linkedin-cringe

linkedin-cringe is a skill for Claude Code from matteobaccan/LinkedInCringe. It costs 157 tokens per session (5,393 once invoked), scanned A, original, MIT.

A generator for deliberately awkward LinkedIn posts, mainly in Italian but usable in other languages. LinkedIn is a professional social network, and the posts are designed to imitate exaggerated or embarrassing business writing.

In plain words
What is it for?
Use it to create posts from a real event or topic, choose a cringe level, set the tone, and select writing patterns from its catalogue.
Why use it?
It removes the need to manually reproduce a specific level and style of LinkedIn cringe. You can control how believable, parodic, or surreal the result is.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

Good fit Use it to create posts from a real event or topic, choose a cringe level, set the tone, and select writing patterns from its catalogue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matteobaccan/linkedincringe/linkedin-cringe
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 matteobaccan/LinkedInCringe --skill linkedin-cringe
Clone the repo
git clone --depth 1 https://github.com/matteobaccan/LinkedInCringe

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 linkedin-cringe

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe.svg)](https://agentmods.dev/skills/matteobaccan/linkedincringe/linkedin-cringe)
Your own site
<a href="https://agentmods.dev/skills/matteobaccan/linkedincringe/linkedin-cringe"><img src="https://agentmods.dev/badge/skills/matteobaccan/linkedincringe/linkedin-cringe.svg" alt="Measured on agentmods" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,393 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00157 $0.05393
Opus 5 $0.00078 $0.02697
Sonnet 5 $0.00031 $0.01079
Haiku 4.5 $0.00016 $0.00539

Measured 8d ago against content hash 47521db252b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

linkedin-cringe 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 8d 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.

.claude/skills/linkedin-cringe/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LinkedIn Cringe: generatore di post

Genera post LinkedIn in italiano che riproducono il cringe autentico di LinkedIn Italia.

Principio guida

Il cringe non è "scritto male". Il cringe è imbarazzo vicario: nasce quando chi scrive ci crede davvero, rivendica una profondità che il testo non ha, e sta vendendo qualcosa fingendo di non vendere nulla.

Regola non negoziabile: la voce non strizza mai l'occhio. Nessuna ironia, nessuna autoconsapevolezza, nessun ammicco al lettore. Appena il testo ammicca, smette di essere cringe e diventa barzelletta.

Leggi references/tassonomia.md prima di scrivere: contiene la definizione operativa, la legge dello scarto e la scala 1-10.

Flusso

1. Raccogli i parametri

Se l'utente ha già indicato tema, livello o moduli nella richiesta, non fare domande: usa quello che ha detto e riempi i buchi con i default (livello 7, credibile).

Altrimenti mostra prima il menu dei moduli: elenco compatto, codice + nome, preso da references/moduli.md, e poi chiedi i parametri con AskUserQuestion, quattro domande:

D1. Livello di cringe (header: "Livello")

  • 4 Lieve: passa inosservato, lascia solo un leggero fastidio
  • 7 Imbarazzante (consigliato): il punto dolce, chi legge fa una faccia
  • 9 Insostenibile: screenshottabile, il tipo di post che gira nelle chat
  • 10 Leggendario: tutti i tic insieme, oltre il limite del sopportabile

D2. Registro (header: "Registro")

  • Credibile (consigliato): deve poter passare per un post vero, pescato dal feed. Nessuna esagerazione che tradisca la finzione.
  • Parodico: esagerazione dichiarata, si capisce che è una presa in giro
  • Surreale deadpan: il mondo raccontato è impossibile e la voce non se ne accorge. Né credibile né parodico, nessuna battuta. Vive dal livello 7 in su, il punto dolce è il 9
  • AI-SLOP: il post non ha un autore, è stato generato e incollato senza rileggerlo. Ribalta la regola anti-AI di questa skill. Non viene mai scelto dalla skill: solo dall'utente, qui o per nome. Vive dal livello 5 in su, il punto dolce è l'8

Read the full file on GitHub · 348 lines

Files

What ships with it

8 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. 8d ago First seen · 348 lines · 157 tokens per session scan A 47521db252b5

Subscribe to this mod's changes

linkedin-cringe is a skill published in the GitHub repository matteobaccan/LinkedInCringe (19 stars, last pushed 14d ago), licensed MIT. It adds 157 tokens to every session and 5,393 once invoked, about $0.0008 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.