ishandutta2007
- 60 skills
- 0 followers
- 16 repo stars
- last month last updated
- ▌ Ax Extract Workflow 2 · ishandutta2007Reconstructs the workflow behind a shipped artifact from ax session evidence, commits, and PR context. Use when asking what made a feature, fix, demo, or PR work, or when turning a past success into a repeatable recipe.
- ▌ Skill Porter · ishandutta2007Imports, converts, and optimizes external agent skills (Claude Code, Cursor, generic LLMs) into native Google Antigravity plugins and skills with parallel invoke_subagent arrays and artifact generation.
- ▌ Understand Project Yylo · ishandutta2007Inspects a repository's architecture, dependencies, and validation loops before planning or implementing a requested change, so agent edits stay grounded in how the product actually works. Antigravity port of the YYLO understand-project skill.
- ▌ Universal Clipboard Vision · ishandutta2007 bundleZero-click image inspection and multi-screenshot visual debugging directly from the native Windows system clipboard (Win + Shift + S) across Antigravity, Claude Code CLI, and Codex sessions without requiring developers to manually save temporary screenshot files to disk.
- ▌ Linkedin · ishandutta2007General-purpose LinkedIn automation – fetch profiles, search people and companies, send messages, manage connections, create posts, and more. Use when the user wants to interact with LinkedIn.
- ▌ Hermes Tweet · ishandutta2007Guides agents through safe Hermes Tweet X/Twitter plugin setup, read workflows, and explicit action gating. Use when installing Hermes Tweet, checking its Hermes Agent integration, or choosing read versus action tools.
- ▌ Video Router · ishandutta2007 bundleGuides agents to select and lock a video-production route. Use when a brief must be classified as generation, deterministic composition, footage editing, or an end-to-end combination before production, asset creation, editing, or rendering begins.
- ▌ Xquik Public Data · ishandutta2007Guides agents through safe Xquik public X data workflows using documented API, MCP, monitor, and webhook surfaces. Use when a task needs X/Twitter tweet, user, trend, list, community, article, monitor, or webhook data through Xquik.
- ▌ MCP Tool Integration · ishandutta2007Implementing and connecting Model Context Protocol (MCP) tools. Use when you need to extend an agent's capabilities with external data sources or execution environments.
- ▌ Eval Driven Development · ishandutta2007Building rigorous LLM evaluation pipelines. Use when developing AI features to ensure quality and prevent regressions across different model versions.
- ▌ Using Awesome AI Skills · ishandutta2007Discovers and invokes Awesome AI Skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Claude Skill Simplicity First · ishandutta2007Premium Claude Skill - Simplicity First. Bias towards the minimum code required to solve the problem. Prevents overengineering and speculative features.
- ▌ Claude Skill Surgical Changes · ishandutta2007Premium Claude Skill - Surgical Changes. Ensures edits are precise and minimally invasive. Matches existing style and avoids unrelated refactoring.
- ▌ Claude Skill Think Before Coding · ishandutta2007Premium Claude Skill - Think Before Coding. Forces explicit reasoning, surfaces assumptions, and handles ambiguity before implementation to reduce LLM mistakes.
- ▌ Claude Skill Goal Driven Execution · ishandutta2007Premium Claude Skill - Goal-Driven Execution. Transforms tasks into verifiable success criteria. Leverages the LLM's ability to loop until goals are met.