deweight-verify-gate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited deweight-verify-gate (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.
证明改写不是“换了一种 AI 味”。验收必须同时检查 AI 残留、事实完整性和文意锚定。
../../_shared/references/residual-verification-gates.md../../_shared/references/semantic-anchor-schema.md../../_shared/references/pattern-coverage-matrix-schema.md../../_shared/references/templates/residual-report-template.md../../_shared/scripts/check_residual_report.pyFor every rewritten paragraph:
paragraph_id:
original_hit_modes:
remaining_hit_modes:
new_hit_modes:
max_remaining_severity:
max_new_severity:
semantic_anchor_match: pass | fail
immutable_token_match: pass | fail
claim_polarity_match: pass | fail
evidence_strength_match: pass | fail
verdict: pass | revise | blocked
reason:
next_action:blocked.blocked.revise.revise.blocked.For multi-round rewriting, compare previous and current matrices:
Return a concise verification table. Do not do fresh rewriting in this skill.
Before claiming pass, the report should pass:
python3 ../../_shared/scripts/check_residual_report.py <residual-report.md>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.