notch-so-good: Skill for Claude Code

.agents/skills/linkedin-content/SKILL.md

linkedin-content is a skill for Claude Code from deepshal99/notch-so-good. It costs 93 tokens per session (2,236 once invoked), scanned A, original, MIT.

A writing guide for creating LinkedIn posts, the short professional updates shared on LinkedIn. It covers post structure, formatting, length limits, and common engagement patterns.

In plain words
What is it for?
Use it for professional updates, thought-leadership posts, business-to-business content, or personal branding. It also includes guidance for adapting a post for X.
Why use it?
It helps turn an idea into a readable post with a clear opening, useful main section, and closing request. It also helps keep posts within LinkedIn's publishing constraints.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is deepshal99/notch-so-good's own configuration. It tells Claude Code how to work on notch-so-good itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything notch-so-good configures →

Reuse

Borrowing it

Nothing to install: this file belongs to deepshal99/notch-so-good. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/deepshal99/notch-so-good/main/.agents/skills/linkedin-content/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/deepshal99/notch-so-good

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-content

README.md
[![agentmods](https://agentmods.dev/badge/skills/deepshal99/notch-so-good/linkedin-content.svg)](https://agentmods.dev/skills/deepshal99/notch-so-good/linkedin-content)
Your own site
<a href="https://agentmods.dev/skills/deepshal99/notch-so-good/linkedin-content"><img src="https://agentmods.dev/badge/skills/deepshal99/notch-so-good/linkedin-content.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,236 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 $0.00093 $0.02236
Opus 5 $0.00046 $0.01118
Sonnet 5 $0.00019 $0.00447
Haiku 4.5 $0.00009 $0.00224

Measured 7d ago against content hash ad68a44e8d24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

linkedin-content 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 7d 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.

.agents/skills/linkedin-content/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LinkedIn Content

Write high-engagement LinkedIn posts via inference.sh CLI.

Quick Start

Requires inference.sh CLI (infsh). Get installation instructions: npx skills add inference-sh/skills@agent-tools

infsh login

# Research trending LinkedIn content patterns
infsh app run tavily/search-assistant --input '{
  "query": "LinkedIn viral post examples 2024 high engagement patterns"
}'

# Post to X (cross-posting reference)
infsh app run x/post-create --input '{
  "text": "Your cross-posted version here"
}'

Post Anatomy

┌─────────────────────────────────────┐
│ HOOK (first 1-2 lines)             │ ← Visible before "...see more"
│                                     │
│ ...see more ─────────────────────── │ ← The click gate
│                                     │
│ BODY (story/value)                  │
│ - Formatted with line breaks        │
│ - Short paragraphs (1-2 sentences)  │
│ - Lists or numbered points          │
│                                     │
│ CTA (last 1-2 lines)              │ ← Ask for engagement
│                                     │
│ #hashtags (3-5)                     │
└─────────────────────────────────────┘

Character Limits

Element Limit
Post text 3,000 characters
Visible before "see more" ~210 characters (~2 lines on mobile)
Hashtags 3-5 recommended
Comment 1,250 characters
Article title 100 characters
Article body 125,000 characters

The first 210 characters are everything. If the hook fails, nobody clicks "see more."

Hook Formulas

What Works

Formula Example
Contrarian opinion "Unpopular opinion: code reviews are a waste of time."
Personal story opening "I got fired on a Tuesday. Best thing that ever happened."
Surprising stat "92% of startups fail. But not for the reason you think."
List promise "I've hired 200+ engineers. Here are 5 red flags I look for."
Bold statement "Your resume doesn't matter. Here's what does."
Before/after "3 years ago I couldn't get a single interview. Yesterday I turned down a FAANG offer."
Pattern interrupt "Stop. Before you send that cold email, read this."

Read the full file on GitHub · 234 lines

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. 7d ago First seen · 234 lines · 93 tokens per session scan A ad68a44e8d24

Subscribe to this mod's changes

linkedin-content is a skill published in the GitHub repository deepshal99/notch-so-good (7 stars, last pushed 25d ago), licensed MIT. It adds 93 tokens to every session and 2,236 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

lights-hooks

Install Lights traffic-light status hooks into Claude Code's settings.json. Lights is a macOS menu-bar app that shows AI activity as a floating traffic light (red=executing, yellow=needs input, green=idle). Use this skill when the user mentions Lights, asks how to connect Lights to Claude Code, says "set up lights…

fengyiqicoder/Lights · 93 tokens

claudexor

Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…

razzant/claudexor · 73 tokens

tokf-discover

Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.

mpecan/tokf · 24 tokens

cross-campaign

Discover and reference other camps, projects, and files across camp boundaries. Use when the user mentions another camp or campaign by name, references work done "in another project/camp", or needs to find/copy/compare code across camps.

Obedience-Corp/festival · 52 tokens

dashiai-ppt

A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.

huangrichao2020/pretty-skills · 62 tokens

xiaohongshu-image-creator

An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.

huangrichao2020/pretty-skills · 121 tokens