agentmods.dev

write-abstract

write-abstract is a skill for Claude Code from ShaishavMaisuria/research-paper-lifecycle-skills. It costs 185 tokens per session (2,046 once invoked), scanned A, original, Apache-2.0.

A writing tool for creating or revising research-paper abstracts for specific conferences or publication formats. It can also prepare the title, abstract, authors, topics, and conflict-of-interest details needed for abstract registration.

In plain words
What is it for?
Drafting abstracts, meeting word limits, adding the required keywords or classification section, and preparing registration information before submission.
Why use it?
It helps fit an abstract to a venue's format and length requirements while keeping claims tied to verified results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the paper-writing plugin — 7 skills shipped together

not rated 55repo 3d ago A scan 185 tokens original Apache-2.0

Good fit Drafting abstracts, meeting word limits, adding the required keywords or classification section, and preparing registration information before submission.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract
View source ↗ ShaishavMaisuria/research-paper-lifecycle-skills shaishavmaisuria.github.io
Install

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.

Any agent
npx skills add ShaishavMaisuria/research-paper-lifecycle-skills --skill write-abstract
Clone the repo
git clone --depth 1 https://github.com/ShaishavMaisuria/research-paper-lifecycle-skills

Made for: Claude Code.

Or install paper-writing, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

agentmods badge for write-abstract

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract/github.svg)](https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract)
Your own site
<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract/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.

agentmods 80×15 button for write-abstract

Your own site · 80×15
<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/write-abstract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00185 $0.02046
Opus 5.5 $0.00074 $0.00818
Sonnet 5.5 $0.00037 $0.00409
Haiku 4.5 $0.00018 $0.00205

Measured 1mo ago against content hash 421d8d6d9f98, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-abstract 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/abstract_check.py, scripts/abstract_registration.py, scripts/keywords_block.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/write-abstract/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Abstract

Produce a venue-compliant abstract — right length, right keywords block, five-move structure, verified numbers only — and, when the venue has a separate abstract-registration deadline, the complete registration card (title, abstract, authors, topics, COI list) ready to paste into the submission form.

When to use

  • Drafting or rewriting an abstract for a specific venue or template family (acmart / IEEEtran / llncs / NeurIPS-style).
  • Fitting an abstract to a word limit, or adding the missing CCS Concepts / Index Terms / keywords block.
  • An abstract-registration deadline is approaching and the user must register title + abstract + topics + conflicts before the paper PDF.

Related skills: tailor-to-venue (whole-paper retargeting), parse-cfp (build a missing venue profile), preflight-check (final desk-reject lint), verify-citations (gate for any reference work).

Inputs

  • The draft (main .tex preferred — keyword blocks are checked in context) or the abstract as plain text; or, for a fresh draft, the paper's contributions and verified results from the user.
  • Venue profile: venues/conferences/<id>.yml or venues/families/<f>.yml (schema: venues/schema.yml). If neither exists, do NOT invent venue facts — run parse-cfp on the CFP URL or quote the live CFP directly.

Process

1. Resolve venue norms, then re-verify (mandatory)

Load the profile (format.abstract_words, format.keywords, deadlines.abstract/paper + timezone, review.blind). Profiles go stale: before the user relies on a word limit, keyword requirement, or any deadline, re-verify it against the live cfp_url and say what was checked and when. If the CFP cannot be fetched, label every profile-derived fact "UNVERIFIED — confirm on CFP". When abstract_words is null, present 150-250 words as a convention, never as a venue rule — see references/venue-norms.md.

2. Draft (or diagnose) with the five-move structure

Read the full file on GitHub · 169 lines

Files

What ships with it

7 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.

Changes

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.

  1. 1mo ago First seen · 169 lines · 185 tokens per session scan A 421d8d6d9f98

Subscribe to this mod's changes

write-abstract is a skill published in the GitHub repository ShaishavMaisuria/research-paper-lifecycle-skills (55 stars, last pushed 3d ago), licensed Apache-2.0. It adds 185 tokens to every session and 2,046 once invoked, about $0.0007 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.

LaTeXResearchWriting and docsacademic-writingagent-skillsai-agentscitation-verificationliterature-review
Related

Other skills, from other repositories

research-manager

Use this when starting a new research project or managing a complex, multi-step research workflow.

poemswe/co-researcher · 21 tokens

academic-writing

You must use this when producing any research prose — literature reviews, syntheses, analyses, methodology descriptions, discussion sections, abstracts, or any written output intended for an academic audience.

poemswe/co-researcher · 39 tokens

systematic-review

You must use this when conducting PRISMA-standard systematic reviews, protocol development, or Risk of Bias assessment.

poemswe/co-researcher · 26 tokens

hypothesis-testing

You must use this when formulating testable hypotheses, designing experimental controls, or defining falsification criteria.

poemswe/co-researcher · 25 tokens

multi-source-investigation

You must use this when investigating complex claims across diverse sources or fact-checking contradictory information.

poemswe/co-researcher · 23 tokens

peer-review

You must use this when critiquing academic manuscripts, evaluating methodological rigor, or providing structured reviewer feedback.

poemswe/co-researcher · 24 tokens