SKILLEMALL.ai
GitHub ↗ RU Sign in

CF qwen-mm-plugins-edu-agent

Generate step-by-step math problem-solving tutorial videos in Chinese (Mandarin). Use when: (1) a user provides a math problem and wants an explanation video, (2) someone says "make a math tutorial", "explain this equation", "create a teaching video for this problem", "讲解这道题", "生成解题视频", (3) the user wants a Chinese-language math lesson covering formulas, equations, or geometric figures, (4) the user shares a math problem in text or LaTeX and asks for a video walkthrough, (5) the input is an image_assets/ folder containing problem images — the skill will extract the problem via visual recognition, solve it, and generate a tutorial video. Teaching components are rendered as realistic objects (solid opaque panels, 3D cards, SVG figures) with a modern aurora mesh aesthetic.

QwenLM/Qwen-MM-Plugins Agent Skills author: QwenLM 80 files body ≈ 16 890 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Generate step-by-step math problem-solving tutorial videos in Chinese (Mandarin).

As a process F 33/100 · No process to follow — References files that are not bundled: references/step-0-image-input.md, references/step-1-problem-analysis.md, references/step-2-teaching-script.md

ProcedureLaTeXLearningMedia and videotype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
65
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: references/step-0-image-input.md, references/step-1-problem-analysis.md, references/step-2-teaching-script.md
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. 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: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 16890 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/step-0-image-input.md
  • warning missing-ref reference to a missing file: references/step-1-problem-analysis.md
  • warning missing-ref reference to a missing file: references/step-2-teaching-script.md
  • warning missing-ref reference to a missing file: references/step-3-voice-generation.md
  • warning missing-ref reference to a missing file: references/step-4-storyboard.md
  • warning missing-ref reference to a missing file: references/step-5-build-components.md
  • warning missing-ref reference to a missing file: references/step-6-compose-render.md
  • warning missing-ref reference to a missing file: design-system.md
  • warning missing-ref reference to a missing file: references/math-components.md
  • warning missing-ref reference to a missing file: references/geometry-construction-guide.md
  • warning missing-ref reference to a missing file: references/golden-example-geometry.md
  • warning missing-ref reference to a missing file: references/circuit-schematic-guide.md
  • warning missing-ref reference to a missing file: references/example-process-animation.md
  • warning missing-ref reference to a missing file: references/examples/mitosis-anaphase.scene.html
  • warning missing-ref reference to a missing file: references/golden-example-interactive-transform.md
  • warning missing-ref reference to a missing file: scripts/check_chromosome_example.py
  • warning missing-ref reference to a missing file: scripts/check_cjk_font.py
  • warning missing-ref reference to a missing file: scripts/check_caption_position.py
  • warning missing-ref reference to a missing file: scripts/check_caption_overflow.py
  • warning missing-ref reference to a missing file: scripts/check_scene_layout.py
  • warning missing-ref reference to a missing file: scripts/check_scene_overflow.py
  • warning missing-ref reference to a missing file: scripts/check_svg_height_bound.py
  • warning missing-ref reference to a missing file: scripts/check_scene_fit.py
  • warning missing-ref reference to a missing file: scripts/check_svg_label_overlap.py
  • warning missing-ref reference to a missing file: scripts/check_svg_node_graph.py
  • warning missing-ref reference to a missing file: scripts/check_no_glass.py
  • warning missing-ref reference to a missing file: assets/katex/katex.min.css
  • warning missing-ref reference to a missing file: assets/fonts/
  • warning missing-ref reference to a missing file: assets/k12-scholar-font-template.css
  • warning missing-ref reference to a missing file: assets/gsap/
  • warning missing-ref reference to a missing file: scripts/check_asset_mirror.py
  • warning missing-ref reference to a missing file: scripts/check_root_compositions.py
  • warning missing-ref reference to a missing file: scripts/check_composition_format.py
  • warning missing-ref reference to a missing file: scripts/check_svg_filter_bbox.py
  • warning missing-ref reference to a missing file: scripts/check_svg_arrow.py
  • warning missing-ref reference to a missing file: scripts/check_svg_label_on_figure.py
  • warning missing-ref reference to a missing file: scripts/check_svg_transform_anim.py
  • warning missing-ref reference to a missing file: scripts/check_composition_root_id.py
  • note edit-residue the text marks something as outdated (lines 187): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: references/step-0-image-input.md, references/step-1-problem-analysis.md, references/step-2-teaching-script.md
  • 0Tools and files. 38 referenced file(s) missing: references/step-0-image-input.md, references/step-1-problem-analysis.md, references/step-2-teaching-script.md
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 10Execution cost. Instruction body is 16890 tokens: crowds the task out of the window
  • 30Running it twice. 8 mutating operations with no state check
  • 40Consistency. Frontmatter name (qwen-mm-plugins-edu-agent) differs from the folder (skill)
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Steps. 65 steps, 6 vague phrases
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (59 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)
  • +3Output format is not stated: the model decides each time
  • -216 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 780: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 65 items
  • +4Has examples (8 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.