DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Structured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.
65 4mo ago A 27 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.
65 4mo ago A 23 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.
65 4mo ago A 32 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.
65 4mo ago B 35 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.
65 4mo ago A 36 tokens
original MIT
refactoring
30DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
65 4mo ago A 22 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
65 4mo ago A 32 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Applies OWASP Top 10, secrets management, and least-privilege principles before any code ships. Security is a build step, not an afterthought.
65 4mo ago A 37 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Prevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions, no unnecessary complexity.
65 4mo ago A 27 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Enforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.
65 4mo ago A 36 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.
65 4mo ago A 34 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Red-green-refactor cycle with meaningful coverage. Tests are written before implementation. Coverage is a side effect of good tests, not the goal.
65 4mo ago A 32 tokens
original MIT
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Forces explicit reasoning before writing any code. Surfaces assumptions, manages confusion, and prevents hallucination by demanding clarity upfront.
65 4mo ago A 30 tokens
original MIT