cosmix
UserA Rust-based agent orchestrator enabling a swarm of Claude Code instances building software.
Categories
Indexed Skills (50)
loom-grafana
Observability visualization with Grafana and the LGTM stack. Use for creating dashboards, configuring panels, writing LogQL/TraceQL queries, setting up data sources, dashboard variables/templates, and Grafana alerts. Do not use for PromQL (see loom-prometheus).
loom-accessibility
Web accessibility patterns, WCAG compliance, and inclusive design. Use when implementing accessible UI, keyboard navigation, screen reader support, focus management, semantic HTML, ARIA patterns, or auditing for compliance.
loom-api-design
Designs RESTful APIs, GraphQL schemas, and RPC interfaces for consistency, usability, and scalability. Use when defining endpoints, resource models, HTTP semantics, pagination, versioning, or RPC service contracts.
loom-api-documentation
Document REST APIs with OpenAPI/Swagger specifications, endpoint references, authentication flows, error handling, and SDK guides. Use for API reference docs, Swagger specs, interactive explorers, and client library documentation.
loom-argocd
GitOps continuous delivery with Argo CD for Kubernetes. Use when implementing declarative GitOps workflows, application sync/rollback, multi-cluster deployments, progressive delivery, or CD automation.
loom-auth
Authentication and authorization patterns including OAuth2, JWT, RBAC/ABAC, session management, API keys, password hashing, and MFA. Use for login flows, access control, identity management, tokens, permissions, and API key authentication. Do not use for vulnerability scanning (use loom-security-scan), audits (loom-security-audit), or threat modeling (loom-threat-model).
loom-background-jobs
Background job processing patterns including job queues, scheduled jobs, worker pools, retry strategies, and delivery guarantees. Use when implementing async processing, ETL pipelines, ML training jobs, cron schedules, or dead letter queues.
loom-before-after
Generates before/after verification pairs for loom plans. Proves a stage actually changed system behavior by capturing state before and after implementation. Use for delta-proof verification of new commands, endpoints, modules, or bug fixes.
loom-caching
Caching strategies for performance optimization — cache-aside, write-through, write-behind, TTL policies, eviction, and stampede prevention. Use for Redis/Memcached, CDN caching, database query caching, ML model caching, and distributed cache design.
loom-ci-cd
Designs and implements CI/CD pipelines for automated testing, building, deployment, and security scanning across GitHub Actions, GitLab CI, Jenkins, CircleCI, and cloud-native platforms. Covers pipeline optimization, test integration, artifact management, and release automation.
loom-code-migration
Strategies and patterns for safe code migrations and upgrades. Use when upgrading frameworks, migrating between technologies, handling deprecations, planning incremental rollouts, or applying automated codemods.
loom-code-review
Comprehensive code review covering correctness, maintainability, performance, security, and best practices. Use for PR reviews, pre-merge audits, architecture and design critique, and actionable reviewer feedback.
loom-concurrency
Concurrency and parallelism patterns for multi-threaded and async code. Use when implementing async/await, parallel processing, thread safety, worker pools, channels, or debugging race conditions and deadlocks across Rust (tokio), Python (asyncio), TypeScript, and Go.
loom-crossplane
Cloud-native infrastructure management with Crossplane via Kubernetes APIs. Use for building internal platform APIs, composite resources, XRDs, compositions, claims, provider configuration, and multi-cloud self-service provisioning.
loom-data-validation
Data validation patterns covering schema validation, input sanitization, output encoding, and type coercion. Use for form/API validation with Zod/Pydantic/Joi/JSON Schema, XSS and injection prevention, constraint checks, data pipeline and ML feature validation.
loom-data-visualization
Build effective charts, dashboards, and reports across analytics, infrastructure monitoring, and ML domains. Use for library selection, visualization UX, accessibility, and domain-specific dashboard design.
