Install
$ agentstack add skill-slidespeak-slide-design-skill-opex ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Operational Excellence — Authoring Guide
A deliberately conservative internal management deck at the bar of a large industrial group's board and steering-committee communication. It is structured, dense and functional. It should look like something a real corporation would table in a programme review, not a designed artefact.
Action titles, not topics
Every content slide's title is a complete-sentence claim, never a label. Read top to bottom, the titles alone carry the management argument.
- Wrong: "Current situation"
- Right: "Growth through acquisitions has increased operational complexity."
Density is the point
These slides carry a lot, on purpose. Use the richest layout the content needs — a numbered point grid, a stat grid, a three-column table, a scoring matrix, a risk table, a layered architecture, an org hierarchy, a timeline. Type always stays readable (14–19px body); never shrink text to fit. Avoid large empty hero slides and excessive whitespace; a steering-committee slide is expected to be full.
Colour discipline
- White ground on content slides; deep navy (#15263D) on cover, closing, message bands and the governance rail.
- Corporate blue (#1F4E79) is the single accent: numerals, key markers, table emphasis, the recommended column. Steel blue (#4A77A8) is a tint only.
- The severity reds/ambers/greens exist only as risk-matrix likelihood/impact chips. Nowhere else.
- Hairlines (#D4DAE1) for rules, gridlines and table borders.
Imagery
- Charts, tables and diagrams are drawn by the system in its own hairlines.
- Any real-world photograph (a plant, a line, a logistics yard, a meeting) is a labelled placeholder frame, never an AI or stock image dropped onto a content slide.
Voice
- Lead with the conclusion. Plain, measured, corporate. No hype, no hedging.
- Sentence case everywhere. This is internal communication, not marketing.
- If a slide could appear in a consumer product launch, it is wrong for this deck.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: SlideSpeak
- Source: SlideSpeak/slide-design-skill
- License: MIT
- Homepage: https://slidespeak.co
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.