SKILLEMALL.ai
GitHub ↗ RU Sign in

BF gpt-image2-ppt

Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<id>.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT.

ClawHub Agent Skills author: JuneYaooo v0.1.0 MIT-0 80 files · 1 script body ≈ 8 531 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<id>.md or mimic a user-supplied .pptx template; outputs high-res…

As a process F 38/100 · Will not run — References files that are not bundled: examples/<id>/recipe.md, examples/<id>/slides_plan.md, examples/<id>/

GeneratorPowerPointAI and agentsSoftware developmenttype 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
76/100
safety, quality, tests
Safety 60%
80
Quality 40%
70
Run on models
none yet
Process rating
F
38/100
Will not run
References files that are not bundled: examples/<id>/recipe.md, examples/<id>/slides_plan.md, examples/<id>/
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

What is at stake

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

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Exfiltration net-redirectable-api-key scripts/editable_pptx/provider.py:21
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/generate_ppt.py:119
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/image_generator.py:79
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/template_analyzer.py:192
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment

Files scanned: 78. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8531 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: examples/<id>/recipe.md
  • warning missing-ref reference to a missing file: examples/<id>/slides_plan.md
  • warning missing-ref reference to a missing file: examples/<id>/
  • warning missing-ref reference to a missing file: references/slide-XX-asset-skeleton.png

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: examples/<id>/recipe.md, examples/<id>/slides_plan.md, examples/<id>/
  • 0Tools and files. 4 referenced file(s) missing: examples/<id>/recipe.md, examples/<id>/slides_plan.md, examples/<id>/
  • 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
  • 40Consistency. Frontmatter name (gpt-image2-ppt) differs from the folder (gpt-image2-ppt-skills)
  • 40Execution cost. Instruction body is 8531 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 157 steps
  • 100Running it twice. No mutating operations
  • low 16 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (30 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
  • +2Single-language instructions
  • +3Description length 346: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 157 items
  • +4Has examples (27 code blocks)
  • +4Reference files are cited in the instructions (5 of 7)
  • +3All 6 scripts are documented
  • +1License stated

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

External checks

ClawHub: suspicious
The skill’s presentation-generation purpose is coherent, but its installer and optional Codex backend create review-worthy credential and broad-agent-execution risks.
LLM: suspicious (high) · 22 Jul 2026