write-opinion — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited write-opinion (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 an opinion piece for the author.
./scripts/print-published.sh opinion to read all published opinions in one callguidelines/opinion.md for style rules (includes language and publication targets)references/professional-profile.md for backgroundWhen reading recent pieces, actively note and vary:
Openings: If recent pieces start with scene-setting in a specific location, try a different concrete opening (an action, a quote, a surprising fact) Sentence rhythm: Vary between punchy short sentences and longer flowing ones Closing formulas: Don't repeat the same forward-looking structure - find fresh ways to land the argument Examples: Rotate between local and international examples; between industry, government, and everyday life Rhetorical devices: If recent pieces use lists or parallel structure heavily, try a different approach
The goal is a consistent voice with varied execution. Each piece should feel fresh while still sounding like the author.
wc -m to verify)guidelines/opinion.mdwc -mAfter saving the draft, run the character count checker:
scripts/check-char-count.sh <yaml-file>Adjust the content if the character count is outside the 3000-4000 range.
Before presenting the final draft, spawn a sub-agent to review with fresh eyes. The reviewer should:
guidelines/opinion.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.