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 agentmods add skills/carbonshow/intent-fluid/slidevnpx skills add carbonshow/intent-fluid --skill slidevgit clone --depth 1 https://github.com/carbonshow/intent-fluidWrote 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/carbonshow/intent-fluid/slidev)<a href="https://agentmods.dev/skills/carbonshow/intent-fluid/slidev"><img src="https://agentmods.dev/badge/skills/carbonshow/intent-fluid/slidev.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.06298 |
| Opus 5 | $0.00042 | $0.03149 |
| Sonnet 5 | $0.00017 | $0.01260 |
| Haiku 4.5 | $0.00008 | $0.00630 |
Grade A, and why
slidev 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 4d 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 — 649 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slidev
You are a presentation engineer specializing in Slidev. You create Markdown-based slide decks with animations, code highlighting, and Vue interactivity, using a centralized runner that avoids per-project npm installs.
This skill bundles scripts for deterministic operations (initialization, validation, quality review, image generation, build/export, and visual audit). Your job is to make content design decisions and orchestrate these scripts — not to re-implement their logic in natural language.
Resolving Paths
Every script in this skill auto-resolves its own location using
$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd). You do not need to hard-code
paths. Just find the directory containing this SKILL.md (the skill root) and call
scripts relative to it:
SKILL_ROOT="<directory containing this SKILL.md>"
bash "$SKILL_ROOT/scripts/new-presentation.sh" ...
bash "$SKILL_ROOT/scripts/validate-slides.sh" ...
bash "$SKILL_ROOT/scripts/run.sh" ...
bash "$SKILL_ROOT/scripts/review-presentation.sh" ...
bash "$SKILL_ROOT/scripts/build-deck.sh" ...
All scripts accept absolute paths for the slides file. Always resolve paths to absolute before passing them.
Critical Gotchas
These cause silent failures. The validate-slides.sh script checks for all of
them automatically, but understanding why helps you avoid them while editing.
1. No --- inside frontmatter (including comments)
Slidev uses --- to delimit frontmatter. A --- on any line between the opening
and closing delimiters — even inside a YAML comment — silently truncates everything
after it. The YAML parser sees it as "frontmatter ends here" and the rest becomes
orphaned slide content.
# BAD — comment contains ---, truncates theme and everything below
# --- Field definitions below ---
theme: default
# GOOD — no --- anywhere in frontmatter body
theme: default
2. colorSchema: light is mandatory
Slidev inherits the operating system's color scheme by default. On machines set to
dark mode, the default theme renders dark text on a dark background — invisible.
Forcing colorSchema: light makes the presentation look the same everywhere,
regardless of the viewer's OS settings.
What ships with it
60 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.
- assets/runner/package-lock.json 339 KB
- assets/runner/package.json 340 B
- assets/slidev-starter/slides.md 2.4 KB
- assets/themes/_skeleton.css 7.8 KB
- assets/themes/.gitkeep 0 B
- assets/themes/code-focus-light.css 5.3 KB
- assets/themes/code-focus-light.image-style.txt 148 B
- assets/themes/corporate-navy.css 5.3 KB
- assets/themes/corporate-navy.image-style.txt 116 B
- assets/themes/edu-warm.css 5.3 KB
- assets/themes/edu-warm.image-style.txt 98 B
- assets/themes/minimal-exec.css 5.3 KB
- assets/themes/minimal-exec.image-style.txt 124 B
- assets/themes/playful-bright.css 5.6 KB
- assets/themes/playful-bright.image-style.txt 97 B
- assets/themes/tech-dark.css 5.6 KB
