AC deeptutor-lite
融合 HKUDS/DeepTutor（arXiv:2604.26962）与 THU-MAIC/OpenMAIC（JCST 2026）的开源思路，在 WorkBuddy 内实现免外部 key 的轻量个性化辅导台。 港大版提供：混合个性化引擎（静态 RAG grounding + 动态学习者记忆）、L1/L2/L3 三层可检视记忆 + 记忆图谱、难度校准出题、引用溯源辅导、多引擎 RAG。 清华版提供：多智能体课堂角色（导师/助教/多人格同学/编排）、认知学生建模、布鲁姆分类法/ZPD/UDL 教育理论底座、圆桌辩论多视角理解。 本技能把两者压成可运行的辅导工作流：三层记忆 + 认知掌握度模型(BKT-lite) + 教育理论校准的难度出题 + 多视角圆桌 + 引用溯源 + 可选可视化讲解 + 主动复习触发 + Anki 直推。 适用：长期个性化一对一/小班陪学（化学/任意学科）；薄弱点被记住、被针对、被多视角辨析；讲解必须溯源；题落在最近发展区。 不适用：纯摘要/一次性解题（直接答）；仅排计划（路由 xuexi-zhidao）；仅转卡（路由 anki制作）。 trigger 词（中英）：个性化辅导 / 记住他的薄弱点 / 针对他的情况出题 / 掌握度追踪 / 我的学生档案 / 长期陪学 / 难度校准 / 引用教材讲解 / 多视角辨析 / 圆桌 / 认知诊断 / personalized tutor / mastery tracking / calibrated quiz / cognitive tutor
融合 HKUDS/DeepTutor（arXiv:2604.26962）与 THU-MAIC/OpenMAIC（JCST 2026）的开源思路，在 WorkBuddy 内实现免外部 key 的轻量个性化辅导台。 港大版提供：混合个性化引擎（静态 RAG grounding + 动态学习者记忆）、L1/L2/L3…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "source_book" - note
frontmatter-keyunknown frontmatter key "related_skills"
Process rating: all ten parameters 51/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 63 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2990 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- -223 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 662: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 63 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.