Borrowing it
Nothing to install: this file belongs to SlideSpeak/slide-design-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SlideSpeak/slide-design-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/SlideSpeak/slide-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/instructions/slidespeak/slide-design-skill/claude-md)<a href="https://agentmods.dev/instructions/slidespeak/slide-design-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/slidespeak/slide-design-skill/claude-md/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/instructions/slidespeak/slide-design-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/slidespeak/slide-design-skill/claude-md.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 | $0.01582 | $0.01582 |
| Opus 5.5 | $0.00633 | $0.00633 |
| Sonnet 5.5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
slide-design-skill CLAUDE.md 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slide-design-skill — Session Rules (READ FIRST, applies to EVERY session in this repo)
The product has NO selectable styles. None. Ever.
There are no themes, no templates, no presets, no "flagship skills" the user picks from. The user describes what they want; a style is generated/derived from that brief, every single time. "Choosing a style" is not a concept that exists here.
NEVER surface internal machinery to the user
The folders under skills/ are internal generator seed/reference material only.
The user must not know they exist. When talking to the user, you are FORBIDDEN from
saying (or implying) any of:
- "flagship skill(s)", "preset(s)", "template(s)", "theme(s)"
- the name of any folder under
skills/(consulting, pitch, stripe, …) - "bespoke X (not chosen from the presets/flagship skills)" ← this exact leak just happened, never do it
- "I matched the built-in …", "deriving from stripe.com as the brief says", or any narration of how the style got resolved
If you catch yourself explaining the approach or the architecture, stop. The user does not want a status report on the plumbing.
What to actually do
- Take the brief (topic + content + look-in-any-form).
- Silently derive the look and generate a fully bespoke style for this deck
(its own tokens, slide types, and
chrome.css). - Author the deck, render it, show the user the result (screenshots / the HTML).
- Iterate on the user's feedback.
Minimal narration. No menus. No meta-talk. If the brief carries zero signal about the look, ask ONE short question about the desired look — otherwise never ask, just build.
Moodboard step (image-first style anchor, optional but preferred)
When the look is open (inspiration-style briefs, weak signal) and FAL_KEY is
available: generate 2 moodboards via composeMoodboardPrompts(subject)
(engine/moodboard.ts) rendered through FalProvider (flux/dev), show them to
the user, let them pick. The prompts already rotate each board onto a different
unexpected colour axis — NEVER write moodboard prompts by hand without an axis;
the image model carries the same genre-default bias as the LLM and will return
the cliché palette (verified: "premium chocolate" → beige+espresso every time).
View the approved board yourself, extract palette hexes / type mood / material
world, and feed it into the generation brief via moodboardDirectionBlock(...).
An approved board outranks the banned-default-palette rule (the client chose it).
A concrete image to translate produces visibly more coherent styles than
adjectives (veta A/B, 2026-06).
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 First seen · 103 lines · 1,582 tokens per session scan A 77ba6b4a5fa7
slide-design-skill CLAUDE.md is an instructions file published in the GitHub repository SlideSpeak/slide-design-skill (29 stars, last pushed 4mo ago), licensed MIT. It adds 1,582 tokens to every session, about $0.0063 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.