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 gpsaggese/helpers --skill slides.convert_to_typstgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/slides.convert_to_typst)<a href="https://agentmods.dev/skills/gpsaggese/helpers/slides.convert_to_typst"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.convert_to_typst/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/gpsaggese/helpers/slides.convert_to_typst"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.convert_to_typst.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 | $0.00011 | $0.00833 |
| Opus 5.5 | $0.00004 | $0.00333 |
| Sonnet 5.5 | $0.00002 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
slides.convert_to_typst 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Convert a markdown slides file to Typst presentation format
- Preserve structure, content, and formatting
- Output clean, well-formatted markdown code suitable for conversion to Typst
Workflow
Read Input File
- Read the markdown slides file (e.g.,
lectures.md)
Apply Conversion Rules
- Systematically fix math, unicode, and formatting
Validate Output
- Verify no content loss and structure preserved
Output File
- Write converted markdown with same base name
- Say in the output file how it was generated, with this comment right after the
metadata-comment block:
// Generated by `.claude/skills/slides.convert_to_typst/SKILL.md`
Quality Checks
- All slide headers and hierarchy preserved
- No content deleted or truncated
- All math expressions wrapped (
$...$) - No unicode math characters remain
- Operators properly formatted with
op() - Code blocks and lists intact
- File is valid markdown
Conventions
LaTeX Custom Commands
- Replace presentation-specific commands with Typst equivalents:
$\EE$->$bb(E)$(blackboard E)$\VV$->$bb(V)$(blackboard V)$\Pr$->$Pr$(remove backslash)
Variables and Math Expressions
- Wrap all variables, parameters, and math expressions in
$...$:- Bad (unwrapped, renders as plain text):
Randomly permute the values of x_j across all samples - Good (wrapped in math mode):
Randomly permute the values of $x_j$ across all samples
- Bad (unwrapped, renders as plain text):
Unicode to LaTeX
- Replace unicode math characters with LaTeX:
Ω->$\Omega$→->$\to$≤->$\leq$×->$\times$
Subscripts and Superscripts
- Use math mode for all subscripts/superscripts:
- Bad (unicode subscript or bare caret, invalid Typst math): P₀ or P^n
- Good (math mode syntax):
$P_0$or$P^n$
Math Operators
- Use
op()for named operators in Typst:- Bad (named operator unwrapped, Typst renders it as variables):
$g^* = arg min_(g in G)$ - Good (wrapped with
op()):$g^* = op("arg min")_(g in G)$ - Also:
$max_i x_i$->$op("max")_i x_i$
- Bad (named operator unwrapped, Typst renders it as variables):
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.
- yesterday First seen · 97 lines · 11 tokens per session scan A 234e91073ec3
slides.convert_to_typst is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 833 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 2026-11-06.
slides.convert_to_typst compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| slides.convert_to_typstgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 11 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | today | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 68 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 17 | Claude Code, Codex |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 54 | Claude Code, Codex |