Transformers
K-Dense-AI/scientific-agent-skills
Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks.
Inspect, filter, summarize, and transform sandbox files with shell tools.
Apache-2.0Auto-check passed
Install Shell Data Workbench
$ npx skills add bionic-gpt/bionic-gpt --skill shell-data-workbench -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bionic-gpt/bionic-gpt shell-data-workbench --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/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/builtin-skills/skills/shell-data-workbench .claude/skills/shell-data-workbench && 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 "shell-data-workbench" agent skill from https://github.com/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbench into .claude/skills/shell-data-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shell-data-workbench", 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/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbenchType 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 bionic-gpt/bionic-gpt --skill shell-data-workbench -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bionic-gpt/bionic-gpt shell-data-workbench --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .agents/skills && cp -r skills-src/crates/builtin-skills/skills/shell-data-workbench .agents/skills/shell-data-workbench && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "shell-data-workbench" agent skill from https://github.com/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbench into .agents/skills/shell-data-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shell-data-workbench", 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 bionic-gpt/bionic-gpt --skill shell-data-workbench -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bionic-gpt/bionic-gpt shell-data-workbench --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/crates/builtin-skills/skills/shell-data-workbench .cursor/skills/shell-data-workbench && 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 "shell-data-workbench" agent skill from https://github.com/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbench into .cursor/skills/shell-data-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shell-data-workbench", 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/bionic-gpt/bionic-gpt.git --path crates/builtin-skills/skills/shell-data-workbench--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 bionic-gpt/bionic-gpt --skill shell-data-workbench -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bionic-gpt/bionic-gpt shell-data-workbench --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/crates/builtin-skills/skills/shell-data-workbench .gemini/skills/shell-data-workbench && 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 "shell-data-workbench" agent skill from https://github.com/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbench into .gemini/skills/shell-data-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shell-data-workbench", 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 bionic-gpt/bionic-gpt shell-data-workbenchInstalls 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 bionic-gpt/bionic-gpt --skill shell-data-workbench -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .github/skills && cp -r skills-src/crates/builtin-skills/skills/shell-data-workbench .github/skills/shell-data-workbench && 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 "shell-data-workbench" agent skill from https://github.com/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbench into .github/skills/shell-data-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shell-data-workbench", 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 bionic-gpt/bionic-gpt --skill shell-data-workbench -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bionic-gpt/bionic-gpt shell-data-workbench --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/crates/builtin-skills/skills/shell-data-workbench .opencode/skills/shell-data-workbench && 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 "shell-data-workbench" agent skill from https://github.com/bionic-gpt/bionic-gpt/tree/main/crates/builtin-skills/skills/shell-data-workbench into .opencode/skills/shell-data-workbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shell-data-workbench", 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
shell-data-workbench- GitHub stars
- 2.4k
- Token cost
- ~131 tokens
- SKILL.md length
- 60 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Inspect, filter, summarize, and transform sandbox files with shell tools.
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Shell Data Workbench is an agent skill from bionic-gpt/bionic-gpt. Inspect, filter, summarize, and transform sandbox files with shell tools.
Its SKILL.md is about 130 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems. The licence is Apache-2.0.
Example prompts
- “/shell-data-workbench”
What it can do on your machine
Read from SKILL.md and the folder at commit c155c00. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Shell Data Workbench loads about 131 tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 60 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from bionic-gpt/bionic-gpt at commit c155c00, republished under its Apache-2.0 licence (© bionic-gpt). 60 words, ~131 tokens.
Download SKILL.mdSave it as
.claude/skills/shell-data-workbench/SKILL.md (or your agent's skills folder).- name
- shell-data-workbench
- description
- Inspect, filter, summarize, and transform sandbox files with shell tools.
Shell Data Workbench
Use this skill when the user asks to inspect, filter, summarize, or transform files inside the Bashkit sandbox.
Prefer normal shell tools such as find, rg, grep, awk, sed, sort, uniq, wc, jq, csv, yaml, and tomlq.
Work inside /home/user unless the task requires /tmp. Keep intermediate files small and explain the final result, not every command.
© bionic-gpt, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in crates/builtin-skills/skills/shell-data-workbench of bionic-gpt/bionic-gpt.