- assets/themes/tech-dark.image-style.txt 134 B
- evals/sp1-scenarios/01-tech-talk/result.md 4.7 KB
- evals/sp1-scenarios/01-tech-talk/scenario.md 1.7 KB
- evals/sp1-scenarios/02-exec-report/result.md 4.0 KB
- evals/sp1-scenarios/02-exec-report/scenario.md 981 B
- evals/sp1-scenarios/03-edu-course/result.md 4.3 KB
- evals/sp1-scenarios/03-edu-course/scenario.md 1.1 KB
- evals/sp1-scenarios/DELIVERY.md 10 KB
- evals/sp1-scenarios/fixtures/.gitkeep 0 B
- evals/sp1-scenarios/fixtures/check10-tests.sh 1.5 KB runs code
- evals/sp1-scenarios/fixtures/grader-tests.sh 2.7 KB runs code
- evals/sp1-scenarios/fixtures/invalid-layout.md 281 B
- evals/sp1-scenarios/fixtures/over-length.md 471 B
- evals/sp1-scenarios/fixtures/review-count-tests.sh 3.1 KB runs code
- evals/sp1-scenarios/fixtures/theme-flag-tests.sh 3.3 KB runs code
- evals/sp1-scenarios/fixtures/two-columns-bad-pattern.md 397 B
- evals/sp1-scenarios/fixtures/two-columns-valid.md 653 B
- evals/sp1-scenarios/fixtures/valid.md 1.1 KB
- evals/sp2-scenarios/01-image-focus/result.md 4.1 KB
- evals/sp2-scenarios/01-image-focus/scenario.md 8.1 KB
- evals/sp2-scenarios/02-image-text-split/result.md 3.6 KB
- evals/sp2-scenarios/02-image-text-split/scenario.md 7.8 KB
- evals/sp2-scenarios/03-two-columns-image/result.md 4.7 KB
- evals/sp2-scenarios/03-two-columns-image/scenario.md 9.1 KB
- evals/sp2-scenarios/DELIVERY.md 6.9 KB
- evals/sp2-scenarios/fixtures/grader-tests.sh 3.4 KB runs code
- evals/sp2-scenarios/fixtures/minimal-deck/_skeleton.css 78 B
- evals/sp2-scenarios/fixtures/minimal-deck/image-style.txt 134 B
- evals/sp2-scenarios/fixtures/minimal-deck/public/hero.jpg 1 B
- evals/sp2-scenarios/fixtures/minimal-deck/slides.md 1.3 KB
- evals/sp2-scenarios/fixtures/minimal-deck/theme.css 183 B
- evals/visual-audit/.gitkeep 0 B
- ISSUES.md 5.3 KB
- references/content-design.md 13 KB
- references/content-strategy.md 11 KB
- references/eval-suite.md 4.6 KB
- references/frontmatter-guide.md 3.1 KB
- references/image-generation.md 11 KB
- references/layout-catalog.md 29 KB
- references/slidev-syntax.md 9.1 KB
- references/theme-library.md 8.0 KB
- references/troubleshooting.md 7.5 KB
- scripts/.preflight.sh 720 B runs code
- scripts/audit-visual.sh 696 B 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.
- 4d ago First seen · 649 lines · 83 tokens per session scan A beb3d22af326
slidev is a skill published in the GitHub repository carbonshow/intent-fluid (6 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 6,298 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 2026-08-31.
Other skills, from other repositories
slidev
Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.
slidev-deck-pipeline
Deterministic pipeline for authoring, verifying, exporting, and deploying OpenCoven Slidev decks (the weekly Show'n Spells system and one-off branded decks). Use whenever asked to build, rebuild, update, export, or publish a Slidev slide deck for OpenCoven — weekly meeting decks, launch decks, or explainer decks.
presentation-forge
创建中文商业汇报，从主题、文档或 slides.md 生成原生可编辑 PPTX，提供 Markdown-first 实时画布、样式切换和同版导出，使用 image-2 辅助生成独立视觉资产，把截图或图片型幻灯片重建为可编辑 PPTX/SVG，或用原生 PPTX 模板填充新内容。用户要求制作售前方案、项目汇报、产品介绍、行业分析、培训材料、像 Markdown 一样编辑并导出、AIPPT 式可编辑演示、套用 PowerPoint 模板、图片页转可编辑 PowerPoint、重建幻灯片或输出 SVG 时使用。.
dev-slides
This skill enables creation of developer-focused presentations using Slidev - a Vue-powered presentation framework. Write slides in Markdown with live code demos, diagrams, and components.
md-slides
This skill enables creation of presentations from pure Markdown using Marp. Write slides in familiar Markdown syntax and export to PDF, PPTX, or HTML with professional themes.
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…