harness-design
SolidDesign 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. Do NOT use to stress-test or critique an already-written plan document; use plan-swarm-review for that (this skill designs the harness, it does not review plans).
Install
Quality Score: 90/100
Skill Content
Details
- Author
- AnastasiyaW
- Repository
- AnastasiyaW/claude-code-config
- Created
- 4 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
neo-agent-harness
Use this skill when the user asks to improve AI-assisted development reliability, AGENTS.md, skills, tests, CI, hooks, review loops, agent workflow governance, loop engineering, agent automations, worktree isolation, maker/checker separation, or external state design for long-running agents. It designs feedforward guides, feedback sensors, verification gates, human decision points, and loop architectures from repository evidence.
harness-eng
Use when designing, evaluating, or simplifying an agent project harness: AGENTS.md/CLAUDE.md rules, startup scripts, progress logs, feature trackers, handoffs, evaluator rubrics, quality documents, repo-local knowledge maps, and mechanical guardrails for coding agents. Especially useful when converting raw agent-workflow notes into a concise, verifiable project control layer.
deepagents-harness
Use when designing long-horizon agents that need subagents, isolated context windows, filesystem-backed work, persistence, human approval, MCP tools, or production tracing.