loom-database-design
Database schema and data model design for relational, NoSQL, time-series, and warehouse systems. Use for ERDs, normalization/denormalization, indexing, migrations, star/snowflake schemas, event sourcing, and OLTP/OLAP performance tuning.
loom-dead-code-check
Generate dead code detection configuration for loom plan verification across Rust, TypeScript, Python, Go, and JavaScript. Use when adding the dead_code_check field or dead-code acceptance criteria to a plan, or catching incomplete wiring where code exists but is never called.
loom-debugging
Systematic diagnosis and resolution of software bugs, test failures, data quality issues, and performance problems. Use for root-cause analysis, stack trace investigation, flaky/intermittent tests, regressions, crash triage, and "passes locally, fails in CI".
loom-dependency-scan
Scan project dependencies for CVEs, outdated packages, and license compliance across npm, pip, cargo, go, maven, and other ecosystems. Use for vulnerability scanning, SBOM generation, supply chain analysis, and automated dependency updates.
loom-diagramming
Create technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machines. Use for visualizing system design, data flows, C4 models, and process diagrams in documentation.
loom-docker
Docker and container expertise. Use for writing Dockerfiles, docker-compose files, multi-stage builds, layer optimization, image security hardening, networking, volumes, registries, and container debugging.
loom-documentation
Creates and maintains technical documentation including API docs, READMEs, architecture docs, changelogs, ADRs, and inline code comments. Use for any documentation task from code-level docstrings to project-level guides.
loom-e2e-testing
End-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer. Use for setting up E2E tests, debugging failures, improving reliability, and implementing browser automation with Page Object Model, selector strategies, network interception, visual regression, and flaky-test prevention.
loom-error-handling
Error handling patterns and strategies including Rust Result/Option, API error responses, data pipeline errors, and security-aware handling. Use for exception handling, error recovery, retry logic, circuit breakers, fallbacks, graceful degradation, error taxonomy, and designing error hierarchies.
loom-event-driven
Event-driven architecture patterns including message queues, pub/sub, event sourcing, CQRS, and sagas. Use for async messaging, distributed transactions, event stores, domain/integration events, data streaming, choreography/orchestration, delivery guarantees, or integrating with Kafka, RabbitMQ, Pulsar, SQS/SNS, or NATS.
loom-feature-flags
Feature flag patterns for controlled rollouts, A/B testing, kill switches, and runtime configuration. Use for feature toggles, gradual/percentage/canary rollouts, dark launches, user targeting, experiments, emergency kill switches, and model/infrastructure flag switching.
loom-fluxcd
GitOps continuous delivery toolkit for Kubernetes with Flux CD. Use for declarative deployments, Helm chart automation, Kustomize overlays, image update automation, multi-tenancy, and Git-based continuous delivery.
loom-git-workflow
Git operations guidance including branching strategies, commit conventions, merge workflows, conflict resolution, and worktree management. Use for any Git-related task from branch design to history rewriting.
loom-golang
Go language expertise for idiomatic, production-quality code. Use for Go development, concurrency patterns with goroutines and channels, error handling, testing, and module management following Effective Go principles.
loom-i18n
Internationalization and localization patterns for multi-language applications. Use when implementing translation systems, locale-specific formatting (dates, numbers, currency), RTL layouts, pluralization, or language switching with libraries like i18next, react-intl, FormatJS, or gettext.
loom-istio
Service mesh implementation with Istio for microservices traffic management, security, and observability. Use for mTLS, traffic routing, load balancing, circuit breakers, retries, timeouts, canary/blue-green deployments, A/B testing, and Envoy sidecar configuration.
loom-karpenter
Kubernetes node autoscaling and cost optimization with Karpenter. Use for node provisioning, spot instance management, cluster right-sizing, node consolidation, NodePool/EC2NodeClass configuration, disruption budgets, and multi-architecture support.
loom-kubernetes
Kubernetes deployment, cluster architecture, security, and operations. Use for manifests, Helm charts, RBAC, network policies, operators/CRDs, PodSecurityStandards, troubleshooting, and production best practices.
