File Format Conversion
pipeshub-ai/pipeshub-ai
Picks the right library for converting between CSV, XLSX, JSON, images, DOCX and PDF text, and lists the conversions that are not supported so the agent does not attempt them.
Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy.
Install Heavy File Ingestion
$ npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NateBJones-Projects/OB1 heavy-file-ingestion --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/heavy-file-ingestion .claude/skills/heavy-file-ingestion && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "heavy-file-ingestion" agent skill from https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestion into .claude/skills/heavy-file-ingestion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "heavy-file-ingestion", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NateBJones-Projects/OB1 heavy-file-ingestion --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/heavy-file-ingestion .agents/skills/heavy-file-ingestion && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "heavy-file-ingestion" agent skill from https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestion into .agents/skills/heavy-file-ingestion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "heavy-file-ingestion", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NateBJones-Projects/OB1 heavy-file-ingestion --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/heavy-file-ingestion .cursor/skills/heavy-file-ingestion && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "heavy-file-ingestion" agent skill from https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestion into .cursor/skills/heavy-file-ingestion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "heavy-file-ingestion", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NateBJones-Projects/OB1.git --path skills/heavy-file-ingestion--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NateBJones-Projects/OB1 heavy-file-ingestion --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/heavy-file-ingestion .gemini/skills/heavy-file-ingestion && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "heavy-file-ingestion" agent skill from https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestion into .gemini/skills/heavy-file-ingestion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "heavy-file-ingestion", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NateBJones-Projects/OB1 heavy-file-ingestionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/heavy-file-ingestion .github/skills/heavy-file-ingestion && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "heavy-file-ingestion" agent skill from https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestion into .github/skills/heavy-file-ingestion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "heavy-file-ingestion", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NateBJones-Projects/OB1 heavy-file-ingestion --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/heavy-file-ingestion .opencode/skills/heavy-file-ingestion && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "heavy-file-ingestion" agent skill from https://github.com/NateBJones-Projects/OB1/tree/main/skills/heavy-file-ingestion into .opencode/skills/heavy-file-ingestion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "heavy-file-ingestion", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
heavy-file-ingestion- GitHub stars
- 4.7k
- Token cost
- ~995 tokens
- SKILL.md length
- 479 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy.
- Works in 4 steps: Convert before reading. Do not dump raw… → Index before reasoning. Read the… → Match the converter to the file type. → …
- Asked to read or summarize a large PDF, slide deck or spreadsheet
- SKILL.md covers Problem, Trigger Conditions, Core Policy and Process, plus 2 more sections
- Runs Python scripts from its folder; calls python and uv
What it does
Instead of reading a heavyweight file raw, the agent first runs a converter script and reads the generated index.md (or index.json), which says what the file contains, how clean the extraction was and whether escalation is justified. PDFs and documents become a markdown artifact, presentations a markdown slide outline, and spreadsheets one CSV per sheet plus a markdown manifest. Only the outputs the index calls worth reading are opened afterwards.
Escalation follows cost tiers: a deterministic converter with an index first, a cheap model on the extracted artifact only when quality flags show structure was lost, and an expensive model only once the file has been compressed or sampled. The scripts are convert_heavy_file.py and build_client_exports.py, run through uv with libraries such as pdfplumber and python-docx, and the converter can be told to prefer markitdown for PDF and DOCX when it is installed. A reference file covers the open-source stack.
When your agent uses it
- Asked to read or summarize a large PDF, slide deck or spreadsheet
- Keeping token use down when a file is bulky or structured
- Getting a markdown working copy or CSV extraction plus a quick map of a file
Example prompts
- “Read ./reports/annual-report.pdf and summarize the main findings.”
- “Look through ./data/orders.xlsx and tell me which sheets matter.”
- “Summarize the deck in ./pitch/funding-round.pptx without loading the whole file into context.”
Requirements
- Python with uv to run the converter scripts
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Convert before reading. Do not dump raw heavyweight files into model context if a deterministic converter can create a cheaper artifact.
- Index before reasoning. Read the generated index.md or index.json first. It should tell you what is in the file, how clean the extraction…
- Match the converter to the file type.
- Escalate by cost tier, not instinct.
What it can do on your machine
Read from SKILL.md and the folder at commit 238df6c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonuv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Heavy File Ingestion loads about 995 tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 479 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 479 words (~995 tokens).
“Agents waste money and context when they read heavyweight files raw. This skill turns bulky documents into cheaper working artifacts first, then tells the main agent how much reasoning power the file actually deserves.”
- name
- heavy-file-ingestion
- author
- Nate B. Jones
- version
- 1.0.0
Files
SKILL.md and 6 other files (scripts, references) in skills/heavy-file-ingestion of NateBJones-Projects/OB1.
