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 che626/competition-ppt-template-first-skill --skill competition-ppt-template-firstgit clone --depth 1 https://github.com/che626/competition-ppt-template-first-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/che626/competition-ppt-template-first-skill/competition-ppt-template-first)<a href="https://agentmods.dev/skills/che626/competition-ppt-template-first-skill/competition-ppt-template-first"><img src="https://agentmods.dev/badge/skills/che626/competition-ppt-template-first-skill/competition-ppt-template-first/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/che626/competition-ppt-template-first-skill/competition-ppt-template-first"><img src="https://agentmods.dev/badge/skills/che626/competition-ppt-template-first-skill/competition-ppt-template-first.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 | $0.00090 | $0.04220 |
| Opus 5 | $0.00045 | $0.02110 |
| Sonnet 5 | $0.00018 | $0.00844 |
| Haiku 4.5 | $0.00009 | $0.00422 |
Grade A, and why
competition-ppt-template-first 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competition PPT: Template-First Workflow
Use this skill when a user wants an attractive competition, defense, product-showcase, technical-review, research, or course-presentation deck. The goal is not merely to fill a PPT with text. The goal is a coherent visual narrative in which every page has a purpose-built composition, the important text and evidence remain editable, and the visual system belongs to the actual subject rather than a default AI style.
Read the references needed for the selected mode before creating slides. For any supplied document or project package, read references/content-to-template-analysis.md, references/source-ingestion.md, references/workflow.md, references/project-conventions.md, and references/quality-gates.md; use references/layout-archetypes.md, references/prompt-library.md, references/deck-token-system.md, references/image-asset-roles.md, and references/rendered-visual-critique.md when planning layouts and visual templates.
The Core Principle
Do not start by assembling generic rectangles, UI lines, and text boxes directly in PowerPoint. That approach usually produces a flat, repetitive, low-end deck.
Instead:
- Split the supplied report, requirements, screenshots, data, and user requests into a content-to-deck analysis.
- Decide what kind of deck it is, who must be convinced, what the story route is, and what must visibly appear on every page.
- Lock the deck style tokens and register each image as style reference, template source, real evidence, replaceable screenshot, or decorative cutout.
- Build a slide map, speaker map, layout registry with page rhythm, and template contract for every page before drawing anything. Create a data-evidence plan for every quantitative or comparison claim.
- After that page's contract is complete, generate or art-direct one whole-slide visual template image for every page. The template must include the required visual anchor, real-asset zones, text zones, and subject-specific visual ingredients.
- Turn the approved templates into a layered PPT: background, real images, editable text, and only the overlays that need to remain editable.
- Render, critique composition/hierarchy/density/typography, fix at least one observed defect when needed, and re-inspect the affected pages.
What ships with it
31 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 836 B
- examples/ai-vision-defense-example.md 4.1 KB
- examples/prompt-recipes.md 4.3 KB
- references/content-to-template-analysis.md 8.7 KB
- references/deck-token-system.md 1.7 KB
- references/image-asset-roles.md 2.0 KB
- references/layout-archetypes.md 3.0 KB
- references/project-conventions.md 3.1 KB
- references/prompt-library.md 6.1 KB
- references/quality-gates.md 4.7 KB
- references/rendered-visual-critique.md 3.1 KB
- references/source-ingestion.md 5.0 KB
- references/workflow.md 10 KB
- scripts/__pycache__/init-report-grounded-deck.cpython-310.pyc 2.6 KB
- scripts/init-report-grounded-deck.py 4.9 KB runs code
- scripts/test-workspace-contract.py 2.1 KB runs code
- scripts/validate-distribution.ps1 1.3 KB runs code
- scripts/validate-package.py 5.0 KB runs code
- templates/content-analysis.md 2.4 KB
- templates/data-evidence-plan.md 1.4 KB
- templates/deck-brief.md 2.1 KB
- templates/deck-style-tokens.md 2.4 KB
- templates/fact-registry.md 773 B
- templates/image-asset-register.md 2.0 KB
- templates/layout-registry.md 2.0 KB
- templates/rendered-visual-critique.md 1.2 KB
- templates/revision-record.md 706 B
- templates/slide-blueprint.md 3.1 KB
- templates/slide-source-map.md 873 B
- templates/source-manifest.md 702 B
- templates/speaker-map.md 1.3 KB
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 · 209 lines · 90 tokens per session scan A b7a3b69393bf
competition-ppt-template-first is a skill published in the GitHub repository che626/competition-ppt-template-first-skill (14 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 4,220 once invoked, about $0.0005 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
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign…
codex-ppt
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
deep-ppt
Use when creating or revising research-style PowerPoint decks for lab meetings, journal clubs, defenses, weekly reports, or conferences, especially Chinese or English academic slides that need a resumable agent workflow, the deepPPT blue title system, evidence-led layouts, selective red key findings, package checks…
themed-cn-pptx
Build, modify, and QA-verify Chinese + IP/character-themed + QR-embeddable EDITABLE PPTX decks using PptxGenJS, with SOTA AI image generation via OpenAI GPT Image 2 or Google Nano Banana Pro, locked aesthetic recipes, and a deterministic render-QA gate (CJK overflow, text overlap, editable-text, color contrast).…
imagegen-pptx-pipeline
End-to-end stateful workflow for designing and generating editable PowerPoint decks from briefs, templates, reference decks, brand assets, data, ImageGen comps, or user-supplied slide images. Uses multi-round content/style confirmation, reviewed per-slide comps, mandatory Real-ESRGAN 4K comp/icon upscaling, built-in…
ppt-visual
Design presentation visuals and slide layouts. Create visual concepts, suggest graphics, and provide design specifications for impactful PowerPoint slides.