Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jamditis/claude-skills-journalism/plugin install pdf-playgroundWrote 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/commands/jamditis/claude-skills-journalism/slides)<a href="https://agentmods.dev/commands/jamditis/claude-skills-journalism/slides"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/slides/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/commands/jamditis/claude-skills-journalism/slides"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/slides.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 | $0.00008 | $0.01912 |
| Opus 5.5 | $0.00003 | $0.00765 |
| Sonnet 5.5 | $0.00002 | $0.00382 |
| Haiku 4.5 | $0.00001 | $0.00191 |
Grade A, and why
slides 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create HTML presentation slides.
Version check
Read the plugin version from ${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json and note it. If the file doesn't exist or the read fails, warn the user that the plugin may not be properly installed.
Setup
- Check for brand configuration at
.claude/pdf-playground.local.md - If found, parse the YAML frontmatter for brand settings
- Load the slides template from
${CLAUDE_PLUGIN_ROOT}/templates/slides-template.html
Slide format
Default: 16:9 widescreen (13.333" × 7.5"). For 4:3, update both places in templates/slides-template.html:
--slide-width: 10inon the:rootblock (drives the.slidewidth)@page { size: 10in 7.5in; }(drives the PDF page size, CSS variables aren't permitted inside@page, so it must be edited directly)
If you only change one, the on-screen preview and the rendered PDF will disagree and content will clip.
Slide types
The template ships with layouts for most pitch- and walkthrough-style decks. Use the right one for each slide rather than forcing everything through a generic content layout.
Cover and hero
.slide-title, Gradient title slide with centered headline, subtitle, presenter line. Use when no cover photo is available.
.slide-hero, Full-bleed photo background with right-aligned headline and subtitle, plus a red branded footer bar. Best for opening pitch decks. Set the background image on the .hero-bg child via inline style.
.slide-hero.slide-closing, Same hero with left-aligned headline for closing "Ready on [date]" slides. The subtitle sits tight to the headline on purpose, the close reads as one unit, not two floating lines.
Section dividers
.slide-section, Solid red background with a large outlined section number and title. Use for clean typographic chapter breaks.
.slide-section.with-photo, Photo background with a red section chip ("Section 8.1") and a large section title. Use when the deck mirrors a numbered document (RFP response, report) and reviewers need to cross-reference.
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 · 132 lines · 8 tokens per session scan A de0bc4b3f52c
slides is a command published in the GitHub repository jamditis/claude-skills-journalism (432 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 1,912 once invoked, about $0.0000 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 commands, from other repositories
export-latex
Export the current paper draft to production-ready LaTeX (.tex) and PDF using the arxiv-style template. Converts draft.md + references.bib + figures/ into a complete LaTeX project with resolved citations, tables, and figures. Compiles to PDF automatically.
review-paper
Simulate a double-blind peer review of the current paper. Generates 2 independent reviewer reports in the style of top IS/CS conferences (ICIS, ECIS, MISQ level). Each report includes Summary, Strengths, Weaknesses, Minor Comments, and Overall Recommendation. Output is saved as simulatedreviews.md and can be fed…
scooping-check
Scooping risk assessment — is someone else working on your research idea? Identifies competing groups, assesses pace of publication, evaluates whether the core insight is "in the air", and provides a watch list with search terms, key researchers, and venues to monitor.
audit-paper
Audit a paper's empirical claims against the linked code repository — catches MISMATCH, MISSING, and PARTIAL claims before submission.
brainstorm
Creative research brainstorming — generate ideas researchers within a single field would miss. Cross-field connections, assumption challenges, alternative framings, and wild cards. Produces bold, specific, surprising ideas rather than safe incremental ones.
draft-section
Write one specific section of a paper as complete paragraphs. Use when you already have context and just need one section drafted. Follows writing-engine templates.