productivity▌

An autonomous experimentation loop for any programming task. You define the goal and how to measure it; the agent iterates autonomously -- modifying code, running experiments, measuring results, and keeping or discarding changes -- until interrupted.

Installs and authenticates the Parallel CLI for agent integration. \n \n Provides two installation methods: automated install script or pip-based installation via pipx \n Includes authentication setup via parallel-cli login and verification commands to confirm successful installation \n Requires PATH configuration if the CLI binary is not automatically discoverable after installation \n

Comprehensive guide for building modular skills that extend Claude's capabilities with specialized knowledge and workflows. \n \n Skills are self-contained packages combining procedural instructions, tool integrations, domain expertise, and bundled resources (scripts, references, assets) to transform Claude into a specialized agent \n Follows progressive disclosure design: metadata always available, SKILL.md loaded on trigger, bundled resources loaded as needed to minimize context bloat \n Core

Generate images using ModelScope's Z-Image API with simple command-line prompts. \n \n Supports three API key configuration methods: hardcoded in script, command-line argument, or .env file in the scripts folder \n Accepts optional parameters for custom output filename and alternative model IDs \n Requires Python 3 with requests library and a ModelScope account with Alibaba Cloud binding for API access \n Returns 401 errors if the account lacks proper Alibaba Cloud setup; users must bind their a

Pragmatic coding standards emphasizing conciseness, single responsibility, and direct solutions. \n \n Covers five core principles: Single Responsibility, DRY, KISS, YAGNI, and the Boy Scout rule for incremental code improvement \n Provides naming conventions for variables, functions, booleans, and constants designed to self-document intent without excessive comments \n Enforces function discipline: max 20 lines, one level of abstraction, minimal arguments, and no unexpected side effects \n Incl

nansen-wallet-batch

Ship anything to production — AI agents, APIs, backends, bots, MCP servers, frontends, webhooks, workers, and more.

Configure server URLs to receive real-time events from Vapi during calls — transcripts, tool calls, status changes, and end-of-call reports.

Triage and review Google Workspace security alerts from Alert Center. \n \n Lists active security alerts with table formatting for quick overview \n Retrieves detailed information for specific alerts by ID \n Acknowledges alerts to mark them as reviewed or resolved \n Requires the gws-alertcenter skill as a prerequisite \n

Bulk enrichment of company, people, or product data with web-sourced fields like CEO names, funding, and contact info. \n \n Accepts inline JSON data or CSV files; outputs enriched results to CSV \n Runs asynchronously with progress tracking via monitoring URL and polling commands \n Requires parallel-cli tool and internet access; handles large datasets with configurable timeouts \n Supports flexible field requests through natural language intent descriptions (e.g., \"CEO name and founding year\