Skills

data-scientist

data-scientist is a skill in code-yeongyu/oh-my-openagent, last changed 3 Sept 2026. It can download software, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing. Our pattern check found 8 items to review at commit 79d7978 on 26 Oct 2026.

Pattern check: 8 items to review · commit 79d7978 · 26 Oct 2026

Install
From the author
Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or plotting a dataset.
Licence
Licence not identified
Repo stars
70.4k
Folder last changed
3 Sept 2026 (opens in a new tab)
Publisher
code-yeongyu
Files
11 files
Checked
79d7978 (opens in a new tab) · 26 Oct 2026

Install

Each tab says whether it installs commit 79d7978, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 79d7978, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/code-yeongyu/oh-my-openagent.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 79d797838381957c58035425730bdf61c3192f03 &&
  git -C "$tmp" sparse-checkout set -- packages/shared-skills/skills/data-scientist &&
  git -C "$tmp" checkout -q 79d797838381957c58035425730bdf61c3192f03 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/data-scientist &&
  cp -R "$tmp"/packages/shared-skills/skills/data-scientist/. .claude/skills/data-scientist/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 79d7978. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

    scripts/setup-uv.ps1 · scripts/setup-uv.sh

  • Downloads software

    It fetches programs or packages from the internet, or from a package source other than the default.

    references/uv-setup.md:19 · references/uv-setup.md:27 · references/uv-setup.md:35 and 6 more

Pattern check

Pattern check: 8 items to review · commit 79d7978 · 26 Oct 2026

We checked every text file in this skill, at commit 79d7978 on 26 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://astral.sh/uv/install.sh
  • https://astral.sh/uv/install.ps1
  • https://bun.sh

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses
  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      The description is 216 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

We only show SKILL.md text here when its licence clearly allows it.

Read SKILL.md on GitHub (opens in a new tab)

Files

11 files

PathSize
SKILL.md (opens in a new tab)5.7 KB
references/execution-surfaces.md (opens in a new tab)4 KB
references/placement.md (opens in a new tab)3.3 KB
references/polars-lane.md (opens in a new tab)3.5 KB
references/uv-setup.md (opens in a new tab)2.7 KB
references/visualization.md (opens in a new tab)2.9 KB
scripts/ensure-js-deps.sh (opens in a new tab)983 B
scripts/ensure-py-deps.sh (opens in a new tab)1.3 KB
scripts/quick-query.py (opens in a new tab)3.3 KB
scripts/setup-uv.ps1 (opens in a new tab)2.3 KB
scripts/setup-uv.sh (opens in a new tab)1.8 KB

More from code-yeongyu/oh-my-openagent

  • ast-grep

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.

    Pattern check: Items to reviewWhat it can touch: Downloads software · Changes agent settings +4

    MIT · 70.4k repo stars · Updated 25 Oct 2026

  • browser

    code-yeongyu/oh-my-openagent

    Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA traces. Use for any interactive browser task; not for a plain search or an unblocked static fetch.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Names web addresses +1

    No licence · 70.4k repo stars · Updated 23 Oct 2026

  • coding-agent-sessions

    code-yeongyu/oh-my-openagent

    Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Bundles scripts

    No licence · 70.4k repo stars · Updated 25 Oct 2026

  • comment-checker

    code-yeongyu/oh-my-openagent

    Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    No licence · 70.4k repo stars · Updated 30 May 2026

  • dag-library

    code-yeongyu/oh-my-openagent

    Stores a DAG definition once and re-runs it by name, instead of pasting the definition into every run. Use when the user wants to save a DAG, run a saved one, or schedule the same multi-agent graph repeatedly.

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    No licence · 70.4k repo stars · Updated 3 Sept 2026

  • debugging

    code-yeongyu/oh-my-openagent

    Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.

    Pattern check: Nothing flaggedWhat it can touch: Touches credentials · Downloads software +4

    No licence · 70.4k repo stars · Updated 30 Sept 2026

All skills in code-yeongyu/oh-my-openagent