- SKILL.md
- README.md
- metadata.json
- references/open-source-stack.md
- scripts/build_client_exports.py
- scripts/convert_heavy_file.py
- variants
Open the folder on GitHubat commit 238df6c
Compare with similar skills
Heavy File Ingestion next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Heavy File Ingestion this skillNateBJones-Projects/OB1 | 4.7k | — | ~995 | Automated safety check: Pass | Custom licence | |
| File Format Conversionpipeshub-ai/pipeshub-ai | 3.8k | — | ~865 | Automated safety check: Pass | Apache-2.0 | |
| Office ArtifactsPrismer-AI/PrismerCloud | 1.6k | — | ~2.6k | Automated safety check: Pass | MIT | |
| Document Converterwentorai/Research-Claw | 858 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| MinerU Document Readeropendatalab/MinerU | 81k | — | ~9.4k | Automated safety check: Warn | Custom licence |
Similar skills
Office Artifacts
Prismer-AI/PrismerCloud
Generate real DOCX, PPTX, XLSX, PDF, CSV files using python-docx / python-pptx / openpyxl / reportlab by writing them into the dispatch artifacts dir, then explicitly deliver each one with cloud…
Document Converter
wentorai/Research-Claw
Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown.
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
MinerU Document Reader
opendatalab/MinerU
Reads, OCRs, searches and cites local documents through the mineru CLI, covering PDF, images, Office files, EPUB, HTML and CSV.
Huashu Markdown Publishing Pipeline
alchaincyf/huashu-md-html
Converts files and web pages into clean Markdown, then turns Markdown into polished HTML, Word, PDF and EPUB using four templates.
More from NateBJones-Projects/OB1
All 24 skills in this repoAiception Skill Extraction
NateBJones-Projects/OB1
Pulls reusable knowledge out of work sessions and turns it into new skills, checking existing notes and skills first to avoid duplicates.
Claude Code Auto-Capture Hook
NateBJones-Projects/OB1
Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up.
Open Brain Local HTTP
NateBJones-Projects/OB1
Captures and searches personal notes in a self-hosted Open Brain using plain curl calls over HTTP, for setups where MCP is disabled or blocked.
Panning for Gold
NateBJones-Projects/OB1
Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis.
Agentic Harness Design and Review
NateBJones-Projects/OB1
Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.
Weekly Signal Diff
NateBJones-Projects/OB1
Turns a noisy week of AI or software market news into a short list of structural changes, weighted by what the user already tracks in Open Brain memory.
Related
Works with
Categories
Questions about Heavy File Ingestion
What does Heavy File Ingestion do?
Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy. json), which says what the file contains, how clean the extraction was and whether escalation is justified. PDFs and documents become a markdown artifact, presentations a markdown slide outline, and spreadsheets one CSV per sheet plus a markdown manifest.
When should I use Heavy File Ingestion?
Heavy File Ingestion fits situations like: asked to read or summarize a large PDF, slide deck or spreadsheet; keeping token use down when a file is bulky or structured; getting a markdown working copy or CSV extraction plus a quick map of a file.
How do I install Heavy File Ingestion in Claude Code?
Run `npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a claude-code`. Or copy the skill folder (skills/heavy-file-ingestion in NateBJones-Projects/OB1) into .claude/skills/heavy-file-ingestion in your project. Claude Code loads it when a task matches its description.
How do I install Heavy File Ingestion in Codex?
Run `npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a codex`. Or copy the skill folder (skills/heavy-file-ingestion in NateBJones-Projects/OB1) into .agents/skills/heavy-file-ingestion in your project. Codex loads it when a task matches its description.
Can I use Heavy File Ingestion in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NateBJones-Projects/OB1 --skill heavy-file-ingestion -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/heavy-file-ingestion, .gemini/skills/heavy-file-ingestion, .github/skills/heavy-file-ingestion and .opencode/skills/heavy-file-ingestion in your project.
What does Heavy File Ingestion need to run?
Going by SKILL.md and its folder, Heavy File Ingestion needs Python for the scripts in its folder and the command-line tools its instructions call (python and uv). Our summary lists: Python with uv to run the converter scripts.
Does Heavy File Ingestion access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Heavy File Ingestion safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Heavy File Ingestion use?
Heavy File Ingestion has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Heavy File Ingestion use?
About 995 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 723 tokens, read only when the agent opens those files.
What are the alternatives to Heavy File Ingestion?
Skills that share tags, products or a category with Heavy File Ingestion: File Format Conversion (pipeshub-ai/pipeshub-ai, 3.8k stars), Office Artifacts (Prismer-AI/PrismerCloud, 1.6k stars), Document Converter (wentorai/Research-Claw, 858 stars) and Markitdown (ImCa0/just-laws, 781 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Heavy File Ingestion?
NateBJones-Projects (a GitHub organization) maintains it in NateBJones-Projects/OB1, which has 4,710 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.
Source: NateBJones-Projects/OB1 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.