54 skills · sorted by relevance
Review external integration points for breaking changes that could disrupt existing use. Examine app-server APIs, command-line parameters, configuration loading, and session resumption from saved records, continuing beyond the first issue to cover possible failure paths.
Repeat candidate searches and comparisons while keeping an append-only decision log. Record evidence, compare results with earlier winners, and check replay, freshness, and approval requirements before moving to live trading or production actions.
Manage firmware updates across IoT device fleets through staged rollouts. Check a small initial group for anomalies before expanding deployment, inspect rollout status, and roll back updates with explicit user approval for device changes.
Inventory feature flags, switches that control feature availability, and remove eligible flags with their unused code branches. Leave ongoing rollouts and experiments untouched, run verification checks, and prepare a pull request for human review.
Design and automate machine learning workflows from data preparation through training, validation, deployment, and monitoring. Provides guidance and templates for reproducible experiments, quality checks, gradual model rollouts, and restoring a previous model when problems occur.
Progressive delivery with Argo Rollouts and Flagger. Use when implementing canary deployments, blue-green deployments, or traffic shifting strategies.
The English summary is being prepared. Showing the original description.
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
The English summary is being prepared. Showing the original description.
Provides GitOps best practices for ArgoCD, Flux, Argo Rollouts, and progressive delivery strategies. Use when setting up GitOps workflows, configuring continuous delivery, managing Kubernetes deployments declaratively, or when user mentions 'gitops', 'argocd', 'flux', 'progressive delivery', 'reconciliation', 'argo rollouts', 'canary', 'sealed secrets'.
The English summary is being prepared. Showing the original description.
Manages ArgoCD Application sync waves and hooks through the ArgoCD REST API and Kubernetes custom resources. Uses kubectl diff and Helm template rendering to validate manifests before triggering progressive rollouts via Argo Rollouts.
The English summary is being prepared. Showing the original description.
Feature flag lifecycle management -- safe feature toggling, gradual rollouts, A/B testing patterns, flag cleanup strategies, and technical debt prevention. Covers LaunchDarkly, Unleash, OpenFeature, and custom implementations.
The English summary is being prepared. Showing the original description.
PostHog feature flags, rollouts, A/B testing. Use when implementing gradual rollouts, A/B tests, kill switches, remote configuration, beta features, or user targeting with PostHog.
The English summary is being prepared. Showing the original description.
Use when introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage rollouts, building kill-switch + circuit-breaker patterns, structuring evaluation contexts (user IDs, plan tier, region), or building flag-cleanup discipline. Triggers: LaunchDarkly / GrowthBook / Unleash / Flagsmith / OpenFeature, percentage ramp, sticky bucketing, kill switch wired to alerting, "we still have flags from 2 years ago", flag debt, OpenFeature provider, evaluation context, default value on provider failure. NOT for A/B test statistical analysis (separate skill), traffic-split routing at the edge, build-time bundler defines, or environment-based config.
The English summary is being prepared. Showing the original description.
Use when introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage rollouts, building kill-switch + circuit-breaker patterns, structuring evaluation contexts (user IDs, plan tier, region), or building flag-cleanup discipline. Triggers: LaunchDarkly / GrowthBook / Unleash / Flagsmith / OpenFeature, percentage ramp, sticky bucketing, kill switch wired to alerting, "we still have flags from 2 years ago", flag debt, OpenFeature provider, evaluation context, default value on provider failure. NOT for A/B test statistical analysis (separate skill), traffic-split routing at the edge, build-time bundler defines, or environment-based config.
The English summary is being prepared. Showing the original description.
Build and evaluate single-agent reinforcement learning experiments, where an agent learns actions from rewards. Use Stable Baselines3 to choose algorithms, create environments, monitor training, and save models with the normalization data needed for consistent evaluation.
Helps implement centralized settings management in Java with Azure App Configuration. Covers environment-specific settings, feature flags that control feature availability, and snapshots that preserve settings at a particular point in time.
Set up Kubernetes deployments with ArgoCD or Flux CD using GitOps, an approach that stores the desired system configuration in Git. Configure automatic synchronization, staged rollouts, secret management, and deployment workflows across environments or clusters.
Prepare employee communications for organizational changes, tool rollouts, and policy updates. Create announcements, audience-specific FAQs, manager talking points, and a communication calendar, while checking tone, channel choices, and sequencing against the change's impact.
Manage OpenKruise in KubeSphere, from extension installation to troubleshooting. Generate SidecarSet configuration for adding helper containers and CloneSet configuration for application updates, including in-place changes and staged rollouts, with commands to apply and verify each configuration.
Plan changes to Convex data structures while an app keeps running. The skill guides staged deployments, updates to existing records, and verification for required fields, type changes, and table restructuring using @convex-dev/migrations.
Analyze product usage in PostHog and manage experiments, dashboards, surveys, and feature flags, which control feature availability. Use connected tools to investigate user behavior and errors, run queries, and summarize findings with numbers and links.
Operate Iris jobs and tasks, from submission and monitoring to debugging and recovery. The skill also guides scheduling checks, coordination between clusters, controller deployments, development GPU or TPU reservations, and investigation of stuck CoreWeave pods.
Run Isaac for Healthcare workflows in a simulator using a learned policy or rule-based controller. Verify completed episodes through the final success summary, visible behavior, and recorded data, with checkpoint compatibility checks when a checkpoint is supplied.
Operate MySQL-compatible databases on PlanetScale with branching workflows, safe migrations, and production rollouts.
The English summary is being prepared. Showing the original description.
Implement feature flags for progressive feature rollout using LaunchDarkly, Unleash, or custom solutions. Control feature visibility, perform A/B testing, and enable trunk-based development. Use when implementing gradual rollouts, feature toggles, or experimentation platforms.
The English summary is being prepared. Showing the original description.