SKILLEMALL.ai
GitHub ↗ RU Sign in

BC book-learning-tutor

把书课程化并作为「专业教师」逐课带人类学完：课前备课→详尽费曼教学→练习闸门→间隔复习→背诵作业→自进化。默认处理使用者已提供的本地书（PDF/EPUB/DJVU/MOBI/AZW/DOCX/TXT/MD/CBZ）；**当使用者无本地书且明确授权时，可代为联网检索公开来源并用项目抓取工具获取**。当用户说「学这本书 <本地路径> / 把这本 PDF 课程化 / 教我这本书 / 继续学 <书> / 复习 <书> / 考考我 <书> / 帮我学 X」时调用。教学引擎已单包自包含，无需再加载其他技能。

ClawHub Agent Skills author: fangyuan-3149 v0.1.3 MIT-0 48 files · 1 script body ≈ 3 727 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

把书课程化并作为「专业教师」逐课带人类学完：课前备课→详尽费曼教学→练习闸门→间隔复习→背诵作业→自进化。默认处理使用者已提供的本地书（PDF/EPUB/DJVU/MOBI/AZW/DOCX/TXT/MD/CBZ）；当使用者无本地书且明确授权时，可代为联网检索公开来源并用项目抓取工具获取。当用户说「学这本书…

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureWordLearningtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
93
Quality 40%
74
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Obfuscation uni-zero-width examples/flatland/第01章_I__Of_the_Nature_of_Flatland/第01课_I__Of_the_Nature_of_Flatland.md:6
    Zero-width / invisible characters (possible hidden text) (6 occurrences) (test fixture / example file)
    Imagine a vast sheet of paper on which straight Lines, Triangles, Squares, Pentagons, Hexagons, and other Figures, instead of remaining fixed in their places, m…
    fixture
  • low Obfuscation obf-base64-blob tools/acquire/pipeline.py:482
    Long base64-looking blob (quoted — discussed, not commanded)
    "iVBO…mNk+M8AAAMBAQDJ/pLvAAAAAElFTkSuQmCC")
    quoted
  • low Obfuscation obf-base64-blob tools/acquire/pipeline.py:604
    Long base64-looking blob (quoted — discussed, not commanded)
    "iVBO…mNk+M8AAAMBAQDJ/pLvAAAAAElFTkSuQmCC")
    quoted

Files scanned: 48. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "description_en"
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 57/100

  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 32 steps, 2 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3727 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 (6 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 250: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 32 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
The skill is mostly a disclosed book-tutoring tool, but its optional acquisition path can run untrusted source rules through local JavaScript and broad network fetching with weak safeguards.
LLM: suspicious (high) · 11 Aug 2026