Real Skill packageSource verifiedClawHub registry

Report Number Audit(数鉴-报告审计)

数鉴-报告审计技能。做报告时就用:算数即记账,交付前对账。两条路产同一本账本——①有指标定义(ledger.yaml + indicators.yaml)→ rla_ledger 生成账本,模板里写 [[id]] 渲染,数字天生带出处、数据变了拒绝渲染;②有脚本跑数 → rla_report 录像自动记账。审计时把报告数字逐个追溯回账本,追不到即拦;覆盖率不足不许判定通过。适用三时机:出报告(算数记账)、改报告(改完拿现有账本重核,防只改一份漏其余)、查问题(数字对不上、客户质疑出处)。触发词:出数据报告、做报告、改报告、更新数据、数据补录、口径调整、重新生成报告、交付前检查、数字对不上、可追溯、审计报告。项目里已有 ledger.yaml / indicators.yaml 时,改动报告前后都应复核。产出四件套:audit.md 结论、audit.html 审计凭证、evidence.csv 证据清单、manifest.json 机检回执。不适用:改的是纯文字(不含数字)、或报告里没有需要追溯的指标。

Identity and source

Publisher attributionwopy112-gaoregistry owner unverified by skillvetai
Functional categoryData, Spreadsheets & Analyticsautomatically inferred · 53% rule confidence
Package forminstruction with code31 recorded files
Canonical sourceClawHub registryclawhub:wopy112-gao:leafather-report-audit
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 11/16/2026.claude/skills/leafather-report-audit

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 11/16/2026.agents/skills/leafather-report-audit

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 11/16/2026skills/leafather-report-audit

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @wopy112-gao/leafather-report-audit
clawhub inspect @wopy112-gao/leafather-report-audit --version 3.6.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
31 / 31 inspected as text
Checked
11/16/2026, 6:35:05 AM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
7 dependency and API indicators
  • pypi: duckdb >=1.1.0
  • pypi: pyyaml >=6.0
  • pypi: python-docx >=1.1.0 # docx 审计
  • pypi: python-pptx >=0.6.23 # pptx 审计
  • pypi: openpyxl >=3.1.0 # xlsx 审计
  • pypi: beautifulsoup4 >=4.12 # html 审计
  • api: clawhub.ai
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
11/16/2026, 4:27:03 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:905996216452ad2b7752ec130a7f3f66eb07c7486e944f1de2c98a1e56b20e31
Show up to 30 recorded paths
  • examples/build_report.mjs
  • examples/cross-file-build.py
  • examples/cross-file-demo.md
  • examples/metrics.yaml
  • LICENSE
  • policy.yaml
  • README.en.md
  • references/usage-notes.md
  • requirements-optional.txt
  • requirements.txt
  • scripts/cmd_sqlite.py
  • scripts/deps_check.py
  • scripts/metrics.py
  • scripts/policy.py
  • scripts/rla_audit.py
  • scripts/rla_collect.py
  • scripts/rla_derive.py
  • scripts/rla_extract.py
  • scripts/rla_health.py
  • scripts/rla_ledger.py
  • scripts/rla_note.py
  • scripts/rla_render.py
  • scripts/rla_replay.py
  • scripts/rla_report.py
  • scripts/rla_selftest.py
  • scripts/rla_track_node.cjs
  • scripts/rla_track.py
  • scripts/rla_xlsx.py
  • skill-card.md
  • SKILL.md

Source changelog

v3.6.0 replaces report-ledger entirely: (1) rla_ledger builds the ledger from metric definitions — four value modes (sql / col / expr / num-den), {{pool}}/{{cap}} substitution, invariants, ratio, confidence, data fingerprint; (2) rla_render renders [[id]] placeholders and refuses to render when the data snapshot changed; (3) rla_note lets pandas / pure-Python numbers enter the same ledger with one line; (4) rla_health reports, right after your build script runs, which numbers will have no provenance; (5) gates grew from 5 to 7 (stale ledger = FAIL, unrendered placeholders = FAIL, unused metrics = REVIEW); (6) verified end-to-end on a real 832 MB business dataset: 100% coverage, 8/8 recomputed; (7) fixed recompute not handling ratio metrics that return num/den columns.