一键导入
file-structure-check
Use when auditing repository folder structure, required directories, missing paths, or misplaced files against a profile.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when auditing repository folder structure, required directories, missing paths, or misplaced files against a profile.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | file-structure-check |
| description | Use when auditing repository folder structure, required directories, missing paths, or misplaced files against a profile. |
| metadata | {"triggers":["audit repository folder structure","check required directories and paths","detect misplaced files in a repo","validate project layout against a profile","generate a structure audit report"],"side_effects":["read_only","write_files"]} |
This execution-focused skill definition keeps the behavior, invocation shape, and adapter-facing contract unchanged while moving explanation-oriented content into supporting assets.
这个 pattern 的核心是把结构检查稳定组织为 audit → report → fix(optional):
report,包括缺失项、错位项、配置来源和建议修复动作fix 不是默认执行,而是基于报告结果,在后续单独、显式地进行人工修复或其他受控修复动作Input:
profilestrictnessProcess:
auditreportfix(optional)Output:
reportskill_assessment_output, trimmed to the structure-audit scenario这样组织的原因是,结构治理首先需要可靠审计,而不是直接改动。先做 audit,再看 report,最后才决定是否需要 fix,可以避免把启发式规则误当成自动改造命令。
先审计事实,再讨论修复。
Audit the current structure before discussing fixes.
规则应通过配置表达,而不是硬编码猜测。
Express structure rules through configuration instead of hard-coded guesses.
默认只做检查,不做修改。
Only audit by default and do not modify the repository.
报告要区分问题与建议修复。
Separate detected issues from suggested fixes in the report.
fix 必须显式触发。
Any fix action must be explicitly requested.
audit:解析审计输入。
读取目标根目录、默认规则、项目覆盖配置和显式参数;确认 --profile、--strictness、--config、--json、--dry-run 等输入,并确定本次使用的 profile、strictness 和规则来源。
audit:扫描并校验结构。
递归扫描仓库文件,跳过配置中列出的忽略目录;检查 required directories、optional directories、required paths,并按 source / config / test / doc 分类识别错位文件。此阶段只检查结构,不创建目录、不移动文件。
report:生成结构化结果。
输出缺失目录、缺失必需路径、错位文件、建议修复项以及本次使用的配置路径;如启用 --json,则输出机器可读结构;否则输出可读文本报告。这里的 suggested fixes 属于建议,不等于已经执行 fix。需要 assessment 口径时,引用 shared assessment output protocol,并按结构审计场景裁剪字段,不强制所有字段满配。
fix:决定是否进入后续修复。
只有在用户或项目流程显式要求时,才基于报告进入后续修复动作,例如人工调整目录、补充 required path,或更新项目本地配置。默认不在本 skill 内自动执行修复。
输出审计回顾。
在结果中说明本次使用的目录、profile、strictness、配置来源、主要结构问题,以及哪些内容只是建议修复而非实际改动。
--json 输出方式Adapter entry for bootstrapping agent rules, contracts, validation, task packages, reports, and handoff boundaries for financial data engineering or operations projects. Canonical source is in skills/financial-data-agent-bootstrap.
Use when bootstrapping agent rules, contracts, validation, task packages, reports, and handoff boundaries for financial data engineering or operations projects.
Use when evaluating, scoring, diagnosing, or explicitly refactoring a single skill under controlled governance.
Use when onboarding a new maintainer or AI agent, scanning an unfamiliar repository, or generating a takeover packet.
Use when preparing a handoff task package, bounded execution, or execution report across AI agents.
Use when assessing migration readiness for a financial-data Python project with script sprawl, Excel assets, or Wind/Desktop coupling.