SKILLEMALL.ai
GitHub ↗ RU Sign in

CD ppt-master

AI-driven multi-format SVG content generation system for presentations, social media graphics, and marketing materials. Use when creating PPTs, posters, or visual content from documents.

ClawHub Agent Skills author: Zhaofeng v1.1.0 MIT-0 65 files · 24 scripts body ≈ 779 tokens Open the sourceclawhub.ai↗ analyzed 7 d ago

AI-driven multi-format SVG content generation system for presentations, social media graphics, and marketing materials.

As a process D 35/100 · Unfinished process — References files that are not bundled: docs/design_guidelines.md, docs/canvas_formats.md, examples/ppt169_demo/

GeneratorPowerPointSoftware developmentMarketingtype 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
C
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
72
Run on models
none yet
Process rating
D
35/100
Unfinished process
References files that are not bundled: docs/design_guidelines.md, docs/canvas_formats.md, examples/ppt169_demo/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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: 65. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: docs/design_guidelines.md
  • warning missing-ref reference to a missing file: docs/canvas_formats.md
  • warning missing-ref reference to a missing file: examples/ppt169_demo/
  • warning missing-ref reference to a missing file: examples/xiaohongshu_demo/
  • warning missing-ref reference to a missing file: examples/poster_demo/
  • warning missing-ref reference to a missing file: docs/workflow_tutorial.md
  • warning missing-ref reference to a missing file: docs/svg_image_embedding.md

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: docs/design_guidelines.md, docs/canvas_formats.md, examples/ppt169_demo/
  • 0Tools and files. 7 referenced file(s) missing: docs/design_guidelines.md, docs/canvas_formats.md, examples/ppt169_demo/
  • 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
  • 100Steps. 31 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 779 tokens
  • 100Running it twice. No mutating operations
  • low 10 top-level sections: this looks like several domains in one skill
  • 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 186: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 31 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

In the sandbox The scripts kept to themselves

The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

Запущено 12 скриптов, ещё 12 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

Из них 9 не дошли до работы, и об их поведении мы ничего не узнали.

tools/analyze_images.pyне запустился: Error: PIL/Pillow not installed. Run: pip install Pillow
tools/batch_validate.pyничего за пределами своей папки
tools/config.pyничего за пределами своей папки
tools/crop_images.pyне запустился: Error: PIL (Pillow) is required. Run: pip install Pillow
tools/embed_icons.pyне запустился: embed_icons.py: error: the following arguments are required: files
tools/embed_images.pyне запустился: embed_images.py: error: the following arguments are required: files
tools/error_helper.pyничего за пределами своей папки
tools/finalize_svg.pyне запустился: Error: PIL (Pillow) is required. Run: pip install Pillow
tools/fix_image_aspect.pyне запустился: fix_image_aspect.py: error: the following arguments are required: files
tools/flatten_tspan.pyне запустился: EOFError: EOF when reading a line
tools/gemini_watermark_remover.pyне запустился: ModuleNotFoundError: No module named 'numpy'
tools/generate_examples_index.pyне запустился: [ERROR] 生成失败

21 Oct 2026

External checks

ClawHub: suspicious
PPT Master is mostly a coherent presentation-generation skill, but it includes and recommends watermark removal plus broad web fetching with weak transport safeguards, so it should be reviewed before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026