AC agent-copilot-pro
代理副驾驶是面向 AI Agent 开发者的工程化副驾驶，针对"Prompt 答非所问与幻觉、上下文腐烂（Context Rot）、工具选择不当、任务拆解颗粒度失控"四大高频痛点而设计。它把零散的 Prompt 工程经验沉淀为可复用的模板库、评估器与循环工程（Loops Engineering）工作流，让 Agent 从"能跑"升级到"稳定可控"。 核心能力：System Prompt 五段式结构化生成、任务拆解树（DAG）与依赖编排、工具选择决策矩阵、ReAct/CoT/Plan-Execute 三种 Agent Loop 模式、输出解析与 schema 校验、Prompt 质量评估器（含幻觉检测）、Token 预算与上下文腐烂治理。 适用场景：构建客服/助理类 Agent、自动化工作流编排、RAG 应用增强、多 Agent 协作系统、长会话上下文治理、Prompt 评审与回归测试。 差异化：相比仅提供"帮你写 prompt"的浅层助手，本技能新增 (1) 上下文腐烂诊断器，量化三因素（信息密度衰减、噪声累积、注意力漂移）并给出治理建议；(2) 工具选择决策矩阵，基于任务类型、参数复杂度、失败成本三维度推荐工具调用策略；(3) 循环工程工作流，自动发现任务→分配→执行→质检→迭代；(4) Prompt 质量评估器，含幻觉检测与回归测试用例生成；(5) Token 预算管理，按任务复杂度分配上下文配额。 触发关键词：prompt工程、代理设计、任务拆解、工具选择、agent loop、上下文腐烂、幻觉检测、ReAct、CoT、循环工程、prompt engineering、agent design、task decomposition
代理副驾驶是面向 AI Agent 开发者的工程化副驾驶，针对"Prompt 答非所问与幻觉、上下文腐烂（Context Rot）、工具选择不当、任务拆解颗粒度失控"四大高频痛点而设计。它把零散的 Prompt 工程经验沉淀为可复用的模板库、评估器与循环工程（Loops Engineering）工作流，让…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 0
✓ No critical or high findings
Files scanned: 1. 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") - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1860 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 733: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.