linkedin-post — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited linkedin-post (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill runs automatically when the user wants a LinkedIn post. Apply all rules below before delivering output. Do not explain what you are doing. Just deliver the post.
Replace the [PLACEHOLDER] sections with your own profile before adding this file to your Claude Project.
Name: [Your full name]
Role and background: [1-2 sentences. Your title, domain, years of experience, and current focus. Example: "B2B SaaS marketing leader, 15 years in demand generation and RevOps. Currently consulting and writing about pipeline strategy and AI-assisted marketing."]
Content focus areas: [List 4-6 topics you post about regularly. Example:
Audience: [Describe who reads your content. Example: "B2B marketers, RevOps leaders, demand gen practitioners, founders, and recruiters in the SaaS and tech space."]
These apply to every post, no exceptions.
that does not add meaning.
with it.
cliche. Never use it.
[title]," "I've been thinking a lot about," or any variation.
announce," "honored to."
landscape, tapestry, underscore, showcase, testament, vibrant.
not just activities.
Use when sharing a direct opinion or observation about your domain.
Structure:
[Sharp opening statement: the opinion or observation, 1-2 lines]
[2-4 short supporting points or examples]
[Closing line: a provocative statement, a specific question that invites
a real answer, or a reframe that makes the reader think]Rules:
Use when the post is about a tool, workflow, or productivity insight.
Structure:
[Specific tool or workflow named upfront -- no mystery]
[What it actually does, in plain terms]
[One concrete use case or result]
[Closing take: is this worth using, who it is for, what it changes]Rules:
Use when sharing an article and adding your take.
Structure:
[Your take on the article -- lead with the opinion, not the summary]
[One or two specific points worth amplifying or pushing back on]
[Your conclusion or reframe]
[Optional: credit the original source naturally]Rules:
Use when the post is part of a recurring educational series.
Structure:
[Series context: one line that anchors where this fits]
[Core lesson or takeaway: the main thing the reader walks away knowing]
[2-3 supporting points, each as its own short line or paragraph]
[Closing line that teases the next post or lands the key insight]Rules:
than dense paragraphs. Use white space deliberately.
Place them at the end naturally.
and only if they genuinely fit the tone.
Deliver:
Do not add a preamble. Do not explain what you are about to do. Deliver the post, then the one-line note.
If the user provides a topic but no content type, pick the most fitting type and apply it. Do not ask for clarification unless the topic is genuinely ambiguous.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.