loom-kustomize
Kubernetes-native configuration management with Kustomize. Use for environment-specific configs, resource patching (strategic merge, JSON6902), ConfigMap/Secret generation, overlays/bases, multi-environment deployments, and GitOps workflows.
loom-logging-observability
Logging and observability patterns for production systems. Use for structured JSON logging with correlation IDs, distributed tracing (OpenTelemetry, Jaeger, Zipkin), metrics collection (Prometheus), log aggregation (ELK, Loki, Datadog), and alerting strategies.
loom-md-tables
Fix markdown table alignment and spacing issues. Use when formatting tables in markdown files, aligning columns, normalizing cell padding, or ensuring proper GFM table structure. Runs a Python script to normalize column widths while preserving alignment markers.
loom-model-evaluation
Evaluates ML models for performance, fairness, and reliability. Use for metric selection, cross-validation strategies, overfitting/underfitting diagnosis, hyperparameter tuning, LLM evaluation, A/B testing, and production monitoring for model drift.
loom-performance-testing
Performance and load testing with k6, locust, JMeter, Gatling, and artillery. Use for load/stress/spike/soak tests, API and database benchmarking, profiling, p95/p99 latency analysis, throughput measurement, and bottleneck identification.
loom-plan-writer
REQUIRED skill for creating Loom execution plans. Designs DAG-based plans with mandatory knowledge-bootstrap and integration-verify bookends, parallel subagent execution within stages, and concurrent worktree stages for maximum throughput.
loom-prometheus
Prometheus monitoring and alerting for cloud-native observability. Use for writing PromQL queries, configuring scrape targets, creating alerting and recording rules, instrumenting applications, and setting up service discovery. Not for dashboards (use loom-grafana) or log analysis (use loom-logging-observability).
loom-prompt-engineering
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Use for instruction design, prompt security, chain-of-thought reasoning, and in-context learning for orchestrated agents.
loom-python
Python language expertise for idiomatic, production-quality code. Use for web frameworks (FastAPI, Django, Flask), data processing (pandas, numpy), ML patterns (sklearn, pytorch), async programming, type hints, pytest, packaging with uv/poetry, and linting with ruff/mypy/black.
loom-rate-limiting
API rate limiting and quota management. Use when implementing request throttling, API quotas, backpressure handling, or abuse protection. Covers token bucket, leaky bucket, sliding/fixed window algorithms, and distributed rate limiting with Redis.
loom-react
Modern React development patterns. Use for building React 19+ applications with components, hooks, Jotai state, React Router v7, server components, accessibility, performance optimization, and testing. Covers client-side routing, composition, and async data loading.
loom-refactoring
Restructures existing code to improve readability, maintainability, and performance without changing behavior. Use for extracting methods/classes, removing duplication, applying design patterns, improving organization, and reducing technical debt. Not for bug fixes (use loom-debugging) or new features.
loom-rust
Rust language expertise for idiomatic, production-quality code. Use for ownership and lifetimes, error handling with anyhow/thiserror, async/await with tokio, cargo workspace management, CLI tools with clap, and serialization with serde. Primary language of the Loom project.
loom-search
Full-text search and search engine implementation. Use when implementing search functionality, autocomplete, faceted search, relevance tuning, or working with search indexes like Elasticsearch, OpenSearch, Meilisearch, or Typesense.
loom-security-audit
Comprehensive security audits identifying vulnerabilities, misconfigurations, and best-practice violations across applications, APIs, infrastructure, and data pipelines. Use for OWASP Top 10 reviews, compliance assessments (SOC2, PCI-DSS, HIPAA, GDPR), threat modeling, risk assessment, and hardening.
pressure
Pressure-test a loom plan and write a review for the plan's author. Trigger when the user invokes $pressure followed by a plan path. The argument after $pressure is the plan file path.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.