BF agent-harness-engineer
指导AI coding工具构建生产级Agent系统。当用户需要设计、实现或优化AI Agent系统时触发。 特别适用于：Agent架构设计、Harness工程、工具系统、权限模型、上下文管理、多智能体协作、 记忆系统、安全沙箱、MCP集成等场景。支持从概念设计到生产部署的完整Agent系统构建。 触发关键词：构建agent、创建智能体、agent系统、自动化工具、AI助手、多智能体、 agent优化、升级agent、agent脚手架、agent项目模板、agent框架。 核心目标：帮助AI coding工具生成结构完整、可扩展、生产就绪的Agent项目， 而非仅提供最小化demo代码。 与v1/v2版本的区别： - v1版本：提供理论文档和最小示例，AI coding工具需要自己理解如何应用 - v2版本：提供分阶段构建指南，每个阶段都有明确的理论指导、实践步骤、检查清单和常见问题 - v3版本（当前）：引入三级构建规模、代码生成禁止复制策略、技术栈分级推荐、抽象接口引导模式。 AI coding工具必须根据用户需求生成定制化代码，不得直接复制reference中的示例代码。 reference中的代码已全部改为"抽象接口/骨架 + AI引导提示"，确保AI主动设计而非被动复制。
指导AI coding工具构建生产级Agent系统。当用户需要设计、实现或优化AI Agent系统时触发。 特别适用于：Agent架构设计、Harness工程、工具系统、权限模型、上下文管理、多智能体协作、 记忆系统、安全沙箱、MCP集成等场景。支持从概念设计到生产部署的完整Agent系统构建。…
As a process F 40/100 · Will not run — References files that are not bundled: references/01-phase-init.md, references/02-phase-llm.md, references/03-phase-tools.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keytemplates/project-scaffold/nodejs/src/main.js:18Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keytemplates/project-scaffold/python/src/main.py:30Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/01-phase-init.md - warning
missing-refreference to a missing file: references/02-phase-llm.md - warning
missing-refreference to a missing file: references/03-phase-tools.md - warning
missing-refreference to a missing file: references/04-phase-agent-loop.md - warning
missing-refreference to a missing file: references/05-phase-context.md - warning
missing-refreference to a missing file: references/06-phase-permissions.md - warning
missing-refreference to a missing file: references/07-phase-production.md - warning
missing-refreference to a missing file: references/08-core-concepts.md - warning
missing-refreference to a missing file: references/09-multi-agent.md - warning
missing-refreference to a missing file: references/10-mcp-integration.md - warning
missing-refreference to a missing file: references/11-technology-stack.md - warning
missing-refreference to a missing file: references/12-sandbox-advanced.md - warning
missing-refreference to a missing file: references/13-session-design.md - warning
missing-refreference to a missing file: references/14-observability.md - warning
missing-refreference to a missing file: ../templates/minimal/ - warning
missing-refreference to a missing file: ../templates/professional/ - warning
missing-refreference to a missing file: ../templates/enterprise/
Process rating: all ten parameters 40/100
- 0Tools and files. 17 referenced file(s) missing: references/01-phase-init.md, references/02-phase-llm.md, references/03-phase-tools.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 86 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2777 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 552: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 86 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.