Results for “ecosystem”

Estimate calcium-normalized Gapon selectivity coefficients from paired exchange and solution chemistry, or initialize depth-explicit EcoSIM Gapon inputs from the closest bundled ecosystem template when paired chemistry is unavailable. Use when deriving or checking EcoSIM GKC4, GKCH, GKCA, GKCM, GKCN, or GKCK values; matching a target ecosystem, climate, vegetation, and management regime to a starting profile; remapping template values to target soil layers; or documenting that template-based values require calibration or tuning.

The English summary is being prepared. Showing the original description.

Marketing and promotion specialist for Claude ecosystem technology - MCP servers, skills, plugins, and agents. Expert in community engagement, registry submissions, content marketing, and developer relations. Activate on 'promote MCP', 'share skill', 'market plugin', 'launch agent', 'developer marketing', 'MCP registry'. NOT for creating MCPs/skills (use agent-creator), general marketing (use content-marketer), or SEO optimization (use seo-visibility-expert).

The English summary is being prepared. Showing the original description.

Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.

The English summary is being prepared. Showing the original description.

Automatically gathers the past 24 hours of activity from connected services into one morning dashboard, bringing together meetings, pending replies, tasks, and development updates in visual modules suited to each type of information.

• Reviewing activity across tools each morning
• Checking meetings and pending responses together
• Scanning development updates and alerts

Set up and customize Pi, a terminal coding agent framework. This skill guides model configuration, extension development, terminal interfaces, and integration with other applications through its SDK, a software development kit, or process messaging.

• Install Pi and configure model access
• Create custom tools and terminal interfaces
• Embed Pi in another application

Build quantum circuits with Qiskit, test them locally, and prepare them for IBM quantum hardware. The skill covers hardware-specific circuit conversion, sampling, expectation values, and analysis of measurement results, uncertainty, and resource usage.

• Building and simulating quantum circuits locally
• Adapting circuits to IBM quantum hardware
• Comparing sampled results and expectation values

Organize single-cell measurements with cell and gene metadata, read and write h5ad or Zarr files, and prepare subsets or combined datasets. Includes guidance on handling large annotated matrices without loading all measurement values into memory.

• Read and write h5ad or Zarr datasets
• Combine experimental batches with source labels
• Select cells or genes using metadata

Build voice skills for Amazon Alexa and plan an assistant that uses Claude for its intelligence. Covers integration with AWS services including Lambda, DynamoDB, Polly, Transcribe, and Lex, as well as Smart Home.

• Developing voice skills for Amazon Alexa
• Building an Alexa assistant that uses Claude
• Planning Alexa integrations with AWS services

Find autonomous AI agents, frameworks, and tools through AgentFolio. Compare their capabilities, intended users, integrations, and deployment options to shortlist existing products or gather examples and ideas before designing an agent of your own.

• Finding existing agents before building your own
• Shortlisting agent vendors for evaluation
• Researching competitors and market gaps

Guides contributors through adding a new programming language to Airflow, covering SDK structure, runtime coordination, communication rules, executable packaging, tests, and the documentation and configuration changes needed for a pull request.

• Adding support for a new programming language
• Choosing how Airflow launches a language runtime
• Implementing communication and executable bundles

Researches external facts with available web tools and prioritizes original sources. Produces a linked synthesis that checks dates and versions, separates facts from inference, and identifies questions the available evidence has not resolved.

• Checking release notes for recent changes
• Researching official documentation for a specific version
• Investigating earlier work and related approaches

Review PostgreSQL queries and data designs using execution plans, which show how queries run, and targeted index recommendations. Get guidance on JSONB, arrays, full-text search, analytical queries, extensions, and routine database maintenance.

• Investigating slow queries and choosing indexes
• Reviewing JSONB searches and full-text search
• Writing running totals and ranking queries

Design a partner program by defining value for your company, partners, and shared customers. Provides frameworks for partner tiers, phased pilots, joint marketing, and build-versus-partner decisions, with explicit measures for expanding or ending a partnership.

• Designing partner tiers and support levels
• Deciding whether to build internally or partner
• Defining pilot metrics and expansion criteria

Configure GitHub Dependabot to keep dependencies, the packages a project relies on, updated. Organize update pull requests into groups, set schedules and exclusion rules, and configure security updates across projects with multiple packages or package systems.

• Create or revise dependabot.yml
• Group dependency updates into fewer pull requests
• Configure updates across a monorepo

Analyze scheduled token releases, their recipients, and trading volume to estimate potential selling pressure. Review project treasury holdings, operating runway, and token supply growth to assess funding sustainability and the effect of dilution on staking yields.

• Reviewing token releases scheduled for the next 90 days
• Estimating selling pressure relative to trading volume
• Assessing treasury diversification and funding runway

Fine-tune large language models with LoRA and QLoRA while limiting GPU memory use. Guides training settings and adapter management, using small sets of task-specific weights that can be saved, switched, or merged into a base model.

• Fine-tuning an LLM with limited GPU memory
• Choosing LoRA settings and training layers
• Switching task-specific adapters on one base model

Adapt PyTorch training scripts for multiple GPUs or machines with Accelerate. This skill guides code changes, configuration, and launch commands, including mixed precision, which combines numerical formats, and DeepSpeed or FSDP integration for distributed training.

• Moving single-GPU training to multiple GPUs
• Configuring mixed precision training
• Setting up DeepSpeed or FSDP

Find the right specialist skill for a marketing question, coordinate content, SEO, advertising, and analytics tasks, or review gaps across current activities. Get recommended next steps or a campaign plan with a sequence and timeline.

• Choosing a marketing skill for a specific question
• Coordinating a product launch campaign
• Reviewing gaps and priorities across marketing activities

Check Agent Skills for documentation structure and Python script behavior, then score quality and security posture. Get grades and improvement priorities, and use pass criteria in pre-commit checks or continuous integration, which runs checks automatically.

• Checking a newly authored skill before release
• Auditing existing skills and prioritizing improvements
• Testing bundled Python scripts and sample outputs

Audit dependency files across eight language ecosystems for built-in vulnerability patterns, license conflicts, and indirect dependency risks. Generate a prioritized upgrade plan with testing and rollback notes, and pair results with live audit tools for current vulnerability coverage.

• Auditing third-party packages before a release
• Checking dependencies against built-in CVE patterns
• Reviewing license conflicts across dependency chains

Adapt existing PyTorch training scripts to run across multiple GPUs or machines with Accelerate. This skill covers device setup, distributed training configuration, and mixed precision, which uses lower-precision numbers to reduce memory use.

• Adapt a single-GPU training script for multiple GPUs
• Configure mixed precision to reduce training memory use
• Set up training with DeepSpeed or FSDP

Helps fine-tune large language models with LoRA and QLoRA, methods that train small sets of additional parameters. Covers memory-conscious training, configuration choices, saving adapters, and switching task-specific adapters on a shared base model.

• Fine-tune a model with limited GPU memory
• Choose LoRA settings for a specific task
• Switch task-specific adapters on one base model

Manage Hugging Face Hub through the hf command line tool. Download and upload models or datasets, organize cloud storage, manage authentication and local caches, run scheduled jobs, and deploy or maintain model inference services.

• Download or publish models and datasets
• Sync training checkpoints to cloud storage
• Inspect and clean the local cache

Refresh evidence behind paid advertising guidance by checking platform changes, APIs, policies, regulations, and benchmarks. Record sources and contradictions, flag outdated or unsupported claims, and propose updates grounded in current primary sources.

• Refreshing overdue advertising research
• Rechecking platform and API claims
• Reviewing evidence behind advertising benchmarks