PPT Design Skill is a workflow for creating native, editable PowerPoint presentations from requirements, combining content planning, visual design, generation, and image-based review. It is intended for professional presentations such as proposals, strategy decks, investor materials, and formal reports. The catalogue entries provide the instructions and skill used by coding agents to carry out this workflow.
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 sunchaokun/PPT-Design-Skill --skill skillgit clone --depth 1 https://github.com/sunchaokun/PPT-Design-SkillWrote 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/sunchaokun/ppt-design-skill/skill)<a href="https://agentmods.dev/skills/sunchaokun/ppt-design-skill/skill"><img src="https://agentmods.dev/badge/skills/sunchaokun/ppt-design-skill/skill/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/sunchaokun/ppt-design-skill/skill"><img src="https://agentmods.dev/badge/skills/sunchaokun/ppt-design-skill/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.03981 |
| Opus 5.5 | $0.00014 | $0.01592 |
| Sonnet 5.5 | $0.00007 | $0.00796 |
| Haiku 4.5 | $0.00003 | $0.00398 |
Grade A, and why
ppt-design-skill 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 1mo 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Design Skill
This skill is a presentation design director and delivery workflow. The
pptx-designer Python package is the rendering engine; this skill decides
what should be designed, how it should be structured, how it should look, and
whether the rendered result actually satisfies the user's need.
The design framework below keeps the mature design judgment, content rules,
domain paradigms, and quality standards that make the workflow reliable. The
implementation engine is the public pptx-designer Python library.
Designer mindset
Act as a senior presentation designer. Make decisions from the audience and the communication goal, not from the list of available Python functions.
- Audience first: decide what the audience must understand, remember, feel, or do before choosing a layout.
- Restraint over decoration: one clear accent system is better than random effects; every element must earn its place.
- Systematic thinking: a deck is one visual system, not independent pages. Lock margins, spacing rhythm, typography, color roles, corner treatment, image treatment, and component language.
- Intentional variation: vary page architecture and density when the story changes, not merely to make pages look different.
- Explain decisions: be able to state why a page uses a figure, chart, comparison, diagram, image, or sparse statement for this audience.
Stop before writing code
For a new delivery-grade presentation task, initialize the task from
templates/task-init/ and keep task-specific requirements in those task
files. Run init_presentation_task.py from the loaded Skill's scripts/
directory (use its absolute path if the working directory is the project):
python <skill-root>/scripts/init_presentation_task.py --project <project-root> --name <lowercase-task-slug>. It creates an isolated
<project-root>/ppt_tasks/<task-slug>/ and refuses to overwrite it. Do not
begin implementation while a required research or direction decision remains
unresolved.
What ships with it
54 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 377 B
- references/composition-recipes/c1-01.json 958 B
- references/composition-recipes/c2-01.json 1.0 KB
- references/composition-recipes/c3-01.json 888 B
- references/composition-recipes/c4-01.json 940 B
- references/composition-recipes/composition_index.json 413 B
- references/content-schema.md 1.0 KB
- references/design-direction-coach.md 5.2 KB
- references/design-principles.md 5.1 KB
- references/domain-paradigms.md 1.5 KB
- references/install-and-runtime.md 3.1 KB
- references/public-api.md 4.7 KB
- references/qa-and-delivery.md 5.7 KB
- references/scientific-visual-baseline.md 4.2 KB
- references/template-brand.md 2.5 KB
- references/visual-rendering-packs/dark-cinematic-tech.json 1.6 KB
- references/visual-rendering-packs/editorial-infrastructure-ledger.json 2.0 KB
- references/visual-rendering-packs/rendering_packs_index.json 409 B
- references/visual-rendering-packs/scientific-atlas.json 1.6 KB
- references/workflow.md 7.7 KB
- schemas/acceptance-record.schema.json 1.3 KB
- schemas/composition-entry.schema.json 1.6 KB
- schemas/composition-recipe.schema.json 2.5 KB
- schemas/prototype-record.schema.json 2.0 KB
- schemas/rendering-pack.schema.json 2.0 KB
- schemas/runtime-trace.schema.json 1.4 KB
- scripts/audit_case_outputs.py 2.5 KB runs code
- scripts/audit_prototype_provenance.py 3.5 KB runs code
- scripts/audit_regression_pairs.py 3.5 KB runs code
- scripts/audit_visual_review_records.py 2.3 KB runs code
- scripts/build_regression_baselines.py 4.3 KB runs code
- scripts/check_runtime.py 1.4 KB runs code
- scripts/check_scientific_baseline.py 2.8 KB runs code
- scripts/init_presentation_task.py 2.7 KB runs code
- scripts/inspect_pptx.py 1.5 KB runs code
- scripts/inspect_visual_assets.py 2.9 KB runs code
- scripts/refresh_case_prototypes.py 5.5 KB runs code
- scripts/render_pptx.ps1 5.8 KB runs code
- scripts/run_visual_workflow.py 3.1 KB runs code
- scripts/runtime_deps.py 2.0 KB runs code
- scripts/validate_acceptance_record.py 2.2 KB runs code
- scripts/validate_runtime_trace.py 1.9 KB runs code
- scripts/validate_visual_pack.py 12 KB runs code
- templates/case-prototype-index.json 1.7 KB
- templates/case-prototypes/README.md 454 B
- templates/regression-manifest.json 1.3 KB
- templates/task-init/acceptance-contract.md 343 B
- templates/task-init/brief.md 254 B
- templates/task-init/page-plan.md 150 B
- templates/task-init/research.md 449 B
- templates/task-init/task.yaml 356 B
- templates/task-init/theme-lock.yaml 307 B
- templates/task-init/visual-direction.md 610 B
- templates/task-init/visual-review.md 486 B
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.
- 1mo ago Changed · +3 lines 8f758a262fc5
- 1mo ago Changed · +17 lines e8ae4fa65e55
- 1mo ago First seen · 346 lines · 35 tokens per session scan A edcd0a51dd92
ppt-design-skill is a skill published in the GitHub repository sunchaokun/PPT-Design-Skill (350 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 3,981 once invoked, about $0.0001 per session on Opus 5.5. 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
autodoc-next-prospectus-audit
Audit one local prospectus PDF, DOC, or DOCX through PDRouter and download the annotated document with AutoDoc NEXT2.0.
ChatDOC Studio--KnowledgeMate
Create and operate ChatDOC Studio knowledge bases through pdrouter using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base…
Calliper-Compare2Markdown
Compare two local documents and convert differences into LLM-ready Markdown in one synchronous call. Supports PDF, Word, PPT, and image documents accepted by Calliper, and returns a structured markdown diff table suitable for change review, clause comparison, downstream extraction, and rule-based validation.
PDFlux-PDF2Markdown
Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and…
chatdoc-studio-api
ChatDOC Studio API usage guide - complete documentation and examples for PDF parsing, chat applications, agent applications, content retrieval, and data extraction APIs.
open-codex-ui
Install, update, secure, daemonize, expose through Cloudflare Tunnel, and enable speech input for the open-source Open Codex UI application. Use when a user asks to install or enable Open Codex UI, configure its login daemon, set its access password, install or manage the sherpa-onnx bilingual speech model…