Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add CxyZyr/PPTX-Template-Skills --skill ppt-template-adaptationgit clone --depth 1 https://github.com/CxyZyr/PPTX-Template-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cxyzyr/pptx-template-skills/ppt-template-adaptation)<a href="https://agentmods.dev/skills/cxyzyr/pptx-template-skills/ppt-template-adaptation"><img src="https://agentmods.dev/badge/skills/cxyzyr/pptx-template-skills/ppt-template-adaptation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cxyzyr/pptx-template-skills/ppt-template-adaptation"><img src="https://agentmods.dev/badge/skills/cxyzyr/pptx-template-skills/ppt-template-adaptation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01048 |
| Opus 5 | $0.00039 | $0.00524 |
| Sonnet 5 | $0.00015 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
ppt-template-adaptation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Template Adaptation
Use this skill when the task is to rewrite an existing PPT template into a new deck while preserving the
template's visual logic. It consumes spec.json from pptx-template-parsing; do not start from a failed
generated deck or manually inferred shape indices.
This skill is intentionally self-contained. Do not read old external handbooks from previous projects.
What this skill enforces
- Parse first, generate second. If a slot, card count, or style is missing, fix parsing before adding generation fallback logic.
- Work page by page. Incremental runs keep original slide indices stable until the final full build.
- Keep one global outline as the source of truth for contents pages, section dividers, and section titles.
- Fill text before icons, logo, and images.
- Preserve parsed template style: geometry, alignment, theme colors, paragraph/run structure, and number badges unless the user asks for redesign.
- Replace icons and images only when semantics require it and a valid slot exists.
- Validate each page before moving on.
Inputs
- Original template
.pptx. - Parsed
spec.jsonfrompptx-template-parsing. - A
content_plan.jsonwithspec,output,asset_dir, optionalbrand,keep_slides, optionaloutline, andpages[].
Required workflow
- If no current
spec.jsonexists, runpptx-template-parsingfirst. - Read the parser
summary.txt; choose template slides whose roles and slot counts match the needed story. Avoid chart/table slides unless chart/table data will be supplied. - Scaffold a plan:
python3 skills/ppt-template-adaptation/scripts/scaffold_content_plan.py \
--spec workspace/specs/<template>/spec.json \
--out workspace/plans/<deck>.content_plan.json \
--output-pptx workspace/out/<deck>.pptx
- Edit
keep_slides,outline, andpages[]. Map each page to existing slots only: titles totitle, free labels tolabels[], body boxes tobody[], repeated structures tocards[], semantic glyphs tocards[].icon, and photos/screenshots toimages[]. - Validate global text coherence:
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 256 B
- lib/__init__.py 109 B runs code
- lib/pptx_toolkit/__init__.py 2.2 KB runs code
- lib/pptx_toolkit/assets.py 3.2 KB runs code
- lib/pptx_toolkit/autofit.py 13 KB runs code
- lib/pptx_toolkit/content.py 68 KB runs code
- lib/pptx_toolkit/deck.py 815 B runs code
- lib/pptx_toolkit/fonts.py 2.2 KB runs code
- lib/pptx_toolkit/geometry.py 1.0 KB runs code
- lib/pptx_toolkit/render.py 2.9 KB runs code
- lib/pptx_toolkit/shapes.py 2.9 KB runs code
- lib/pptx_toolkit/text.py 8.2 KB runs code
- lib/pptx_toolkit/walk.py 13 KB runs code
- references/icon-fill.md 3.5 KB
- references/image-fill.md 4.1 KB
- references/text-coherence.md 3.6 KB
- references/workflow.md 7.8 KB
- scripts/apply_content_plan.py 9.5 KB runs code
- scripts/render_pages.py 2.3 KB runs code
- scripts/scaffold_content_plan.py 4.5 KB runs code
- scripts/tavily_image_service.py 22 KB runs code
- scripts/validate_content_plan.py 14 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 103 lines · 77 tokens per session scan A 3d75f224ff44
ppt-template-adaptation is a skill published in the GitHub repository CxyZyr/PPTX-Template-Skills (28 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 1,048 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.