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 ai-analyst-lab/ai-analyst-plugin --skill deck-critiquegit clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-pluginWrote 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/ai-analyst-lab/ai-analyst-plugin/deck-critique)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/deck-critique"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/deck-critique.svg" alt="Measured on agentmods" height="20"></a>- 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 | $0.00115 | $0.03505 |
| Opus 5 | $0.00057 | $0.01752 |
| Sonnet 5 | $0.00023 | $0.00701 |
| Haiku 4.5 | $0.00012 | $0.00350 |
Grade A, and why
deck-critique 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.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Deck Critique
Purpose
Score any presentation slide-by-slide against the Data Story Checklist (SO-WHAT, STAKES, EVIDENCE, ASK). Returns a diagnosis report with per-slide scorecards, anti-pattern flags, an overall grade, and a prioritized prescription for fixes.
When to Use
Apply this skill when:
- The user asks to review, critique, or diagnose a deck — "review my deck", "what's wrong with these slides", "critique this presentation"
- Before running
/deck-rescue— the critique is a prerequisite input for the full rescue pipeline - The user provides a Marp
.marp.mdfile or a Google Slides URL/ID for evaluation
This skill can be invoked directly as /deck-critique or auto-fires when the presentation-doctor orchestrator agent runs.
Inputs
{{DECK_SOURCE}}: Path to a Marp.marp.mdfile OR a Google Slides presentation ID/URL{{AUDIENCE}}(optional): Who the presentation is for — informs STAKES scoring{{CONTEXT}}(optional): What decision or meeting this deck supports
Instructions
The Data Story Checklist Scoring System
Every slide is scored on 4 dimensions, each 0-3 points (max 12 per slide):
SO-WHAT (0-3): Does the title state a finding?
| Score | Criteria | Example |
|---|---|---|
| 3 | Action headline — states a specific finding with data | "Incomplete onboarding drives 67% of enterprise churn" |
| 2 | Descriptive headline — describes what's shown but not what it means | "Churn by onboarding status" |
| 1 | Label — generic category name | "Churn Analysis" |
| 0 | Missing or generic — no title, or "Q3 Results" | "Q3 Update" |
STAKES (0-3): Does the audience know why this matters?
| Score | Criteria | Example |
|---|---|---|
| 3 | Explicit impact — quantified business consequence | "$2.3M ARR at risk, growing 15% QoQ" |
| 2 | Implied impact — consequence is suggested but not quantified | "This is our fastest-growing churn segment" |
| 1 | Generic — vague importance claim | "This is important for the business" |
| 0 | None — no reason given for audience to care | (just data, no framing) |
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 · 292 lines · 115 tokens per session scan A b3652d457508
deck-critique is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 12d ago), licensed MIT. It adds 115 tokens to every session and 3,505 once invoked, about $0.0006 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.