productivity▌

State management and thread/message access layer for assistant-ui chat applications. \n \n Provides three runtime types: AssistantRuntime for overall state, ThreadRuntime for current conversation, and ThreadListRuntime for managing multiple threads \n Access state via useAuiState selectors and perform operations through useAui() API (append messages, cancel runs, edit/reload messages, query capabilities) \n Emit and listen to lifecycle events: thread.runStart , thread.runEnd , composer.send , an

Publication-quality scientific diagrams generated with AI and smart iterative refinement. \n \n Supports neural network architectures, system diagrams, flowcharts, biological pathways, circuit diagrams, and complex scientific visualizations through natural language descriptions \n Uses Nano Banana Pro for generation and Gemini 3 Pro for quality review, with smart iteration that stops early if quality meets the threshold for your document type (journal: 8.5/10, poster: 7.0/10, presentation: 6.5/1

AI-powered documentation search and Q&A for GitHub repositories via DeepWiki. \n \n Three command modes: ask natural-language questions about repository code and docs, browse wiki structure and topics, or read full documentation contents \n Supports single or multiple repositories (up to 10) in a single query for comparative analysis \n AI-generated answers are grounded in actual repository documentation, with minimum 1-minute timeout for response generation \n Works with any public GitHub

Trace downstream data lineage to assess change impact before modifying tables or DAGs. \n \n Identifies direct consumers of a target table or DAG through source code search, view dependencies, and BI tool connections \n Builds a full dependency tree mapping all downstream impacts, from tables to dashboards to ML models \n Categorizes dependencies by criticality (critical, high, medium, low) to prioritize stakeholder communication and testing \n Generates an impact report with risk assessment, af

Sanitize code for secrets and artifacts, then create and publish GitHub releases with version tags. \n \n Two-phase workflow: Phase 1 runs blocking checks (secrets scan with gitleaks, LICENSE/README validation, personal artifact removal) and stops on failures; Phase 2 creates version tags and publishes via gh CLI \n Requires gh CLI authenticated, gitleaks installed, and a Git repository with a remote configured \n Includes non-blocking checks for build success and dependency vulnerabilities, plu

Enforces Sentry conventional commit format with proper types, scopes, and issue references. \n \n Requires feature branch creation before committing to main or master; uses the create-branch skill to manage branch workflow \n Supports 12 commit types (feat, fix, ref, perf, docs, test, build, ci, chore, style, meta, license) with clear subject line rules and footer patterns for issue references \n Includes Co-Authored-By attribution for AI-generated changes and handles breaking changes with expli

Side-by-side backtesting comparison of multiple trading strategies on the same symbol. \n \n Compares user-specified strategies (or defaults to ema-crossover, rsi, donchian, supertrend) against the same historical data and NIFTY benchmark \n Supports \"long-vs-short\" mode to test longonly, shortonly, and both directions for a given strategy \n Uses TA-Lib for standard indicators and OpenAlgo ta for specialty indicators like Supertrend and Donchian; cleans signals with exrem() to avoid consecuti

Vision-driven browser automation using your real Chrome browser, preserving sessions and login state. \n \n Operates entirely from screenshots without requiring DOM access; interacts with all visible elements regardless of technology stack \n Connects to desktop Chrome via Midscene Extension through Chrome DevTools Protocol, never taking over mouse or keyboard \n Supports multi-step workflows including navigation, form filling, data extraction, UI testing, and screenshot capture \n Requires visu

Search A-Share/HK/US stock tickers and retrieve historical price data (OHLCV).

6 production-ready project management skills with Atlassian MCP integration.