ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
loom-testing
Comprehensive test implementation across all domains including unit, integration, e2e, security, infrastructure, data pipelines, and ML models. Covers TDD/BDD workflows, test architecture, flaky test debugging, and coverage analysis.
cosmix/loom 36
-
loom-code-migration
cosmix/loom 36
-
loom-documentation
cosmix/loom 36
-
loom-background-jobs
Background job processing patterns including job queues, scheduled jobs, worker pools, and retry strategies. Use when implementing async processing, job queues, workers, task queues, async tasks, delayed jobs, recurring jobs, scheduled tasks, ETL pipelines, data processing, ML training jobs, Celery, Bull, Sidekiq, Resque, cron jobs, retry logic, dead letter queues, DLQ, at-least-once delivery, exactly-once delivery, job monitoring, or worker management.
cosmix/loom 36
-
loom-concurrency
cosmix/loom 36
-
loom-terraform
cosmix/loom 36
-
loom-kustomize
cosmix/loom 36
-
loom-feature-flags
Feature flag patterns for controlled rollouts, A/B testing, kill switches, and runtime configuration. Use when implementing feature toggles, feature flags, gradual rollouts, canary releases, percentage rollouts, dark launches, user targeting, A/B tests, experiments, circuit breakers, emergency kill switches, model switching, or infrastructure flags.
cosmix/loom 36
-
loom-threat-model
cosmix/loom 36
-
loom-usage
Meta-orchestration skill for Claude driving loom. Covers the full loom lifecycle
from plan initialization through execution, monitoring, debugging, and recovery.
Use this when Claude itself needs to operate loom — running plans, interpreting
status, recovering from failures, managing state, and coordinating multi-stage
execution.
USE WHEN: Claude needs to run loom commands, debug failed stages, interpret
loom status output, recover from crashes, manage worktrees, or orchestrate
multi-stage execution.
DO NOT USE: For writing loom plans (use /loom-plan-writer), for designing
wiring checks (use /loom-wiring-test), for before/after verification pairs
(use /loom-before-after), or for dead code detection config (use /loom-dead-code-check).
cosmix/loom 36
-
loom-accessibility
cosmix/loom 36
-
loom-git-workflow
cosmix/loom 36
-
loom-refactoring
Restructures existing code to improve readability, maintainability, and performance without changing external behavior.
USE WHEN: Restructuring code without changing behavior, extracting methods/classes, removing duplication, applying design patterns, improving code organization, reducing technical debt.
DO NOT USE: For bug fixes (use /loom-debugging), for adding tests (use /loom-testing), for new features (implement directly).
TRIGGERS: refactor, restructure, rewrite, clean up, simplify, extract, inline, rename, move, split, merge, decompose, modularize, decouple, technical debt, code smell, DRY, SOLID, improve code, modernize, reorganize.
cosmix/loom 36
-
loom-rust
cosmix/loom 36
-
loom-argocd
cosmix/loom 36
-
loom-istio
cosmix/loom 36
-
loom-plan-writer
cosmix/loom 36
-
loom-kubernetes
cosmix/loom 36
-
loom-api-documentation
cosmix/loom 36
-
loom-data-visualization
cosmix/loom 36
-
loom-md-tables
cosmix/loom 36
-
loom-i18n
cosmix/loom 36
-
loom-test-strategy
cosmix/loom 36
-
loom-auth
Authentication and authorization patterns including OAuth2, JWT, RBAC/ABAC, session management, API keys, password hashing, and MFA.
USE WHEN: Implementing login flows, access control, identity management, tokens, permissions, session handling, API key authentication, or MFA.
DO NOT USE: For security vulnerability scanning (use /loom-security-scan), for security audits (use /loom-security-audit), for threat modeling (use /loom-threat-model).
TRIGGERS: login, logout, signin, signup, authentication, authorization, password, credential, token, JWT, OAuth, OAuth2, OIDC, SSO, SAML, session, cookie, RBAC, ABAC, permissions, roles, MFA, 2FA, TOTP, API key, PKCE.
cosmix/loom 36