BF personal-tutor
🎓 Personal Tutor — Your private AI learning coach. 你的私人AI学习导师。 Formerly knowledge-digest, now rebranded and upgraded to v1.0.1. 原名 knowledge-digest，现已全面升级为 personal-tutor v1.0.1。 Full-cycle learning management: start a subject → daily lessons → quizzes → three-layer post-lesson archiving (learning records + memory + knowledge base). 全流程学习管理：开新课→每日上课→测验→三层课后归档（学习记录+记忆+知识库）。 NEW in v1.0.1: Mandatory Post-Lesson Self-Verification Protocol — agent cannot declare "lesson complete" until all three archive layers are verified. v1.0.1 新增：强制课后自查协议——三层归档全部验证通过，agent 才能说"下课"。 Trigger / 触发："start learning [subject]" / "开始学[科目]" / "continue [subject]" / "继续[科目]" / "update learning records" / "更新学习记录"。 NOT for: casual Q&A, one-off lookups, non-learning conversations. 不适用于：随手问答、一次性查询、非学习类对话。
🎓 Personal Tutor — Your private AI learning coach.
As a process F 47/100 · Will not run — References files that are not bundled: ../folder/file.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:318Instruction to hide actions from the user1. **Do NOT tell the user the lesson is complete** — fix the gap first
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../folder/file.md - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 47/100
- 0Tools and files. 1 referenced file(s) missing: ../folder/file.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4525 tokens
- 85Steps. 88 steps, 2 vague phrases
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 788: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 88 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.