Install
$ agentstack add skill-styfinity-linkedin-engine-linkedin-post-writer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
LinkedIn Post Writer
The hero skill. Turns a topic and a shred of proof into a post that earns attention and proves the competence the buyer is buying. Drafts only, never posts.
Inputs
- The topic or angle, plus any proof you have (a number, a before/after, a build): $ARGUMENTS
- The brief (persona, voice profile, offer, pains) loads automatically.
Do this
- Pick the best-fit hook formula from THE TEN, given the topic and proof:
Pattern-Break, Counter-Intuitive Insight, Experience-Led Observation, Direct Consequence, Confession+Result, Numbered Promise, Enemy-Hero-Gasoline-Teaser, BREAKING/News framing, Stat-Anchored (X% vs Y%), Mechanism-Reveal.
- Write the hook so the first 210 to 235 characters (everything visible before "see more") carry all four value levers at once: dream outcome up, perceived likelihood up, time-delay down, effort down.
- Body gives a SYSTEM, not tips: name the parts and show the arrows between them. Include one copy-paste-able artefact line (a prompt, a check, a template line). Quantify one before/after in money and hours. Land one contrarian quotable line.
- Close with a comment-keyword CTA plus a connect line (e.g. "comment WORD and I'll send it").
- Total length 900 to 1,300 characters. Count it.
Output
- The post, ready to read top to bottom.
- The hook formula used (one of THE TEN).
- The visible-before-cut preview (first 210 to 235 chars, exactly what shows before "see more").
- The character count.
- A suggested comment keyword.
- A note: run /linkedin-humanizer next before posting.
Rules
- Sell the operator, not the artefact: the topic must PROVE the competence the buyer is buying, even when it is not literally the product.
- Outcome + mechanism: name the outcome and reveal the mechanism. AI does the volume, operator judgment picks the targets. Position the operator as a Revenue Partner who uses AI to do the heavy lifting.
- Proof attributes to "a post", "a client", or "an operator", never to a named person or company.
- No em-dashes. No banned hype words.
- Draft only. Pass the draft through /linkedin-humanizer before posting. Nothing auto-posts; the operator approves and publishes.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: styfinity
- Source: styfinity/linkedin-engine
- License: MIT
- Homepage: https://styfinity.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.