deweight-intake-anchor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited deweight-intake-anchor (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
在任何扫描或改写前，先锁定不可变事实和文意。后续步骤只能改“怎么说”，不能改“说什么”和“为什么说”。
../../_shared/references/deweight-workflow-contract.md../../_shared/references/semantic-anchor-schema.md../../_shared/references/templates/semantic-anchor-template.md../../_shared/scripts/check_semantic_anchor.pyRecord all immutable tokens:
For each paragraph:
paragraph_id: P001
section:
status: normal | format-exempt
writing_function:
core_claim:
evidence_or_basis:
information_focus:
reader_takeaway:
context_dependency:
immutable_tokens:
claim_polarity:
evidence_strength:
format_exempt_reason:Pxxx ID.blocked: needs_source_check.format-exempt and explain why.Return structured Markdown tables or YAML-like blocks. Do not rewrite text in this skill.
Before handing off to scan or rewrite, the artifact should pass:
python3 ../../_shared/scripts/check_semantic_anchor.py <semantic-anchor.md>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.