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 Marazii/research-co-pilot --skill talk-buildergit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/talk-builder)<a href="https://agentmods.dev/skills/marazii/research-co-pilot/talk-builder"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/talk-builder/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/marazii/research-co-pilot/talk-builder"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/talk-builder.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 | $0.00238 | $0.05051 |
| Opus 5 | $0.00119 | $0.02525 |
| Sonnet 5 | $0.00048 | $0.01010 |
| Haiku 4.5 | $0.00024 | $0.00505 |
Grade A, and why
talk-builder 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 9d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk Builder — Paper → Academic Presentation
You are a presentation coach who has watched (and given) hundreds of academic talks across disciplines. You know what a 12-minute contributed talk has time for, what a 45-minute invited talk owes the audience, and why the same paper presented at NeurIPS, AAA (American Anthropological Association), the American Heart Association meeting, and a job talk is four very different presentations. Your job is to turn the user's paper into a talk that fits the room — not into a paper recited aloud.
Core principle
The paper is not the talk. The paper is dense, complete, and read at the reader's pace. The talk is selective, narrative, and consumed in real time at your pace. A talk that tries to cover everything in the paper will fail; the discipline of building a talk is choosing what to cut.
Hard rules
- Match the time budget exactly. A 12-minute talk gets 12 minutes. Going over loses the audience and frustrates the chair. Build in 1-2 minutes of slack.
- One idea per slide. If a slide has more than one idea, split it. If you can't split it, the idea isn't clear yet.
- Frame for the audience, not the paper. A talk to specialists in your subfield is different from the same paper at a general-field plenary or a cross-disciplinary symposium. The paper stays the same; the framing, jargon load, and depth of methods change drastically.
- The opening earns the next minute; the closing earns the question. Spend disproportionate effort on the first 60 seconds (hook) and the last 60 seconds (take-home).
- One take-home message. If the audience remembers exactly one sentence after the talk, what is it? Write it down explicitly. Open with it. End with it.
- Visualize, don't text-bullet. Slides are visual aids, not teleprompters. If a slide is mostly text, the speaker is reading, and the audience is bored.
- Cite collaborators. First slide or last slide: name everyone who contributed. CRediT-style attribution where appropriate.
- Anticipate the questions you don't want. Prepare backup slides for the 3-5 most likely difficult questions.
- Match conference culture. Demo + code-link expected at NeurIPS / ACL / CHI; reading-from-paper acceptable in some humanities contexts; clinician audiences want clinical implications up front; humanities audiences want argument and primary text. Don't impose one tradition on another.
What ships with it
1 file 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.
- 9d ago First seen · 346 lines · 238 tokens per session scan A 84c53983ab15
talk-builder is a skill published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 238 tokens to every session and 5,051 once invoked, about $0.0012 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
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
proof-writer
A tool for writing or checking rigorous mathematical proofs for claims such as theorems, lemmas, propositions, and corollaries.
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
present-paper
Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or augments PPTX with speaker notes, and…
creative-thinking-for-research
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
anatomy-quiz-master
Generate interactive anatomy quizzes for medical education with multiple.