abbrevia

abbrevia is a skill for Claude Code from iamursky/sokrati. It costs 276 tokens per session (6,004 once invoked), scanned A, original, MIT.

An Italian-language writing guide for improving professional text using plain, reader-focused wording.

In plain words
What is it for?
Use it to revise, correct, shorten, or clarify Italian professional writing, including emails, landing pages, and similar text.
Why use it?
It helps remove unnecessary words, unclear phrasing, and formal language that can make emails or other work documents harder to understand.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it to revise, correct, shorten, or clarify Italian professional writing, including emails, landing pages, and similar text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iamursky/sokrati/abbrevia
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 iamursky/sokrati --skill abbrevia
Clone the repo
git clone --depth 1 https://github.com/iamursky/sokrati

Made for: Claude Code.

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 abbrevia

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamursky/sokrati/abbrevia/github.svg)](https://agentmods.dev/skills/iamursky/sokrati/abbrevia)
Your own site
<a href="https://agentmods.dev/skills/iamursky/sokrati/abbrevia"><img src="https://agentmods.dev/badge/skills/iamursky/sokrati/abbrevia/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 abbrevia

Your own site · 80×15
<a href="https://agentmods.dev/skills/iamursky/sokrati/abbrevia"><img src="https://agentmods.dev/badge/skills/iamursky/sokrati/abbrevia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 276 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,004 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 $0.00276 $0.06004
Opus 5 $0.00138 $0.03002
Sonnet 5 $0.00055 $0.01201
Haiku 4.5 $0.00028 $0.00600

Measured 11d ago against content hash 4f322ada8620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

abbrevia 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 11d 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.

skills/abbrevia/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sei un redattore professionista formato allo stile informativo. Questo skill si ispira alle idee del libro «Пиши, сокращай 2025» («Scrivi, abbrevia 2025») di Maksim Iljachov e Ljudmila Sarycheva — un classico russo sulla scrittura professionale che si adatta sorprendentemente bene alla tradizione italiana della lingua piana, da Italo Calvino contro l'«antilingua» fino al lavoro di Tullio De Mauro e Michele Cortelazzo sulla semplificazione del linguaggio amministrativo.

Principi fondamentali

Un testo forte ha quattro qualità:

  1. Utilità — il testo promette e mantiene ciò che serve al lettore
  2. Chiarezza — il senso arriva subito, senza bisogno di decifrare
  3. Coerenza — le idee seguono un ordine logico; ogni paragrafo parla di una sola cosa
  4. Sobrietà — niente zavorra linguistica; ogni parola si guadagna il suo posto

I bisogni del lettore vengono prima. Il testo serve il lettore, non l'ego di chi scrive.


Procedura di lavoro

Quando l'utente ti consegna un testo da rivedere, attraversa i livelli in ordine. Non ogni livello è pertinente a ogni testo — salta ciò che non serve.

Livello 0: capire il contesto

Prima di intervenire, stabilisci:

  • Chi è il lettore? (cliente, datore di lavoro, collega, cittadino, pubblico generico)
  • Che tipo di testo è? (email, landing page, relazione, curriculum, comunicato stampa, pagina «Chi siamo», ecc.)
  • Qual è l'azione utile? Perché il lettore lo leggerà di sua spontanea volontà?

Se l'utente non ha precisato — chiedi. Se il contesto è ovvio — procedi.

Livello 1: pulizia a livello di parola

Controlla cinque categorie di parole-spia:

1. Riempitivi e intercalari

  • Tagliare: «ovviamente», «evidentemente», «come tutti sanno», «è risaputo che», «francamente», «sinceramente», «a dire il vero», «tra parentesi», «secondo me» (a meno che non si contrapponga a un'altra opinione), «diciamo», «tipo» (nei testi professionali), «in pratica» (quando non è esatto), «praticamente» (quando non è preciso), «letteralmente» (quando non è letterale), «fondamentalmente», «in effetti» (quando è ridondante)
  • Sostituire l'elencazione verbale («in primo luogo, in secondo luogo») con un elenco puntato o spezzando in paragrafi
  • Parentesi con contenuto irrilevante — eliminare; con contenuto importante — sciogliere in una frase a sé

Read the full file on GitHub · 327 lines

Files

What ships with it

2 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. 11d ago First seen · 327 lines · 276 tokens per session scan A 4f322ada8620

Subscribe to this mod's changes

abbrevia is a skill published in the GitHub repository iamursky/sokrati (17 stars, last pushed 1mo ago), licensed MIT. It adds 276 tokens to every session and 6,004 once invoked, about $0.0014 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.

Related

Other skills, from other repositories

baoyu-translate

A translation workflow for converting articles and other text into another language. It offers quick, standard, and publication-focused approaches with different levels of review.

JimLiu/baoyu-skills · 121 tokens

hreflang-international

International / multilingual SEO audit focused on hreflang correctness. Detects and diagnoses the most common (and ranking-damaging) hreflang mistakes: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, conflicts between hreflang and canonical, and inconsistent…

nowork-studio/notfair-plugin · 242 tokens

i18n-parity

MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored READMEs, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change…

hoangsonww/Claude-Code-Agent-Monitor · 138 tokens

extract-source-sample

Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…

gooseworks-ai/goose-skills · 160 tokens

internationalization

Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled…

rampstackco/claude-skills · 123 tokens

i18n-helper

A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.

laolaoshiren/claude-code-skills-zh · 33 tokens