysis techniques (ACH, Key Assumptions Check, Red Team). Ensures reasoning is replayable and bias-resistant.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
QA / Risk & Ethics / Gatekeeper - Performs tradecraft QA, compliance checks, risk assessment. Makes final Go/No-Go decision. Uses prevent-disasters-first and revocability thinking.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Data Analyst / Numbers & Consistency - Handles data cleaning, metric unification, sensitivity analysis. Ensures numbers are consistent, comparable, and uncertainty is properly expressed.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
Agent "research-lead" from trotsky1997/My-Claude-Agent-Skills, covering research lead / owner, core responsibilities, mental model, key outputs and quality gates.
trotsky1997/My-Claude-Agent-Skills
Agent Cursor
You are the Verification Expert responsible for verifying user-generated content, images, videos, and event materials. Your job is to ensure evidence is authentic and auditable.
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Convert documentation into structured Agent Skills following progressive disclosure principles. Use when (1) Converting user documentation or guides into skills, (2) Creating skills from existing technical documentation, (3) Organizing knowledge into skill format with references, (4) Applying skill design principles…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Comprehensive guide for using GitHub CLI (gh) to interact with GitHub from the command line. Use when (1) Managing GitHub repositories, issues, pull requests, or releases from terminal, (2) Automating GitHub workflows in scripts, (3) Creating or managing pull requests, (4) Working with GitHub issues, (5) Creating…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Comprehensive guide for developing Model Context Protocol (MCP) servers. Use when (1) Creating new MCP servers, (2) Implementing MCP tools and handlers, (3) Testing MCP servers, (4) Debugging MCP communication issues, (5) Setting up stdio-based MCP servers, (6) Setting up SSE (Server-Sent Events) based MCP servers…
trotsky1997/My-Claude-Agent-Skills
Skill Claude CodeCodex
Comprehensive guide for using Pixi, a fast and reproducible package management tool for Python, Rust, C/C++, and other languages. Use when (1) Managing Python project dependencies and environments, (2) Setting up reproducible development environments with conda and PyPI packages, (3) Creating cross-platform task…