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 SlideSpeak/slide-design-skill --skill pitchgit 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/skills/slidespeak/slide-design-skill/pitch)<a href="https://agentmods.dev/skills/slidespeak/slide-design-skill/pitch"><img src="https://agentmods.dev/badge/skills/slidespeak/slide-design-skill/pitch/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/slidespeak/slide-design-skill/pitch"><img src="https://agentmods.dev/badge/skills/slidespeak/slide-design-skill/pitch.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 | $0.00061 | $0.01027 |
| Opus 5.5 | $0.00024 | $0.00411 |
| Sonnet 5.5 | $0.00012 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
pitch 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch Style — Authoring Guide
You write decks as if you are the founder pitching to top-tier investors. The reader has 8 minutes. They will remember three things at most.
Voice
- First-person plural. "We", not "the company".
- Headlines are decisions, not descriptions. "We are building the operating system for legal teams" not "About our product".
- Numbers come before words. "$12M ARR, +18% MoM" before any paragraph.
- No buzzwords. "Disrupt", "synergy", "ecosystem play" — banned. Use plain English.
- If a slide has more than 25 words of body copy, cut to 15.
Structure (canonical pitch arc)
- Cover — company name, single line of what you do
- Problem — one sentence, named persona
- Market size — TAM/SAM/SOM as three numbers, no spreadsheet
- Solution — product screenshot or live demo placeholder, single claim
- Why now — single trend, single chart
- Traction — three metrics, one chart
- Business model — pricing tiers, one number per tier
- GTM — three channels, owner of each
- Team — founders only, three bullets each max
- Competition — 2x2 framework or feature matrix
- Ask — single number, single use of funds split (3 bullets)
Visual System
- Off-white ground (#FAFAF8), ink (#0A0A0A).
- ONE accent color per deck (default: electric blue #2563EB). Used for: cover wordmark, big numbers, the underline beneath the ask.
- Typography is one family in 3 weights (regular, semibold, bold). No serifs. No italics except for sourcing.
- 8-column grid, 32px gutter. Numbers and headlines align to this grid hard.
- Generous whitespace. A pitch slide that looks full looks amateur.
Graphic system
- Signature mark: the conviction stroke, a single rising stroke with a square terminal (a chart reduced to its claim), drawn as inline SVG. It appears small and exact at the cover masthead, beside the why-now trend line, and above the ask. Always the same geometry, never redrawn per slide.
- Depth moment: the cover carries the stroke at roughly 25x scale, pale blue, cropped by the bottom-right canvas edge, behind the wordmark.
- Surface: cover and ask sit on a faint chart-paper grid (hairlines at 120px). All other slides stay flat off-white.
- Structural device: metric and feature rules are an ink hairline carrying a short 56px signal dash at the left end (.px-rule), never a full-width colored border.
- The system never does: shapes unrelated to the rising stroke, decoration on the problem slide (the claim stands alone), more than one stroke instance per slide.
What ships with it
5 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.
- 1mo ago First seen · 75 lines · 61 tokens per session scan A 4abe05aae5ce
pitch is a skill published in the GitHub repository SlideSpeak/slide-design-skill (29 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,027 once invoked, about $0.0002 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 skills, from other repositories
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
queues-jobs
Implement reliable asynchronous jobs and message consumers with explicit delivery, retry and shutdown semantics. Use when adding BullMQ or another established queue, background processing or scheduled work; enqueue success is not job completion.