DD html2pptx
Convert a rendered HTML page (especially A0 conference posters) into a native PowerPoint .pptx with editable text + native shapes — NOT a PNG-in-slide. Walks the live DOM via headless chromium, extracts BLOCK-level text containers (p/h1-h6/li/td) as TextBoxes with inline <strong>/<em> as mixed-style Runs, <img> as Picture with object-fit:contain respected (plus white-tile decoration under transparent-PNG logos), CSS ::before/::after generated content (e.g. 'So what →' callouts) as inherited-style runs, SVG via cairosvg rasterization, decorative <div>/<section> with bg/border/gradient/box-shadow as Rectangle/RoundedRect with matching fill (solid + linear-gradient + outer shadow). All CSS colors (including color-mix/oklab/color()) normalized via canvas. CSS hyphens:auto becomes OOXML soft hyphens via pyphen. CSS line-height absolute Pt for paragraph spacing. Native OOXML bullets with hanging indent. Optional Claude-vision fidelity auditor runs by default (toggle with `--no-vision-audit`); diffs HTML truth vs PPT render → structured 12-category issue report. Supports both direct API (`ANTHROPIC_AUTH_TOKEN`) and base-URL proxy (`ANTHROPIC_BASE_URL`) auth. Targets ~95% visual fidelity with web fonts installed. TRIGGER when user asks: 'HTML to PPT', 'poster to PowerPoint', 'editable PPT from HTML', 'pptx from html', '1:1 PPT clone', or wants an HTML render shipped as an editable .pptx for a non-developer collaborator.
Convert a rendered HTML page (especially A0 conference posters) into a native PowerPoint .pptx with editable text + native shapes — NOT a PNG-in-slide. Walks…
As a process D 42/100 · Unfinished process — References files that are not bundled: assets/…
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 Exfiltration
net-redirectable-api-keyscripts/auto_correct_loop.py:272Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/vision_audit.py:142Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/vision_compare.py:104Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1435 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5669 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/… - note
edit-residuethe text marks something as outdated (lines 287): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 42/100
- 0Tools and files. 1 referenced file(s) missing: assets/…
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5669 tokens
- 85Steps. 55 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (20 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)
- +3Description length 1435: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -33 of 10 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 32.