ratemyharness

仓库创建 2026年7月27日最近提交 19 小时前SkillHot 收录 15 小时前
这个 Skill 做什么

把你的 agent runtime / harness 当成产品来打分审计,检查循环逻辑、工具调用、上下文隔离、权限沙箱、重试与幂等、超时与可观测性等点。用在准备上线、做 release-gate 或想红队测试运行时可信度时。要求有真实的 harness 工件或运行痕迹,结论可复现、按统一标准评分。

▸ 展开 SKILL.md 英文原文

Use this skill to rate, audit, red-team, or release-gate a concrete AI agent harness, runtime, orchestrator, runner, repository, deployment, trace set, or configuration. Use for loop correctness, tool dispatch and result correlation, context and memory isolation, permissions and sandboxing, approvals, retry and idempotency, timeouts, cancellation, budgets, termination, observability, cost, recovery, author defense, and same-rubric re-reviews. Trigger for wording such as rate my harness, audit this agent runtime, review my agent loop, red-team this orchestrator, is this agent production ready, harness 上线前挑刺, 给 agent harness 打分, or 这个智能体运行时能上线吗. Require an actual harness artifact or runtime evidence, including one in the current workspace. Do not use for generic agent architecture advice, ordinary code review, reviewing a standalone Skill or prompt, validating only a plugin manifest, debugging one model response, or evaluating a model without its runtime.

1
Stars
0
Forks
2
仓库内 Skill
积累中
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/AmsonntagChow/ratemyharness/main/skills/ratemyharness/SKILL.md
或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/AmsonntagChow/ratemyharness/main/skills/ratemyharness/SKILL.md"
SKILL.MD 节选查看完整文件 ↗
# RateMyHarness

Use these boundaries throughout the review:

- **Model** proposes the next message, tool call, or action.
- **Loop** repeatedly invokes the model, dispatches tools, returns results, and decides whether to continue.
- **Harness** is the runtime around the loop: context, state, memory, tool registry, permissions, sandbox, approvals, budgets, retries, cancellation, checkpoints, tracing, evaluation, and recovery.
- **Skill** is an instruction/resource package loaded inside a host harness. It can shape behavior but cannot grant authority or enforce a sandbox.

An isolated loop is reviewable, but label the verdict as component-limited. Never present it as a complete harness audit.
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有