Yash-Kavaiya

Test-phase skill for pi-forge. Use during the Test phase to run the project's test suites (unit, integration, contract, E2E for the general path), capture results and coverage, write artifacts/test-report.md, and record metrics via forge_metric.

Safe bridge to the cxas CLI for pi-forge CXAS projects. Use whenever a CX Agent Studio project needs to lint an app directory, run evaluations, manage apps/deployments, or migrate from Dialogflow CX. Always go through the forge_cxas tool (never raw shell); it enforces an allow-list and returns structured results.

Evaluate-phase skill for pi-forge. Use during the Evaluate phase to make a holistic, freeform judgment of the work against the brief, write artifacts/scorecard.md with an approve|iterate recommendation plus justification and risks, and record the verdict via forge_metric to inform the G2 gate.

First Build-phase skill for pi-forge. Use at the start of the Build phase to turn the approved brief into an executable plan. Reads artifacts/brief.json and writes artifacts/plan.md with the approach, module/feature breakdown (WBS), build sequence, and stack rationale.

Drives a project through the pi-forge delivery lifecycle (intake → clarify → build → test → evaluate → improve → deliver). Use when starting or continuing a pi-forge project, or whenever asked to "run the project", "continue the project", or after /forge-new. Reads state via forge_status and advances phases via forge_advance, opening gates with forge_gate.

Improve-phase skill for pi-forge. Use during the Improve phase after an iterate verdict to root-cause the scorecard findings, write a prioritized artifacts/backlog.md, and hand back so the orchestrator re-enters the Build phase (bounded by maxIterations).

Clarify-phase skill for pi-forge. Use during the Clarify phase to turn a raw request into a high-quality Project Brief. Scans for ambiguity across functional, non-functional, integration, data, user, edge-case, metric, and scope dimensions, asks batched categorized questions, and writes artifacts/brief.md + brief.json.

Second Build-phase skill for pi-forge. Use to implement the plan with strict test-first discipline by delegating to superpowers:test-driven-development. Reads artifacts/plan.md and brief.json, implements each acceptance criterion red-green-refactor, and makes conventional commits.

Manage advanced features in Google Dialogflow CX via REST API. Use for environments, webhooks, and deployment management. Supports v3beta1 API.

Manage agents in Google Dialogflow CX via REST API. Use for creating, listing, updating, and deleting chatbot agents. Supports v3beta1 API.

Manage conversations and sessions in Google Dialogflow CX via REST API. Use for testing intents, handling user interactions, and managing conversation state. Supports v3beta1 API.

Manage flows and pages in Google Dialogflow CX via REST API. Use for creating and organizing conversation paths within agents. Supports v3beta1 API.

Manage intents and entity types in Google Dialogflow CX via REST API. Use for creating, updating, and managing natural language understanding components. Supports v3beta1 API.

Create a long landscape 16:9 quiz/practice-test video from a CSV of multiple-choice / multi-select questions using Manim and Sarvam AI English voiceover. Brand theme is USER-SELECTED (never assume). Use when the user asks to "make a quiz video from a CSV", "practice test video", "manim quiz video", "MCQ video", "certification quiz video", or "turn questions CSV into a narrated video".

Production-level short-form vertical reels (9:16) with Manim animations + Qwen TTS voice cloning. Optimized for Instagram, TikTok, YouTube Shorts, and LinkedIn. Takes context/topic and produces complete voiced reels.

Create landscape 16:9 Manim videos from CSV question banks with NVIDIA branding and TTS voiceover

Dynamic, production-ready pipeline to convert any YouTube lecture playlist into a professional LaTeX PDF book. Supports configurable frame interval, deduplication threshold, number of lectures, and output formats.

End-to-end pipeline to create a professional LaTeX PDF book from a YouTube playlist of lectures. Includes frame extraction every 5s, perceptual deduplication, enhanced Markdown notes with Mermaid/TikZ, tables, code blocks, and master book compilation.

