OpenDesign is an open-source, local-first desktop app that lets coding agents create prototypes, dashboards, slide decks, images, video, and design systems as exportable files. It is used by people working with agent runtimes such as Claude Code, Codex, Cursor, and DeepSeek Harness. The catalogue add-ons extend the OpenDesign workflow with skills, instructions, commands, and plugins.
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 nexu-io/open-design --skill pptx-html-fidelity-auditgit clone --depth 1 https://github.com/nexu-io/open-designWrote 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/nexu-io/open-design/pptx-html-fidelity-audit)<a href="https://agentmods.dev/skills/nexu-io/open-design/pptx-html-fidelity-audit"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/pptx-html-fidelity-audit/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/nexu-io/open-design/pptx-html-fidelity-audit"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/pptx-html-fidelity-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00185 | $0.03488 |
| Opus 5 | $0.00093 | $0.01744 |
| Sonnet 5 | $0.00037 | $0.00698 |
| Haiku 4.5 | $0.00018 | $0.00349 |
Grade A, and why
pptx-html-fidelity-audit 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 8d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- pptx-html-fidelity-audit — 100% identical, 0 lines differ
- pptx-html-fidelity-audit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPTX ↔ HTML Fidelity Audit
A repeatable workflow for catching the ways a python-pptx export silently drifts from its HTML source — and fixing them with a layout discipline that prevents the same regressions on the next pass.
When this skill applies
The user has:
-
A source HTML slide deck (typically a single-file deck with
<section class="slide">blocks):<section class="slide light"> <div class="chrome">2026 · Q2 review</div> <span class="kicker">Pillar 03</span> <h2 class="h-xl">Shipping <em>velocity</em> doubled</h2> <p class="lead">…</p> <div class="foot">page 5 / 14</div> </section> -
A PPTX file generated from that deck via python-pptx (or similar).
-
A suspicion (or visible evidence) that the PPTX doesn't match the HTML — text bleeding into the footer, italic words gone flat, hero slides not centered, sections cropped, tag styling lost.
If the user only has one of those two artifacts, this skill doesn't apply yet — first generate the missing one, or ask the user to provide it.
Why this is hard (and why a skill helps)
PPTX is a fixed-canvas, absolute-positioned medium. HTML is a fluid, flow-based medium. A naive python-pptx export pins each block at hand-picked (top, left) coordinates, which works for the first slide it was tested on and silently fails for every other slide whose content has different intrinsic height. The result is the most common drift modes:
- Footer overflow — content's
top + heightcrosses into the footer row. - Off-canvas content — bottom of last block exceeds
7.5"(16:9 canvas). - Italic loss —
<em>in HTML never getsrun.font.italic = True. - Hero slides not centered — vertical-stack slides use
MARGIN_TOPinstead of computing center. - Box bounds intruding — the text fits, but the shape's bounding box is oversized and visually crosses the rail.
- Tag/styling loss — colored chrome rows, kicker uppercase tracking, mono-vs-serif assignments quietly fall back to defaults.
What ships with it
4 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.
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.
- 8d ago First seen · 255 lines · 185 tokens per session scan A 4d1fe39410f0
pptx-html-fidelity-audit is a skill published in the GitHub repository nexu-io/open-design (95,624 stars, last pushed today), licensed Apache-2.0. It adds 185 tokens to every session and 3,488 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
e2e-testing
ORGII keeps two separate E2E surfaces. Do not use one as proof for the other.
dual-instance-verification
Dual-instance (双机) real-machine verification protocol for ORG2 cloud sync and session sharing. Use before declaring any sharing/sync/collab feature or fix "verified": share/unshare, push/retract, fork/import, comments, member-floor, replay, continuation, or anything touching Org2CloudSyncEngine, collab engines, or the…
cuj-guardian
Run and triage AI Atelie's Critical User Journey (CUJ) for every PR — the single end-to-end test that proves a user can open the app, create a project, drive the Claude Code agent, and see the canvas render. Before running, gate by inspecting the PR diff for changes that plausibly affect the journey (routes…
pr-evidence
Run AI Atelie's journey suite and inject inline-rendering evidence (per-journey video + screenshot, in a 4-column markdown table) into the current PR's body. Use whenever the user says "post evidence", "run journeys", "update PR with videos", or after ship-task opens a PR. Wraps bun run journeys; idempotent — re-runs…
verify-with-playwright
Drive a real browser against AI Atelie's running dev server to verify a change works, and capture screenshots + video as PR evidence. Use whenever the user asks to "verify in browser", "prove it works", "add PR evidence", or before opening a PR that touches web/ or any user-facing surface. Assumes bun run dev is…
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.