SKILLEMALL.ai
GitHub ↗ RU Sign in

AF edu-homework-grader

EN: Automated K-12 homework grading for Chinese, Math, English, Physics and Chemistry. Handles objective items (multiple-choice, fill-in-the-blank, true/false) with deterministic scoring, and subjective items (essays, short answers, math derivations) with rubric-based partial-credit evaluation. Produces per-student score sheet, common-error analysis, and personalized improvement suggestions. Use when user provides homework text/photos and asks "批改作业 / 改卷 / 评分 / grade homework". 中文：覆盖 K-12 语数英物化的自动作业批改。客观题（选择/填空/判断）按答案模板确定性评分；主观题（作文/简答/数学推导）按 rubric 给出部分分与文字反馈。输出每生成绩、共性错误分析、个性化提升建议。当用户提供作业内容并要求"批改/改卷/评分"时触发。

ClawHub Agent Skills author: boboy v1.0.0 MIT-0 14 files body ≈ 1 595 tokens Open the sourceclawhub.ai↗ analyzed 29 h ago

EN: Automated K-12 homework grading for Chinese, Math, English, Physics and Chemistry.

As a process F 47/100 · Will not run — References files that are not bundled: scripts/detect_item_types.py, scripts/chem_eq_check.py, templates/rubric_<subject>_<grade>.json

ProcedureWriting and documentsData and analyticstype 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
A
91/100
safety, quality, tests
Safety 60%
100
Quality 40%
77
Run on models
none yet
Process rating
F
47/100
Will not run
References files that are not bundled: scripts/detect_item_types.py, scripts/chem_eq_check.py, templates/rubric_<subject>_<grade>.json
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/detect_item_types.py
  • warning missing-ref reference to a missing file: scripts/chem_eq_check.py
  • warning missing-ref reference to a missing file: templates/rubric_<subject>_<grade>.json
  • warning missing-ref reference to a missing file: scripts/math_step_grader.py
  • warning missing-ref reference to a missing file: scripts/diagnose_errors.py

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: scripts/detect_item_types.py, scripts/chem_eq_check.py, templates/rubric_<subject>_<grade>.json
  • 0Tools and files. 5 referenced file(s) missing: scripts/detect_item_types.py, scripts/chem_eq_check.py, templates/rubric_<subject>_<grade>.json
  • 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
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 43 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1595 tokens
  • 100Running it twice. No mutating operations
  • low The response is described with custom markup (4 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

  • +4Description does not say when NOT to use the skill (false activations)
  • -32 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 2 example trigger phrases
  • +3Description length 614: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 43 items
  • +3Output format is stated explicitly
  • +4Has examples (8 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: clean
This is a coherent local homework-grading skill with no hidden network, credential, persistence, or destructive behavior found, but it can handle sensitive student information.
LLM: benign (high) · VirusTotal: · 28 May 2026