Extracts, edits, and creates viral short-form video reels (45-90 seconds) from long-form video files. Uses Gemini Embedding 2 for multimodal video understanding and scene selection. Adds animated captions synced to speech, background music, sound effects, and visual animations. Outputs 9:16 vertical format optimized for Instagram Reels, YouTube Shorts, and TikTok.

Generate production-ready Python callback code for Google Cloud CX Agent Studio agents. Use this skill whenever the user wants to write, create, or generate a callback for CX Agent Studio, Conversational Agents, or Dialogflow CX Playbooks. Trigger on any mention of "callback", "before_model_callback", "after_model_callback", "before_tool_callback", "after_tool_callback", "before_agent_callback", "after_agent_callback", "custom_payloads", "CallbackContext", "session variable update in callback", "guardrail callback", "input validation callback", "PII redaction callback", "tool chaining callback", or any request to hook into the agent execution lifecycle with Python code. Also trigger when the user says "write callback code", "add a callback", "callback for my agent", "intercept LLM call", "modify tool response", "inject context", or asks how to use callbacks in CX Agent Studio. Even if the user just says "callback" in the context of conversational AI or agent development, use this skill.

Convert quiz/practice-test CSV files (Udemy practice-test format or similar MCQ data) into professionally typeset, brand-themed LaTeX PDF books. Use this skill whenever the user wants to turn a CSV of questions into a PDF book, exam book, study guide, practice-test book, or question bank PDF — or mentions "LaTeX book from CSV", "themed PDF", or a company brand theme (NVIDIA, Databricks, Google, Microsoft, GitHub, Oracle, AWS, Claude/Anthropic, IBM, Meta, OpenAI, Salesforce, Intel, Hugging Face, or any other company). Trigger even if the user only says "make my quiz CSV into a nice PDF" without mentioning LaTeX.

Use when creating AI-topic short reels with branded Manim/LaTeX diagrams, on-screen text, and Sarvam AI voiceover. Builds a complete 9:16 video pipeline from topic to script, brand theme, synchronized voice, rendered MP4, subtitles, and verification.

Build production-grade frontend interfaces in Accenture's brand design language — the signature Accenture Purple (#A100FF) on black-and-white, bold Graphik-style typography, sharp angular shapes, the ">" greater-than mark, and purple→magenta gradients. Use this skill whenever the user asks for a UI, web page, component, dashboard, landing page, app screen, pitch microsite, or admin panel and wants it to look like Accenture, "on-brand for Accenture", an Accenture-style consulting/enterprise site, Accenture Song / Strategy & Consulting / Technology / Operations / Industry X, the "Let there be change" look, or asks for "Accenture purple", "Accenture brand", "Accenture theme", or a confident enterprise-consulting interface. Trigger this even when the user names a framework (Angular, React, Tailwind, shadcn) but clearly wants the Accenture look, and even if they only describe a bold, purple-accented, high-contrast corporate interface with big headlines.

Build production-grade frontend interfaces in Globant's design language — the "Green Book" brand. A signature bright-green palette (spring/mint through lime) used as gradient accents over a white-predominant canvas, near-black text, a bold modern sans-serif, the forward-pointing arrow motif, and delightful motion ("technology that dares to delight"). Use whenever the user wants a UI, web page, component, dashboard, landing page, app screen, or marketing site to look like Globant, "Globant brand", the "Green Book", "Globant green", a green-gradient aesthetic, or a bold, optimistic, forward-moving tech-consultancy look. Defaults to React; also supports framework-free HTML/CSS and any framework via the shared CSS tokens. Trigger even when the user names a framework (React, Angular, Vue) but wants the Globant look, and even if they never say "Globant" but describe a bright-green, gradient-accented, white-predominant, delight-driven interface.

Build production-grade frontend interfaces in Google's design language — Material Design 3 layered with the Google brand palette (Blue

Responsible AI evaluation CLI for CX Agent Studio (CXAS) using Hugging Face models. Evaluates CXAS agents for bias, safety, fairness, compliance with HF Inference API. Generates HTML/JSON/PDF reports with governance policy validation. Use when the user mentions responsible AI, bias testing, safety scoring, fairness metrics, compliance checks, RAI evaluation, or AI governance for CX Agent Studio agents.