GitHub
advanced-evaluation
LLM-as-Judge techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation.
Skills IA Tests et sécurité
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Catégories: Tests et sécurité
Tests et sécurité Effacer les filtres
Explorer
GitHub
anime-js
Anime.js animation patterns for web interfaces including timelines, staggering, and motion design.
GitHub
code-review
Code quality review patterns including quality gates, checklists, and language-specific checks.
GitHub
verification-before-completion
Verification discipline - evidence-based completion claims, running verification commands before asserting success. Use before claiming any work is complete, fixed, or passing.
GitHub
hono-llm-docs
Fetch Hono web framework documentation via llms.txt for up-to-date API references
GitHub
kubernetes-operators
Kubernetes infrastructure patterns including operators, Helm, GitOps, and component provisioning.
GitHub
zod-llm-docs
Fetch Zod schema validation documentation via llms.txt for up-to-date API references
GitHub
healer
Healer monitoring expertise - detection patterns, API endpoints, dual-model architecture, and remediation workflows. Use when monitoring Play workflows or debugging agent failures.
GitHub
expo-upgrading
Guidelines for upgrading Expo SDK versions, fixing dependency issues, and migrating to new architecture
GitHub
elysia-llm-docs
ElysiaJS framework for building type-safe, high-performance backend servers with Bun
GitHub
context7
Query up-to-date library documentation and code examples before implementing features.
GitHub
repomix
Pack codebases into context-optimized formats for analysis and understanding.
GitHub
deep-research
Deep technical research using Firecrawl Agent for autonomous web investigation, competitive analysis, and implementation pattern discovery.
GitHub
argocd-gitops
ArgoCD GitOps patterns including sync waves, app-of-apps, multi-source applications, and Helm value overlays.
GitHub
doc-coauthoring
Structured workflow for co-authoring documentation, PRDs, technical specs, and decision docs. Use when writing substantial documentation, creating proposals, drafting specifications, or any structured content t...
GitHub
prd-analysis
PRD parsing and task decomposition patterns for intake workflows.
GitHub
better-auth-expo
Better Auth integration for Expo/React Native with SecureStore, deep linking, and native provider SDKs
GitHub
testing-strategies
Testing patterns including unit, integration, E2E tests and language-specific frameworks.
GitHub
openmemory
Persistent long-term agent memory for storing and querying past work, patterns, and learnings.
GitHub
secrets-management
External Secrets Operator and OpenBao patterns for secure secret synchronization and management.
GitHub
incident-response
Incident response and remediation patterns including observability, diagnosis, and targeted fixes.
GitHub
evaluation
Agent evaluation methods including LLM-as-judge, rubrics, and quality gates.
GitHub
ai-ml-infra
KubeAI, GPU operators, and model serving patterns for AI/ML infrastructure on Kubernetes.
GitHub
multi-agent-patterns
Supervisor, swarm, and hierarchical multi-agent architectures with context isolation patterns.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.