BC ai-dev-engineer
AI开发工程师全流程工作流。覆盖需求分析→技术选型→数据处理→AI核心开发(Prompt/Agent/RAG/微调)→后端服务→前端交互→测试评估→部署运维→性能优化→LLMOps→安全护栏10大阶段。面向LLM应用开发全链路，提供代码模板、架构决策框架、调试排查指南。触发词: AI开发, AI工程师, AI全栈, LLM应用开发, Agent开发, RAG开发, Prompt工程, 模型微调, AI部署, AI后端, AI前端, 搭建AI应用, AI系统设计, AI架构, MLOps, LLMOps, AgentOps, AI安全, Prompt注入, AI合规, 模型网关, 智能路由, AI dev, LLM app, AI fullstack, build AI app, AI system design, AI safety, guardrails.
AI开发工程师全流程工作流。覆盖需求分析→技术选型→数据处理→AI核心开发(Prompt/Agent/RAG/微调)→后端服务→前端交互→测试评估→部署运维→性能优化→LLMOps→安全护栏10大阶段。面向LLM应用开发全链路，提供代码模板、架构决策框架、调试排查指南。触发词: AI开发, AI工程师, AI全栈…
As a process C 50/100 · 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
✓ Guard found no suspicious behaviour. 2 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 10. 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
body-longSKILL.md body ≈ 8709 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 50/100
- 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
- 40Execution cost. Instruction body is 8709 tokens: crowds the task out of the window
- 100Tools and files. No external tools needed
- 100Steps. 60 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 14 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 384: enough signal without eating the budget
- +4Structure: 58 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (38 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.