rongxinzy/rongxinai/audit-support

Claude Code and agent skill by rongxinzy/rongxinai

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Prepare audit-ready request trackers, evidence indexes, walkthroughs, control test workpapers, sample support, and issue responses. Use for internal or external audit support and SOX-style control testing.

Install

npx vskill@latest install rongxinzy/rongxinai/audit-support

SKILL.md

Audit Support

This skill organizes evidence and testing; it does not issue an audit opinion.

PBC and evidence management

For each request record request ID, description, period, population, owner, due date, status, evidence file, source system, extraction parameters, reviewer, and auditor follow-up. Preserve original files and use versioned working copies.

Evidence must be relevant, reliable, complete, period-correct, and traceable to the request. Do not create missing evidence or alter timestamps. Redact or restrict personal and confidential data according to policy.

Walkthrough and control testing

Document process objective, initiation, systems, roles, key risks, control owner, frequency, evidence, exceptions, and handoffs. For each control distinguish:

  • design: whether the control could prevent or detect the stated risk;
  • implementation: whether it exists and is in use;
  • operating effectiveness: whether it operated consistently during the test period.

Define the population and verify completeness before selecting samples. Record sampling method and rationale; do not claim statistical assurance for judgmental samples.

Workpaper format

Include objective, scope, risk, control, population, sample, procedure, evidence, result, exception, impact, management response, remediation owner/date, preparer, reviewer, and conclusion. Cross-reference every conclusion to evidence.

Escalate missing evidence, contradictory support, repeat exceptions, management override, access conflicts, suspected fraud, or scope limitations. Use neutral language and separate observed fact from interpretation.

Security

  • Security scanPassed, 96 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/rongxinzy/rongxinai/audit-support/badge)](https://verified-skill.com/skills/rongxinzy/rongxinai/audit-support)

Something wrong with this skill or its page? Tell us.