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.
npx skills add spinningrachel/career-engine --skill linkedin-post-writergit clone --depth 1 https://github.com/spinningrachel/career-engineWrote 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.
[](https://agentmods.dev/skills/spinningrachel/career-engine/linkedin-post-writer)<a href="https://agentmods.dev/skills/spinningrachel/career-engine/linkedin-post-writer"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/linkedin-post-writer/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.
<a href="https://agentmods.dev/skills/spinningrachel/career-engine/linkedin-post-writer"><img src="https://agentmods.dev/badge/skills/spinningrachel/career-engine/linkedin-post-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01380 |
| Opus 5 | $0.00014 | $0.00690 |
| Sonnet 5 | $0.00006 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
linkedin-post-writer 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Post Writer Skill
Format Selection
Choose the format based on the idea's content depth and evidence available.
| Format | Word range | Use when |
|---|---|---|
| A — Strategic framework | 800–950w | The idea has a repeatable model, multiple named proof points, or a framework the reader can immediately apply. Requires at least 2 distinct real examples. |
| B — Insight / analysis | 400–600w | A sharp observation backed by one or two real examples. The claim is specific; the evidence is real but limited. |
| C — Tactical deep-dive | 300–500w | A specific tool, technique, or step-by-step workflow. Concrete and actionable. Limited need for narrative or arc. |
When in doubt, choose B. Format A requires evidence depth — a weak Format A produces a padded post. Format C requires a genuinely tactical topic — a strategic observation forced into Format C produces an underdeveloped fragment.
Never exceed the ceiling. If a Format B idea keeps expanding past 600w, it either belongs in A (with proper evidence) or needs editing down.
Hook Writing
The hook is the first 1–3 lines — what appears before LinkedIn's "see more" cut. It is the only thing many readers will see.
Hook rules:
- The hook must earn the click. It must create a specific, credible reason to keep reading — not a generic teaser.
- The hook must not mislead about the content. If the post is about documentation strategy, the hook is about documentation strategy — not a vague "here's what I learned."
- One specific claim or observation in the hook. Not a question. Not a mystery. Not "you won't believe this."
Hook patterns that work:
- A counterintuitive specific claim: "Most API documentation fails at the same moment — when it describes what the call does, not what the user is trying to accomplish."
- A concrete observed gap: "I've reviewed 40+ technical writing samples this year. The most common problem isn't accuracy. It's that the writer knew the answer but never explained why the reader needed it."
- A named tension the reader recognises: "PMM and technical writing teams in deep tech companies are usually solving the same problem from opposite ends. They rarely talk."
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.
- 9d ago First seen · 91 lines · 28 tokens per session scan A 07f22496c9db
linkedin-post-writer is a skill published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 28d ago), licensed MIT. It adds 28 tokens to every session and 1,380 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…