launch-nemo-rl
Provides a playbook for operating NeMo-RL recipes on Kubernetes through the nrl-k8s CLI. Covers ephemeral and long-lived RayCluster modes, run iteration, and debugging hung or failed training jobs.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides a playbook for operating NeMo-RL recipes on Kubernetes through the nrl-k8s CLI. Covers ephemeral and long-lived RayCluster modes, run iteration, and debugging hung or failed training jobs.
Provides techniques for defining interaction places and flows. Covers affordances, edge cases, and failure paths without committing to a visual form.
A cross-platform skill for agents such as WorkBuddy, OpenClaw, and Codex, covering topics, titles, covers, account diagnosis, publishing checks, performance reviews, and original writing. Installation is free; querying public content, comments, short-video scripts, or WeChat article data and generating images require a Lingzao API key.
Identifies Redis metrics for monitoring and alerting, including memory, connections, hit ratio, and throughput. Covers incident triage and query profiling with built-in commands, Redis Insight, and integrations such as Prometheus or Datadog.
Uses WHOIS, RDAP, DNS, historical records, and network lookups to identify domain registrants and operators. Supports phishing and brand-abuse investigations, domain disputes, vendor verification, and infrastructure attribution.
Handles Stage 3 of the Clinical ASR Flywheel by scoring a NeMo manifest. Produces a five-section KER leaderboard with diagnostics by ipa_source; ASR authentication is outside its scope.
Evaluates trader-memory-core state using realized profit and loss, losing-streak cooldowns, and weekly or monthly drawdown limits. Determines daily eligibility for new trade risk without external APIs.
Helps choose between product-led and sales-led growth, optimize activation, and build growth equations. Examines when product complexity calls for human assistance and includes a comparative sales-led revenue experiment.
Improves existing k6 tests using trend data and current documentation. Handles version migrations, service-related failures, script cleanup, and threshold updates, including follow-up changes from test investigations.
Uses behavioral self-enforcement to address convention drift, declining output quality, and forgotten rules in long sessions. Also targets context loss after compaction and during complex tasks with many tool calls.
Define a wireframe's layout before detailed visual design. Specify content priority, component placement, and annotations.
Provides techniques for shaping product strategy around user opportunities and business outcomes. Helps frame solution bets and test their riskiest assumptions at low cost.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name