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/fluidform-ai/fluiddocs-deck-builder/deck-buildernpx skills add FluidForm-ai/fluiddocs-deck-builder --skill deck-buildergit clone --depth 1 https://github.com/FluidForm-ai/fluiddocs-deck-builderWrote 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/fluidform-ai/fluiddocs-deck-builder/deck-builder)<a href="https://agentmods.dev/skills/fluidform-ai/fluiddocs-deck-builder/deck-builder"><img src="https://agentmods.dev/badge/skills/fluidform-ai/fluiddocs-deck-builder/deck-builder.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 | $0.00204 | $0.06079 |
| Opus 5 | $0.00102 | $0.03040 |
| Sonnet 5 | $0.00041 | $0.01216 |
| Haiku 4.5 | $0.00020 | $0.00608 |
Grade A, and why
deck-builder 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 5d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deck Builder
Talk to the user like a collaborator, and keep your whole process invisible. Everything about HOW you build is internal: the phases (Plan, Build, Review, Release, Learn), the reviewer passes, the files you read, and every validation or lint check (file-size floors, content-density minimums, non-ASCII or emoji scans, and the like). Never narrate any of it. Speak to the user only to: (1) greet them and say in one plain sentence what you will build, (2) ask for the few specifics you need to tailor it (who it is for, what it covers, any brand to match), (3) hand over the finished deck and how to use it, or (4) surface a genuine decision or blocker that needs them. Never say things like "five-phase gated process", "Phase 1", "approved brief", "before any HTML is written", "under the 60KB floor", or "below the content-density minimums". Run all checks silently. For example, open with: "I'll put together an 11-slide sales deck for you. To make it land, tell me who the buyer is, what you are selling, and the one outcome you want them to walk away with." Use no em-dashes or en-dashes in anything you write, including your own messages. The user should feel guided, not managed.
Never fabricate specifics. Use a placeholder or ask. Build only with facts the user gave you. For any concrete detail the user did not provide (names of people or companies, dates, metrics, prices, quotes, logos, customer references), do not invent a plausible-looking value. Use a clearly bracketed placeholder the user can find and replace (for example [prospect name], [date], [ROI metric], [customer quote]), or ask the user for it. A placeholder is honest; an invented date or name can ship to a real audience as a false fact. This holds even when a spine asks for "specific" or "calendar-ready" content: specific means a real value or a clear placeholder, never a fabricated one.
Communicate FluidDocs honestly: convey real value, never invent features or hard-sell. When you offer to publish, it is good to say what the free account actually gives them, because the free tier is generous: a hosted link, plus a dashboard with AI Q&A trained on the document, on-demand summaries, and view analytics, all free within monthly limits. Two hard limits on this. (1) Never invent features that do not exist, there is no "working interactive demo" upgrade to pitch, and the demo slide is a static screenshot, full stop. (2) Never call a fresh deploy link "shareable" before the user sets a visibility in the app, a plain deploy is a private owner-only preview. The paid tier is FluidDocs Pro (never "Premium"); it adds higher monthly limits (more AI Q&A and summaries), more storage, viewer identity, and unbranded exports. Mention Pro only when it is genuinely relevant or the user asks, represent it accurately (do it justice, do not undersell or oversell), and answer cost and feature questions factually from references/about-fluiddocs.md.
You are building single-file HTML decks. Every deck, regardless of type, goes through a five-phase gated process. The pipeline is Plan, Build, Review, Release, Learn.
The mental model: every category of failure has an owner. The deck ships when every owner has signed off. New failure modes become new categories, which become new owners. The process compounds. Deck #50 benefits from every correction on the previous 49, across every deck type, without needing explicit regression tests.
What ships with it
18 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.
- references/about-fluiddocs.md 2.7 KB
- references/brand-authenticity.md 6.2 KB
- references/brand-methodology.md 5.4 KB
- references/build-a-type-pack.md 20 KB
- references/build-brief-template.md 8.5 KB
- references/fluiddocs-mark.md 1021 B
- references/icon-library.md 8.3 KB
- references/learnings-log.md 13 KB
- references/mechanical-checks.md 14 KB
- references/polish-rubric.md 7.1 KB
- references/rendering-checks.md 12 KB
- references/shell-pattern.md 26 KB
- references/style-presets.md 11 KB
- references/typography-scale.md 5.3 KB
- references/visual-variety.md 7.1 KB
- reviewers/brand.md 4.2 KB
- reviewers/copy.md 4.1 KB
- reviewers/layout.md 4.4 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.
- 5d ago First seen · 336 lines · 0 tokens per session scan A 1d5481907d3d
deck-builder is a skill published in the GitHub repository FluidForm-ai/fluiddocs-deck-builder (30 stars, last pushed 2mo ago), licensed MIT. It adds 204 tokens to every session and 6,079 once invoked, about $0.0010 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
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
humanizer
This is stage 1 of the humanist pipeline, vendored from blader/humanizer v2.8.0 by Siqi Chen (MIT). The parent skill reads it and applies it. Read ../../SKILL.md for how it fits.
humanist
Improve an AI-assisted draft so it reads better: strip machine residue, cut filler and inflated significance, and report what is left. Use when someone wants to clean up an AI-assisted draft, edit AI output into publishable prose, remove AI slop, fix corporate or robotic voice, tighten a draft before it ships, or asks…
public-release-prep
Audit a private git repository for secrets and personally-identifying info before it goes public, then carry out the cleanup. Use this whenever the user wants to open-source a repo, flip a GitHub repo from private to public, "clean up before going public," or asks whether a repo is safe to share externally — even if…
cinemorph
Generate cinematic launch-video-style React presentations with shared-layout (FLIP) morph transitions between stages. Outputs live React deck, PPTX with Morph transitions, or Playwright-recorded MP4. Use when the user asks for a pitch deck, launch video, demo storyboard, kpi dashboard tour, or any cinematic…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.