How do I install the Onefilellm skill?

Run npx skillmds@latest add onfire7777/onefilellm 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.

Is Onefilellm 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 Onefilellm?

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 Onefilellm free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Onefilellm?

onfire7777 (@onfire7777) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Onefilellm by onfire7777 — Agent Skill

Name: Onefilellm
Author: onfire7777

Onefilellm

Use when aggregating local files, directories, GitHub repositories/issues/PRs, documentation pages, PDFs, arXiv/DOI/PMID sources, YouTube transcripts, stdin, or clipboard text into a single LLM-ready XML context file using the locally installed jimmc414/onefilellm CLI. Use for context packaging, source bundling, repo-to-text conversion, and multi-source research ingestion.

onfire7777 d8d702d 8 files · 40.3 KB Updated Sep 17, 2026

File contents

OneFileLLM

Use this skill to collect multiple sources into one XML-style context payload for LLM analysis.

Source

Upstream repository: https://github.com/jimmc414/onefilellm
Integrated source commit: 99c51a2cbe8cc01c0db037a9f800ca31fae9c2cd
Local checkout: %USERPROFILE%\.onefilellm\onefilellm
Isolated venv CLI: %USERPROFILE%\.onefilellm\venv\Scripts\onefilellm.exe
Windows shim: %USERPROFILE%\.onefilellm\bin\onefilellm.cmd

README-Grounded Usage

The upstream README defines OneFileLLM as a command-line tool and Python API for aggregating local files, GitHub repos, web pages, PDFs, YouTube transcripts, arXiv/DOI/PMID sources, stdin, and clipboard content into a single structured XML output.

Run:

python scripts/run_onefilellm.py ./docs README.md
python scripts/run_onefilellm.py https://github.com/user/project
python scripts/run_onefilellm.py https://docs.python.org/3/tutorial/
python scripts/run_onefilellm.py --help-topic examples

Equivalent direct commands:

& "$env:USERPROFILE\.onefilellm\venv\Scripts\onefilellm.exe" --help
& "$env:USERPROFILE\.onefilellm\bin\onefilellm.cmd" --help-topic crawling

References

references/source-readme.md contains the full upstream README.
references/architecture.md contains upstream architecture notes.
references/requirements.txt and references/requirements-lock.txt document installed dependencies.
references/source-metadata.json records the integrated commit and local paths.

Safety And Quality Rules

Prefer local files/directories when possible.
Treat network sources as active fetches. Only run against trusted URLs or explicit user-provided URLs.
Do not pass secrets, private tokens, or sensitive local directories unless the user explicitly asks and the scope is clear.
Use GITHUB_TOKEN only when private GitHub access or higher rate limits are required.
Use OFFLINE_MODE=1 for local-only dry runs or when network fetches should be blocked.
For YouTube-only transcript work, prefer the youtube-transcript-english skill because it enforces English output more strictly than OneFileLLM's built-in transcript fallback.

---name: onefilellmdescription: Use when aggregating local files, directories, GitHub repositories/issues/PRs, documentation pages, PDFs, arXiv/DOI/PMID sources, YouTube transcripts, stdin, or clipboard text into a single LLM-ready XML context file using the locally installed jimmc414/onefilellm CLI. Use for context packaging, source bundling, repo-to-text conversion, and multi-source research ingestion.license: MIT---# OneFileLLMUse this skill to collect multiple sources into one XML-style context payload for LLM analysis.## Source- Upstream repository: `https://github.com/jimmc414/onefilellm`- Integrated source commit: `99c51a2cbe8cc01c0db037a9f800ca31fae9c2cd`- Local checkout: `%USERPROFILE%\.onefilellm\onefilellm`- Isolated venv CLI: `%USERPROFILE%\.onefilellm\venv\Scripts\onefilellm.exe`- Windows shim: `%USERPROFILE%\.onefilellm\bin\onefilellm.cmd`## README-Grounded UsageThe upstream README defines OneFileLLM as a command-line tool and Python API for aggregating local files, GitHub repos, web pages, PDFs, YouTube transcripts, arXiv/DOI/PMID sources, stdin, and clipboard content into a single structured XML output.Run:```bashpython scripts/run_onefilellm.py ./docs README.mdpython scripts/run_onefilellm.py https://github.com/user/projectpython scripts/run_onefilellm.py https://docs.python.org/3/tutorial/python scripts/run_onefilellm.py --help-topic examples```Equivalent direct commands:```powershell& "$env:USERPROFILE\.onefilellm\venv\Scripts\onefilellm.exe" --help& "$env:USERPROFILE\.onefilellm\bin\onefilellm.cmd" --help-topic crawling```## References- `references/source-readme.md` contains the full upstream README.- `references/architecture.md` contains upstream architecture notes.- `references/requirements.txt` and `references/requirements-lock.txt` document installed dependencies.- `references/source-metadata.json` records the integrated commit and local paths.## Safety And Quality Rules- Prefer local files/directories when possible.- Treat network sources as active fetches. Only run against trusted URLs or explicit user-provided URLs.- Do not pass secrets, private tokens, or sensitive local directories unless the user explicitly asks and the scope is clear.- Use `GITHUB_TOKEN` only when private GitHub access or higher rate limits are required.- Use `OFFLINE_MODE=1` for local-only dry runs or when network fetches should be blocked.- For YouTube-only transcript work, prefer the `youtube-transcript-english` skill because it enforces English output more strictly than OneFileLLM's built-in transcript fallback.

Frequently asked questions