Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill cli-anything명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | cli-anything |
| description | Build and validate CLI apps. |
Use this skill when the user wants Codex to act like the CLI-Anything builder.
If this skill is being used from inside the CLI-Anything repository, read ../cli-anything-plugin/HARNESS.md before implementation. That file is the full methodology source of truth. If it is not available, follow the condensed rules below.
Accept either:
./gimp or /path/to/softwareDerive the software name from the local directory name after cloning if needed.
Use when the user wants a new harness.
Produce this structure:
<software>/
└── agent-harness/
├── <SOFTWARE>.md
├── setup.py
└── cli_anything/
└── <software>/
├── README.md
├── __init__.py
├── __main__.py
├── <software>_cli.py
├── core/
├── utils/
└── tests/
Implement a stateful Click CLI with:
--json machine-readable outputUse when the harness already exists.
First inventory current commands and tests, then do gap analysis against the target software. Prefer:
Do not remove existing commands unless the user explicitly asks for a breaking change.
For Word/docx targets, prioritize:
When the target is a Word editor or .docx workflow, the harness should usually expose these areas first:
| Area | What to cover | Red flag |
|---|---|---|
| Structure | paragraphs, runs, tables, sections, headers, footers | only plain-text read/write |
| Formatting | fonts, bold/italic, spacing, alignment, indentation, styles | formatting lost after round-trip |
| Layout | margins, page size, pagination, section breaks, line/page breaks | layout changes silently |
| Numbering | bullets, numbered lists, captions, headings | numbering resets or desyncs |
| Equations | inline math, display equations, equation insertion/update | equations become images or text blobs |
| References | footnotes, endnotes, captions, cross-references, TOC hooks | references cannot be preserved |
| Validation | schema checks, render/preview, diff after save | no round-trip verification |
Prefer wrappers that operate on document structure rather than string replacement. If the backend supports styles, tables, equations, or section-aware editing, those should be modeled as first-class commands instead of hidden behind a generic edit action.
For Word/docx harnesses, write tests that prove:
Plan tests before writing them. Keep both:
test_core.py for unit coveragetest_full_e2e.py for workflow and backend validationWhen possible, test the installed command via subprocess using cli-anything-<software> rather than only module imports.
Check that the harness:
cli_anything.<software> namespace package layoutsetup.py entry pointPrefer the real software backend over reimplementation. Wrap the actual executable or scripting interface in utils/<software>_backend.py when possible. Use synthetic reimplementation only when the project explicitly requires it or no viable native backend exists.
For Word/docx specifically, prefer a backend that preserves structure and layout. Avoid naive text replacement when the target supports styles, tables, equations, or section-aware editing.
find_namespace_packages(include=["cli_anything.*"])cli_anything/ as a namespace package without a top-level __init__.pycli-anything-<software> through console_scriptsTEST.md, then tests, then run them.pip install -e .When reporting progress or final results, include:
For Word/docx harnesses, call out equation coverage and layout fidelity explicitly.