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 ShaishavMaisuria/research-paper-lifecycle-skills --skill write-talk-scriptgit clone --depth 1 https://github.com/ShaishavMaisuria/research-paper-lifecycle-skillsWrote 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/shaishavmaisuria/research-paper-lifecycle-skills/write-talk-script)<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-talk-script"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-talk-script/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/shaishavmaisuria/research-paper-lifecycle-skills/write-talk-script"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-talk-script.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 | $0.00211 | $0.01762 |
| Opus 5 | $0.00105 | $0.00881 |
| Sonnet 5 | $0.00042 | $0.00352 |
| Haiku 4.5 | $0.00021 | $0.00176 |
Grade B, and why
write-talk-script scanned grade B with 1 finding 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 10d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Timing is an estimate, not a guarantee: never tell the user the talk How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Talk Script
Produce a speaker script that fits an exact talk slot: every slide gets a
word budget at the speaker's real pace, a cumulative timing mark, a
written-out transition, and a marked cut list so running long on stage has a
pre-planned answer. Slides tell the audience what to look at; this script is
what the speaker actually says. It is the post-acceptance companion to
make-slides.
When to use
- "Write the script for my 12-minute SIGSPATIAL talk" / "15-minute slot including 3 minutes of Q&A — what do I say?"
- "Turn my deck into speaker notes I can rehearse from"
- "My talk is running long — what do I cut?"
- "I have a 5-minute lightning talk / spotlight"
- After
make-slides, before the first timed rehearsal.
Inputs
- The exact slot: total minutes, and whether Q&A is inside the slot or handled separately. Ground truth is the presenter instructions and the acceptance email, not memory and not venue profiles.
- The deck or an outline (slide titles in order). No deck yet? Run
make-slidesfirst. - The paper (camera-ready preferred) — the only legitimate source for every number and claim spoken.
- Optional:
venues/conferences/<venue>-<year>.ymlfor venue context, and the speaker's measured pace in words per minute.
Process
-
Pin down the slot facts. Ask for: total minutes, Q&A inside or outside, session language, and whether the chair uses timecards. If a venue profile exists, use it for context only and re-verify against the live
cfp_url/ venue website — profiles do not encode talk slots, and slots change year to year. Typical shapes (verify, never assume): full papers 12–20 min including Q&A; CHI historically ~10 min + 5 Q&A; lightning/spotlight 1–7 min. Details in references/timing-and-cuts.md. -
Calibrate the pace. Default to 130 wpm — a deliberate conference pace. If the speaker can do the 1-minute read-aloud calibration (timing-and-cuts.md §2), use their measured number; suggest 110–120 wpm for non-native speakers or dense technical material. Never exceed 150.
What ships with it
4 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.
- 10d ago First seen · 135 lines · 211 tokens per session scan B 1fbce6ccea2c
write-talk-script is a skill published in the GitHub repository ShaishavMaisuria/research-paper-lifecycle-skills (41 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 211 tokens to every session and 1,762 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
aaai-reproducibility
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that Phase-1 reviewers use to judge rigor across…
aaai-submission
Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.
aaai-topic-selection
Use when deciding whether a project is a strong AAAI submission across its broad AI scope, should be reframed or routed to a dedicated track such as AI for Social Impact or AI Alignment, or should instead go to IJCAI, NeurIPS, ICML, ICLR, AISTATS, UAI, ACL, CVPR, KDD, CHI, ICRA, or another specialist venue.
acl-author-response
Use when drafting an ACL author response inside an ACL Rolling Review cycle on OpenReview, covering the response window before meta-review, reviewer discussion dynamics, score-change strategy, flagging review issues to the area chair, anonymity rules, and deciding between responding now versus revising for a later ARR…
acl-camera-ready
Use when preparing an accepted ACL main-conference or Findings paper for camera-ready, covering the extra content page, de-anonymization and acknowledgements, AI-assistance disclosure, keeping the Limitations section, ACL Anthology metadata and CC BY 4.0 publication, meta-review-driven edits, and presentation-mode…
acl-experiments
Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…