Open the folder on GitHubat commit c155c00
Compare with similar skills
Shell Data Workbench 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 |
|---|---|---|---|---|---|---|
| Shell Data Workbench this skillbionic-gpt/bionic-gpt | 2.4k | — | ~131 | Automated safety check: Pass | Apache-2.0 | |
| TransformersK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~2.8k | Automated safety check: Notes | Apache-2.0 | |
| Research Summarizeralirezarezvani/claude-skills | 28k | 2 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Agent Sandboxruvnet/ruflo | 74k | 3 repos | ~777 | Automated safety check: Pass | MIT | |
| Shell ScriptingRightNow-AI/openfang | 18k | — | ~827 | Automated safety check: Pass | Apache-2.0 | |
| Crush Shell Builtinscharmbracelet/crush | 29k | — | ~790 | Automated safety check: Pass | Custom licence |
Similar skills
Research Summarizer
alirezarezvani/claude-skills
Structured research summarization agent skill for non-dev users.
Agent Sandbox
ruvnet/ruflo
Agent skill for sandbox - invoke with $agent-sandbox. An agent skill from ruvnet/ruflo.
Shell Scripting
RightNow-AI/openfang
Shell scripting expert for Bash, POSIX compliance, error handling, and automation
Crush Shell Builtins
charmbracelet/crush
Explains how to add a new in-process builtin command to Crush's embedded POSIX shell, so it is intercepted before reaching the OS, with context polling and exit-status rules.
Filter
zalando/skipper
Create or modify code in the filters package and all its sub-folders
More from bionic-gpt/bionic-gpt
All 21 skills in this repoStatic Sites
bionic-gpt/bionic-gpt
Create or modify Bionic's generated marketing site, documentation, blog, course pages, and static assets.
Automationbench Eval
bionic-gpt/bionic-gpt
Load the repository's AutomationBench OpenAPI catalogue and run evaluations against the local simulator.
Ron Auth
bionic-gpt/bionic-gpt
Implement identity and authorization boundaries in Rust on Nails applications.
Ron Web Pages
bionic-gpt/bionic-gpt
Build server-rendered Dioxus pages using opinionated Rust on Nails patterns.
Document Generation
bionic-gpt/bionic-gpt
Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents.
Local Deployment
bionic-gpt/bionic-gpt
Deploy one or more locally built Bionic services into the user's k3d cluster.
Questions about Shell Data Workbench
What does Shell Data Workbench do?
Inspect, filter, summarize, and transform sandbox files with shell tools. Shell Data Workbench is an agent skill from bionic-gpt/bionic-gpt. Inspect, filter, summarize, and transform sandbox files with shell tools.
How do I install Shell Data Workbench in Claude Code?
Run `npx skills add bionic-gpt/bionic-gpt --skill shell-data-workbench -a claude-code`. Or copy the skill folder (crates/builtin-skills/skills/shell-data-workbench in bionic-gpt/bionic-gpt) into .claude/skills/shell-data-workbench in your project. Claude Code loads it when a task matches its description.
How do I install Shell Data Workbench in Codex?
Run `npx skills add bionic-gpt/bionic-gpt --skill shell-data-workbench -a codex`. Or copy the skill folder (crates/builtin-skills/skills/shell-data-workbench in bionic-gpt/bionic-gpt) into .agents/skills/shell-data-workbench in your project. Codex loads it when a task matches its description.
Can I use Shell Data Workbench 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 bionic-gpt/bionic-gpt --skill shell-data-workbench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shell-data-workbench, .gemini/skills/shell-data-workbench, .github/skills/shell-data-workbench and .opencode/skills/shell-data-workbench in your project.
What does Shell Data Workbench need to run?
SKILL.md names no scripts, command-line tools or credentials: Shell Data Workbench is instructions for the agent only.
Does Shell Data Workbench access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Shell Data Workbench 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. Review the folder before installing.
What licence does Shell Data Workbench use?
Shell Data Workbench is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Shell Data Workbench use?
About 131 tokens (SKILL.md is roughly 524 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Shell Data Workbench?
Skills that share tags, products or a category with Shell Data Workbench: Transformers (K-Dense-AI/scientific-agent-skills, 48k stars), Research Summarizer (alirezarezvani/claude-skills, 28k stars), Agent Sandbox (ruvnet/ruflo, 74k stars) and Shell Scripting (RightNow-AI/openfang, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Shell Data Workbench?
bionic-gpt (a GitHub organization) maintains it in bionic-gpt/bionic-gpt, which has 2,383 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.
Source: bionic-gpt/bionic-gpt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.