File contents Internal Audit Report(内审报告)
你负责把内审工作底稿与证据材料整理成正式内审报告。涉及证据汇总、表格对齐、引用索引、长文输出时通过 OpenCode 执行。
触发条件
用户要生成/改写内审报告
用户上传稽核底稿、访谈纪要、系统日志、抽样清单等材料
约定
bridge:http://opencode-bridge:8000
鉴权:Authorization: Bearer $OPENCODE_BRIDGE_TOKEN
{user}:私聊 open_id;群共享用 chat_id
输出落盘:
output/audit_report.md(必选)
output/audit_report.docx(常见需要)
output/findings.csv(可选:发现清单)
阶段一:确认报告要素
必须确认:
审计对象与范围(系统/流程/组织/期间)
审计标准与依据(制度、法规、内控要求)
报告读者(管理层/合规/业务负责人)
输出格式(md/docx)
阶段二:上传证据与底稿
要求用户上传所有证据材料,并逐个写入 input/:
curl -sS -F "file=@/path/to/file" "http://opencode-bridge:8000/file/{user}" \
-H "Authorization: Bearer $OPENCODE_BRIDGE_TOKEN"
阶段三:委托 OpenCode(指令模板)
指令必须包含:
报告结构(建议):
执行摘要(结论、重大风险、总体评价)
范围与方法(抽样、访谈、系统核查等)
发现与影响(每条发现要有证据、风险、根因、建议)
整改建议与优先级(含责任人/截止日期)
管理层回复(如有)
发现清单输出:
output/findings.csv:字段建议(编号、主题、等级、证据来源、影响、建议、负责人、截止日期)
证据索引:
output/notes.md:每条发现对应 input/... 的证据路径与页码/段落说明(能定位就定位)
提交:
curl -sS -X POST "http://opencode-bridge:8000/task/{user}" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENCODE_BRIDGE_TOKEN" \
-d '{"message":"<内审报告结构化指令,引用 input/...>"}'
阶段四:回传与复核
先回传:重大发现 Top N + 需要管理层决策项
再回传:audit_report.md/docx/findings.csv
复核修改:按“发现编号”逐条修改,避免泛泛改动
1 --- 2 name: internal-audit-report 3 description: Internal Audit Report 4 --- 5 6 # Internal Audit Report(内审报告) 7 8 你负责把内审工作底稿与证据材料整理成正式内审报告。涉及证据汇总、表格对齐、引用索引、长文输出时通过 OpenCode 执行。 9 10 ## 触发条件 11 12 - 用户要生成/改写内审报告 13 - 用户上传稽核底稿、访谈纪要、系统日志、抽样清单等材料 14 15 ## 约定 16 17 - bridge:`http://opencode-bridge:8000` 18 - 鉴权:`Authorization: Bearer $OPENCODE_BRIDGE_TOKEN` 19 - `{user}`:私聊 `open_id`;群共享用 `chat_id` 20 - 输出落盘: 21 - `output/audit_report.md`(必选) 22 - `output/audit_report.docx`(常见需要) 23 - `output/findings.csv`(可选:发现清单) 24 25 ## 阶段一:确认报告要素 26 27 必须确认: 28 29 - 审计对象与范围(系统/流程/组织/期间) 30 - 审计标准与依据(制度、法规、内控要求) 31 - 报告读者(管理层/合规/业务负责人) 32 - 输出格式(md/docx) 33 34 ## 阶段二:上传证据与底稿 35 36 要求用户上传所有证据材料,并逐个写入 `input/`: 37 38 ```bash 39 curl -sS -F "file=@/path/to/file" "http://opencode-bridge:8000/file/{user}" \ 40 -H "Authorization: Bearer $OPENCODE_BRIDGE_TOKEN" 41 ``` 42 43 ## 阶段三:委托 OpenCode(指令模板) 44 45 指令必须包含: 46 47 - 报告结构(建议): 48 1. 执行摘要(结论、重大风险、总体评价) 49 2. 范围与方法(抽样、访谈、系统核查等) 50 3. 发现与影响(每条发现要有证据、风险、根因、建议) 51 4. 整改建议与优先级(含责任人/截止日期) 52 5. 管理层回复(如有) 53 - 发现清单输出: 54 - `output/findings.csv`:字段建议(编号、主题、等级、证据来源、影响、建议、负责人、截止日期) 55 - 证据索引: 56 - `output/notes.md`:每条发现对应 `input/...` 的证据路径与页码/段落说明(能定位就定位) 57 58 提交: 59 60 ```bash 61 curl -sS -X POST "http://opencode-bridge:8000/task/{user}" \ 62 -H "Content-Type: application/json" \ 63 -H "Authorization: Bearer $OPENCODE_BRIDGE_TOKEN" \ 64 -d '{"message":"<内审报告结构化指令,引用 input/...>"}' 65 ``` 66 67 ## 阶段四:回传与复核 68 69 - 先回传:重大发现 Top N + 需要管理层决策项 70 - 再回传:`audit_report.md`/`docx`/`findings.csv` 71 - 复核修改:按“发现编号”逐条修改,避免泛泛改动
gonglingrui/openwriting-skills/tree/main/internal-audit-report commit 22d5649686
Frequently asked questions How do I install the Internal Audit Report skill? Run npx skillmds@latest add gonglingrui/internal-audit-report in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Internal Audit Report skill do? Internal Audit Report It is listed under Security on SkillMD.
Is Internal Audit Report safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Internal Audit Report? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Internal Audit Report free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Internal Audit Report? GongLingRui (@gonglingrui) published this skill. Their other Agent Skills are listed on their SkillMD profile.