majiayu000

majiayu000/litellm-rs

Settings file Claude Code

Agent settings configuring skills.

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS Authentication Architecture. Covers JWT + API Key + RBAC multi-method auth, DashMap-backed rate limiting, the actix-web middleware pipeline, and credential management (gw- prefixed keys, HMAC hashing). Use when adding auth methods, debugging JWT/API-key validation, implementing RBAC permission checks, or…

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS response caching architecture. Covers the two-tier deterministic cache (L1 in-memory + optional L2 Redis) behind LLMCache and DualCache, SHA-256 cache key generation with schema versioning, TTL and eviction policy, request-path wiring for chat completions and embeddings, cache statistics, and admin…

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS Configuration Architecture. Covers YAML loading with ${VAR} environment substitution, strict serde config models, startup validation via the Validate trait, and the LITELLM env-only fallback. Use when changing config models or serde defaults, debugging env variable substitution failures, updating validation…

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS Error Handling Architecture. Covers two-tier error hierarchy, ProviderError factory methods, HTTP status mapping, retry logic, and error context preservation. Use when designing error types or enums, creating ProviderError instances via factory methods, mapping HTTP statuses to typed errors, deciding…

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS Observability Architecture. Covers the Prometheus-format metrics rendered by the metrics middleware and /metrics endpoint, health/readiness endpoints, request logging, and the OpenTelemetry/Datadog/Langfuse callback exporters. Use when adding or changing metrics or log instrumentation, implementing or…

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS provider system in two tiers - data-driven OpenAI-compatible catalog entries auto-routed through OpenAILikeProvider, plus code-based provider modules implementing the LLMProvider trait behind the closed Provider enum. Covers unified ProviderError handling, connection pooling, capabilities, and model…

majiayu000/litellm-rs

Skill Claude CodeCodex

A development guide for adding language-model providers to LiteLLM-RS, a gateway that connects applications to multiple AI services. It explains provider registration, provider-specific code, and the shared error handling used by the gateway.

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS Routing Architecture. Covers 7 routing strategies over immutable routing snapshots (ArcSwap) with atomic/DashMap state, health-aware deployment selection with cooldown circuit breaker, model-keyed fallback chains, and load balancing. Use when selecting or tuning a routing strategy, or configuring failover…

majiayu000/litellm-rs

Skill Claude CodeCodex

LiteLLM-RS Streaming Architecture. Covers UnifiedSSEParser line buffering, the SSETransformer trait, UnifiedSSEStream backpressure and overflow guarding, provider-specific transformers, and server-side SSE emission. Use when debugging SSE parsing, writing or modifying a provider stream transformer, wiring the stream…

majiayu000/litellm-rs

Instructions file CodexOpenCode

Instructions for majiayu000/litellm-rs, covering agents.md, workflow, commands and rules.

majiayu000/litellm-rs

Instructions file

Instructions for majiayu000/litellm-rs, covering claude.md, version management, automated version bumping (ci/cd), commit message format and version info in code.

majiayu000/awesome-goal-prompts

Skill Claude CodeCodex

Create, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools. Use when the user asks to write, make, generate, improve, productize, or critique a goal prompt, rescue contract, GOAL.md-style task, done-when contract, verification prompt, stop-rule…

majiayu000/vibeguard

Command Claude Code

Execute the /vibeguard:check command. $ARGUMENTS.

majiayu000/vibeguard

Command Claude Code

Execute the /vibeguard:gc command. $ARGUMENTS.

majiayu000/vibeguard

Command Claude Code

Execute the /vibeguard:learn command. $ARGUMENTS.

majiayu000/vibeguard

Command Claude Code

Execute the /vibeguard:preflight command. $ARGUMENTS.

majiayu000/vibeguard

Command Claude Code

Build repair — read build errors, locate root causes, perform minimal repairs, and verify that the build passed.

majiayu000/vibeguard

Command Claude Code

Run all guard scripts with one click and output project health report.

majiayu000/vibeguard

Command Claude Code

Dual-model adversarial review — Claude generates review reports, Codex does adversarial verification, and iterates until convergence.

majiayu000/vibeguard

Command Claude Code

Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.

majiayu000/vibeguard

Command Claude Code

In-depth interviews with user needs before the start of major functions, mining boundary conditions and technical trade-offs, and outputting structured SPEC.

majiayu000/vibeguard

Command Claude Code

Dual-mode learning: (A) Extract guard rules from errors (B) Extract reusable skills from discoveries. Automatic mode routing.

majiayu000/vibeguard

Command Claude Code

Verify live claims with fresh facts, inferences, and unresolved gaps.