awesome-agv

Structured fault tolerance for coordinator agents. 5-level escalation ladder (Retry → Replace → Skip → Redistribute → Degrade), dead-man timers, degraded completion protocol, and cross-level escalation format. Load when orchestrating agents that may fail.

Structured code review protocol for inspecting code quality against the full rule set. Use when auditing code written by yourself or another agent, during the /audit workflow, or when the user asks for a code review.

Reusable convergence protocol for coordinator agents. Defines the BRIEFING → ITERATE → GATE → CONVERGE loop, context hygiene rules, self-succession protocol, turn budget, and handoff compression. Load when orchestrating multi-iteration workflows.

Pre-flight checklist and post-implementation self-review protocol. Use before generating any code (pre-flight) and after writing code but before verification (self-review) to catch issues early.

MECE task decomposition, file ownership enforcement, DAG-based execution, and safe merge protocol for intra-domain parallel dispatch. The safety invariants that prevent merge chaos when multiple agents write in parallel. Applies recursively at every nesting depth.

Shared protocols for all agents in the multi-agent pipeline: recursive nesting, pre-implementation restatement, parallel dispatch format, and agent definition cascade. Load this skill instead of inlining these protocols in every agent file.

Profile-driven performance optimization protocol. Use when profiling data (CPU, heap, trace) is available or when the user requests performance analysis. Covers methodology (Profile → Analyze → Opportunity Scan → Prioritize → Optimize → Benchmark), optimization pattern catalog, safety invariants, and when-to-stop heuristics. Language-specific tooling is in languages/*.md.

Zero-tolerance integrity enforcement for the arbiter agent. Cheating detection, scope violation verification, test integrity checks, and independent build/test re-execution. Exclusive to @arbiter — other agents must not load this skill.

Shared delivery validation protocol for red team agents. Defines verification categories, severity classification, evidence standards, and output format. Loaded by @red-team-lead, @delivery-validator, and @integration-prober.

Mobile E2E testing patterns — Flutter integration_test, Patrol, Maestro, golden testing, device matrix, and test data management. Use when writing E2E tests for mobile applications.

Python type hints, Protocols, Pydantic, async/await, pytest, ruff, mypy strict.

Rust ownership, tokio, thiserror/anyhow, Clippy pedantic, unsafe, lifetimes.

TypeScript strict mode, type narrowing, Zod validation, vitest, ESLint flat config.

Angular components, signals, DI, RxJS, standalone architecture. For TypeScript see typescript-idioms.

Django ORM, class-based views, DRF serializers, migrations, pytest-django. For Python see python-idioms.

Flutter Riverpod 3, freezed, go_router, const widgets, repository pattern.

Go stdlib, error wrapping, interfaces, goroutines, table-driven tests, gofumpt.

Next.js App Router, RSC, Server Actions, ISR. For React see react-idioms. For TypeScript see typescript-idioms.

React hooks, Suspense, Server Components, React 19 patterns. For TypeScript see typescript-idioms.

Vue 3 Composition API, Pinia stores, composables, Vite, Vitest.

Axum HTTP framework patterns — routing, extractors, middleware, state management. For Rust see rust-idioms.

Hono HTTP framework patterns — routing, middleware, Zod validation, RPC client. For TypeScript see typescript-idioms.

CI/CD pipeline design: GitHub Actions, GitLab CI, multi-stage Docker builds, image scanning, SBOM attestation (Cosign keyless), and environment promotion. Layered by complexity — Level 0 (all projects), Level 1 (containerized), Level 2 (Kubernetes). GitOps and Kubernetes deployment patterns in references/gitops-kubernetes.md.

Spec adherence and deliverable completeness verification. Load during /workflow-team REVIEW/VERIFY primitives when spawned as @acceptance-reviewer via dynamic recursive subagent provisioning. Verifies WHAT was delivered matches WHAT was requested.

Detailed testing reference material: test doubles strategy, integration test infrastructure (Testcontainers, Firebase emulator), naming conventions per language, test organization patterns. Load when writing tests or setting up test infrastructure. The core mandates (TDD, AAA, pyramid) are in the testing-strategy rule — this skill provides implementation details.

Playwright browser automation via MCP. Covers E2E testing, UI review, web scraping, screenshot capture, and general browser interaction. MCP-first — CLI is fallback only.

Data pipeline architecture, ETL/ELT patterns, data quality, batch vs stream processing, orchestration, and data governance principles.

Comprehensive protocol for validating root causes of software issues. Use when you need to systematically debug a complex bug, flaky test, or unknown system behavior by forming hypotheses and validating them with specific tasks.

Structured incident workflow: severity classification, triage, diagnosis, mitigation, postmortem, and prevention. Template-driven with blameless review.

ML pipeline design, feature engineering, model training/serving, experiment tracking, model validation, and MLOps principles.

Feature flag implementation: release flags, ops kill switches, experiment flags, and permission gating. PRD-gated — only load when PRD or technical architecture explicitly requires gradual rollout, A/B testing, or kill switches. Includes lifecycle rules (90-day max for release flags), flag evaluation patterns, and CI/CD checklist.

Structured logging implementation patterns: log levels, mandatory context fields (correlationId, userId, duration), security (PII scrubbing), and per-language library choices (Go slog, TypeScript pino, Python structlog). Load when implementing logging in any operation entry point. Prerequisite: logging-and-observability-mandate.md.

Implementation examples for the three testability rules (I/O isolation, pure logic, dependency direction) across Go, TypeScript, Python, Rust, and Dart. Loaded by reference from architectural-pattern.md — not triggered by file patterns.

Token-efficient communication protocol. Activate ONLY when: (1) user explicitly requests it (e.g., "use omni", "be concise", "compress output"), (2) dispatched as a sub-agent in /workflow-team pipelines where token budget matters, or (3) agent-to-agent communication via /omni headless modifier. Never activate by default in normal conversations — users expect natural language responses unless they opt in. Compresses prose form while preserving 100% technical accuracy. Code blocks, tool calls, file paths, and data are NEVER compressed.

Architecture Decision Record skill for documenting significant architectural decisions with context, options, and consequences. Use during the Research phase when choosing between approaches, or whenever the user asks to document an architectural decision.

OpenAPI 3.1 specification writing, request/response examples, error documentation, versioning, and interactive API portal patterns.

Controlled failure injection: hypothesis design, blast radius control, safety mechanisms, game day planning, and resilience verification.

CLI tool design, argument parsing, interactive prompts, shell completions, cross-platform considerations, and distribution strategies.

Resource-constrained development, real-time patterns, interrupt handling, memory management, RTOS patterns, and hardware abstraction layers.

PCI DSS compliance, payment gateway integration, tokenization, webhook reliability, idempotency, fraud prevention, and subscription billing.