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 mr-devs/cc-academic-website --skill create-talkgit clone --depth 1 https://github.com/mr-devs/cc-academic-websiteWrote 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/mr-devs/cc-academic-website/create-talk)<a href="https://agentmods.dev/skills/mr-devs/cc-academic-website/create-talk"><img src="https://agentmods.dev/badge/skills/mr-devs/cc-academic-website/create-talk/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/mr-devs/cc-academic-website/create-talk"><img src="https://agentmods.dev/badge/skills/mr-devs/cc-academic-website/create-talk.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 | $0.00083 | $0.01073 |
| Opus 5.5 | $0.00033 | $0.00429 |
| Sonnet 5.5 | $0.00017 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
create-talk 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Talk
Build a new talk deck by copying talks/templates/ and filling it with real content. If that template doesn't exist yet, build it with the user first (step 0). The template is a viewable reveal.js deck whose slide formats are the design system — the job is composition (which format carries which idea), not visual design.
Input
$ARGUMENTS
Workflow
0. Check that the template exists
Everything below assumes talks/templates/ is present. Check first:
ls talks/templates/index.html
If it's missing, the template has to be built before any talk can be scaffolded. Say so, then follow references/bootstrap-template.md to develop it with the user — it inherits the site's palette and typography, and the format catalog is theirs to choose. Build and verify the template first, then come back to step 1 for the talk they actually asked for.
1. Gather inputs
Collect before outlining (use AskUserQuestion for anything important that's missing — these decisions shape the whole deck):
- Venue, date, and talk title — needed for the title slide and directory name.
- Talk length and audience — drives the slide budget (~1 slide or build-up step per minute) and how much background to include.
- Source material paths — LaTeX source, paper PDF, figure directories, an abstract, or a prior deck to adapt. Read what's provided; see references/content-mapping.md for how to mine each input type.
- Directory name —
talks/YYYY_shortname/(year of the talk + a short lowercase tag, e.g.2026_sicss), matching any decks already undertalks/.
2. Outline first — get approval before writing any HTML
Propose a slide-by-slide outline: for each slide, the format name (from the catalog) and one line of content. Group build-up sequences explicitly ("Figure build-up ×3: baseline → add condition → highlight result"). Getting the outline right is where the user can cheaply redirect; rewriting finished HTML is expensive. Show the outline and wait for approval, adjusting until it fits the time budget and the story the user wants to tell.
What ships with it
3 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 · 64 lines · 83 tokens per session scan A fc63efd77bf1
create-talk is a skill published in the GitHub repository mr-devs/cc-academic-website (7 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,073 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.