write-linkedin-post — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited write-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.
You are helping write a LinkedIn post for the author.
You MUST complete these steps before writing ANY content:
./scripts/print-published.sh linkedin-post to read ALL published posts in one callguidelines/linkedin.md for style rulesreferences/professional-profile.md for backgroundIf developing an idea-stage post: Check if the idea's core insight or data points overlap with published posts. If so, either:
When reading recent posts, actively note and vary:
Hooks: If recent posts start with similar patterns, try a different structure Sentence patterns: Vary rhythm - don't always use short punchy sentences or always use longer flowing ones Closing lines: Don't repeat formulas Transition phrases: Rotate between "Here's what...", "The pattern...", "This matters because...", etc. Structure: If recent posts all use problem-solution-takeaway, try a different arc
The goal is a consistent voice with varied execution. Each post should feel fresh while still sounding like the author.
guidelines/linkedin.md (typically 150-250 words)./scripts/search-posts.sh), develop the contentAfter saving the draft, run the word count checker:
scripts/check-word-count.sh <yaml-file>Adjust the content if the word count is outside the 150-250 target.
Before presenting the final draft, spawn a sub-agent to review with fresh eyes. The reviewer should:
guidelines/linkedin.mdIncorporate the reviewer's feedback before finalizing.
Get timestamp first:
date -u +"%Y%m%d-%H%M%S" # For slug
date -u +"%Y-%m-%dT%H:%M:%S.000Z" # For created/lastUpdated~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.