finance-automation-portfolio: Skill for Claude Code

.claude/skills/linkedin-post/SKILL.md

linkedin-post is a skill for Claude Code from sophonfinance-wq/finance-automation-portfolio. It costs 38 tokens per session (478 once invoked), scanned A, original, MIT.

A writing guide for drafting LinkedIn posts in the founder's voice for Sophon Finance Systems, a finance and accounting company. It sets rules for tone, claims, links, hashtags, calls to action, and accompanying graphics.

In plain words
What is it for?
It is for writing announcements and other LinkedIn copy about finance, accounting, automation, and company work, including the required website and email details when appropriate.
Why use it?
It keeps posts consistent with the founder's voice and prevents unsupported claims, generic AI-style wording, and formatting that conflicts with the stated publishing approach.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sophonfinance-wq/finance-automation-portfolio's own configuration. It tells Claude Code how to work on finance-automation-portfolio 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 finance-automation-portfolio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sophonfinance-wq/finance-automation-portfolio. 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/sophonfinance-wq/finance-automation-portfolio/main/.claude/skills/linkedin-post/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sophonfinance-wq/finance-automation-portfolio

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-post

README.md
[![agentmods](https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/linkedin-post/github.svg)](https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/linkedin-post)
Your own site
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/linkedin-post"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/linkedin-post/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 linkedin-post

Your own site · 80×15
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/linkedin-post"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/linkedin-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 478 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 $0.00038 $0.00478
Opus 5 $0.00019 $0.00239
Sonnet 5 $0.00008 $0.00096
Haiku 4.5 $0.00004 $0.00048

Measured 11d ago against content hash 2fb072eae519, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

linkedin-post 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.

.claude/skills/linkedin-post/SKILL.md · 20 lines

What it actually says

LinkedIn Posts — Founder Voice

Voice rules (non-negotiable, learned by iteration)

  • Hard opener: a blunt claim or contrarian line, then credentials for credit: "18 years closing the books for Fortune 100 and 500 companies." Name: Sophonnarith Hang, senior accounting & tax, GAAP/FAR/CAS.
  • Kill the AI smell: no em-dashes, no emoji-bulleted feature lists, no "it didn't remove X, it moved X" chiasmus slogans, no rule-of-three punchlines, no title-case headers. Short, uneven sentences. Contractions.
  • Max 3 hashtags, lowercase: #finance #accounting #ai.
  • Links: site (sophonfinance.com) + email ([email protected]) in body; GitHub link works better as the FIRST COMMENT (body links get reach-throttled) — but follow the user's explicit ask if they want it in-body.
  • End with a soft CTA: "If your close still eats a week, message me. I'll show you what I'd automate first, free."
  • Always pair with a house-style graphic (see the brand-graphics skill). Deliver copy in a code block for easy copy-paste.
  • Claims must be true to the repo: cite real test counts, real demo output, "fictional data, run it yourself".

Cadence content on file

references/post-series.md (in this skill's folder) holds the ready-to-paste series: launch + one post per engine. Already published: the self-healing launch post (with the tie-out diagram) and "One loop architecture. Five gate policies." (with the gate-policy table).

Posts 2-6 predate these voice rules (em-dashes, Title-Case hashtags) — rewrite them into the voice above before delivering. Posts 7-15 (engines 39-47) are already in this voice and lint clean — deliver them as-is; each carries its GitHub first comment beside it. Continue numbering from 16.

Files

What ships with it

1 file 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 · 20 lines · 38 tokens per session scan A 2fb072eae519

Subscribe to this mod's changes

linkedin-post is a skill published in the GitHub repository sophonfinance-wq/finance-automation-portfolio (11 stars, last pushed 15d ago), licensed MIT. It adds 38 tokens to every session and 478 once invoked, about $0.0002 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.