Daocui sensitive decision
Skill poofang1986/skilltrust-audit/examples/daocui-sensitive-decision
Demonstrate a privacy-minimized, evidence-separated Agent Skill for a synthetic high-impact decision-support workflow. Use only as a review fixture and architecture example; it does not provide real advice or collect real personal data.From its SKILL.md
npx -y skills add poofang1986/skilltrust-audit --skill daocui-sensitive-decisionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.1 KB, 147 tokens by cl100k_base, as published. Nobody here has run it
DaoCui Sensitive Decision Example
Use synthetic case IDs only. Do not collect names, addresses, credentials, medical records, financial account details, recordings, or third-party private information.
Keep these layers separate:
- user-provided synthetic fact,
- deterministic tool output,
- model interpretation,
- independent validation,
- reversible action and stop rule.
Never store an inference as a confirmed fact. Do not write outside the current workspace. Do not access the network, environment variables, browser sessions, or unrelated files.
For any high-impact conclusion, state missing facts and require qualified professional review. This fixture demonstrates how the original DaoCui privacy and evidence boundaries informed SkillTrust's generic trust model.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.