Loading...
Loading...
Found 20 Skills
Deep architectural knowledge of AI Agent Harness design patterns, implementation strategies, and Claude Code internals for building production-grade AI agents
Expert guidance on AI Agent architecture, harness design patterns, and building production-grade Agent systems based on Claude Code analysis
Deployable Flue agent harness lane for HTTP, CI, Node, Cloudflare, and sandbox-backed agents.
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Diagnose why an agent harness misbehaved by reading the local flight-recorder ledger (.vigiles/runs.jsonl) — which skills fired or got hijacked, which hooks blocked or wrongly allowed, which subagent tool-contract violations happened, and how a skill's trigger rate moved. Use when asked why a skill stopped firing, why a hook didn't block, why the wrong skill ran, or to debug/investigate what the harness actually did. NOT for writing new rules (use strengthen) or editing the spec (use edit-spec).
Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture", "agent orchestration", "generator-evaluator", "long-running app", "harness design", "agent pipeline", "quality evaluation loop", "sprint contract", "build app with agents", "Claude Agent SDK architecture", or when building complex full-stack apps that need planning → generation → evaluation cycles. Also use when discussing context degradation, self-evaluation bias, or assumption testing in AI workflows.
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.
Set up deterministic commands, worktrees, and quality gates so agents can run safely in this repository.
Design multi-agent harnesses for long-running autonomous coding tasks. Covers generator/evaluator loops, context reset strategy, sprint contracts, and the planner-generator-evaluator architecture from Anthropic's harness research.
Create polished design artifacts as self-contained HTML — UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, and slide decks. Use this skill whenever the user wants to design, mock up, prototype, wireframe, or visualize any interface, screen, flow, or visual artifact — even when they don't say the word "design" (e.g. "build me a landing page", "show me what a settings screen could look like", "prototype an onboarding flow", "wireframe a few layout ideas", "make a pitch deck"). It drives a full design process: clarifying questions, design-context gathering, and production of one or more HTML deliverables. Runs on portable agent harnesses including Claude Code, Cursor, and Codex Agent — harness-specific tools are resolved from references/.
AI Agent Harness Design Patterns - Memory, Permission, Context Engineering, Delegation, Skill, Hook, Bootstrap. Chinese Version.