New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Dataset Profiler

by oxbshw in oxbshw/LLM-Agents-Ecosystem-Handbook

A skill your agent uses when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.

MITAuto-check passedDevelopment

Install Dataset Profiler

skills CLI
$ npx skills add oxbshw/LLM-Agents-Ecosystem-Handbook --skill dataset-profiler -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install oxbshw/LLM-Agents-Ecosystem-Handbook dataset-profiler --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/oxbshw/LLM-Agents-Ecosystem-Handbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/catalog/dataset-profiler .claude/skills/dataset-profiler && rm -rf skills-src

Use ~/.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/

Facts

Skill name
dataset-profiler
GitHub stars
552
Token cost
~492 tokens
SKILL.md length
216 words
Files
2 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.

  • Works in 8 steps: Load with the right reader… → Schema: column → dtype → nullable →… → Missingness: % per column, top columns… → …
  • First encountering a new dataset — produces a structured profile (schema
  • SKILL.md covers When to use, When NOT to use, Inputs and Outputs, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dataset Profiler is an agent skill from oxbshw/LLM-Agents-Ecosystem-Handbook. Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.

Its SKILL.md is about 490 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/profile-template.md`).

It sits in Development, covering Performance optimization. The repository describes itself as: One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools. The licence is MIT.

When your agent uses it

  • First encountering a new dataset — produces a structured profile (schema
  • Gotchas) before any analysis

Example prompts

  • “/dataset-profiler”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Load with the right reader (extension-detected); record row count, file size
  2. Schema: column → dtype → nullable → example value
  3. Missingness: % per column, top columns by missingness
  4. Distributions: numeric (min, p50, p95, max, std), categorical (top-k, cardinality)
  5. Outliers: flag rows beyond p99 + 3·IQR for numerics
  6. Identify potential keys (unique columns) and join candidates
  7. Gotchas: timezone columns, mixed encodings, suspicious all-zero rows, magic values (-1, 9999-12-31)
  8. Open questions: ambiguous columns / values that need owner input

What it can do on your machine

Read from SKILL.md and the folder at commit 7f8ee3c. 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

Dataset Profiler loads about 492 tokens when it runs, and up to ~689 if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 216 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~492
With references · SKILL.md plus every file in references/, read only if the agent opens them
~689

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 oxbshw/LLM-Agents-Ecosystem-Handbook at commit 7f8ee3c, republished under its MIT licence (© oxbshw). 216 words, ~492 tokens.

Download SKILL.mdSave it as .claude/skills/dataset-profiler/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
dataset-profiler
description
Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.
version
0.1.0
status
experimental
risk
low
tags
data, read-only, writes-files

Dataset Profiler

When to use

  • A new dataset arrives and you need to understand it before using it
  • Before reproducing an analysis that referenced a dataset
  • When data quality is suspect ("the chart looked wrong")

When NOT to use

  • Streaming / online data (this is point-in-time)
  • Sensitive PII without an explicit allow-list

Inputs

NameTypeRequiredNotes
pathpathyesCSV / Parquet / JSONL
targetstringnocolumn of interest (gets extra distribution detail)

Outputs

profile.md with: Source, Schema, Missingness, Distributions, Outliers, Joins / keys, Gotchas, Open questions.

Workflow

  1. Load with the right reader (extension-detected); record row count, file size
  2. Schema: column → dtype → nullable → example value
  3. Missingness: % per column, top columns by missingness
  4. Distributions: numeric (min, p50, p95, max, std), categorical (top-k, cardinality)
  5. Outliers: flag rows beyond p99 + 3·IQR for numerics
  6. Identify potential keys (unique columns) and join candidates
  7. Gotchas: timezone columns, mixed encodings, suspicious all-zero rows, magic values (-1, 9999-12-31)
  8. Open questions: ambiguous columns / values that need owner input

References

Success criteria

  • Every column appears in Schema + Missingness
  • Outliers section includes example rows
  • Gotchas section is non-empty (real datasets always have some)

Failure modes

  • File too large to read in memory → switch to streaming + sampled stats; flag prominently
  • Encoding fails → try common alternatives; if all fail, surface and stop

© oxbshw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/catalog/dataset-profiler of oxbshw/LLM-Agents-Ecosystem-Handbook.

  • SKILL.md
  • references/profile-template.md

Open the folder on GitHubat commit 7f8ee3c

Compare with similar skills

Dataset Profiler 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.

Dataset Profiler compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dataset Profiler this skilloxbshw/LLM-Agents-Ecosystem-Handbook552—~492Automated safety check: PassMIT
LLM Torch Profiler Analysissgl-project/sglang37k2 repos~6.4kAutomated safety check: PassApache-2.0
ExecuTorch Binary Size Reductionpytorch/executorch5.1k—~793Automated safety check: PassCustom licence
The Art of Debuggingstas00/the-art-of-debugging1.7k—~6.1kAutomated safety check: NotesCC-BY-SA-4.0
Cudatechnillogue/ptx-isa-markdown229—~2.5kAutomated safety check: PassNone
Veomni ProfileByteDance-Seed/VeOmni2.2k—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • LLM Torch Profiler Analysis

    sgl-project/sglang

    Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

    37k GitHub starsUsed in 2 repos~6.4k tokens
    DevelopmentAuto-check passed

  • ExecuTorch Binary Size Reduction

    pytorch/executorch

    Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.

    5.1k GitHub stars~793 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • The Art of Debugging

    stas00/the-art-of-debugging

    Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

    1.7k GitHub stars~6.1k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes

  • Cuda

    technillogue/ptx-isa-markdown

    CUDA kernel development, debugging, and performance optimization for Claude Code.

    229 GitHub stars~2.5k tokensUpdated 9 mo ago
    DevelopmentAuto-check passed

  • Veomni Profile

    ByteDance-Seed/VeOmni

    A skill your agent uses for performance profiling and optimization.

    2.2k GitHub stars~1.7k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Torch Profiler Layer Track

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Adds verified layer guides such as L0 and L1 and compact GPU lanes to an existing Torch Profiler Chrome trace, changing how it looks but not how it ran.

    911 GitHub stars~2k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

More from oxbshw/LLM-Agents-Ecosystem-Handbook

  • API Design Reviewer

    oxbshw/LLM-Agents-Ecosystem-Handbook

    A skill your agent uses when reviewing a proposed REST or GraphQL API change before merge — checks contract clarity, backwards compatibility, errors, pagination, auth, and naming.

    552 GitHub stars~553 tokensUpdated 3 mo ago
    Auto-check passed

  • PR Summarizer

    oxbshw/LLM-Agents-Ecosystem-Handbook

    A skill your agent uses when opening a PR — produces a clean PR description (what / why / how to verify / risks) from a branch diff against base.

    552 GitHub stars~441 tokensUpdated 3 mo ago
    Auto-check: notes

  • Adr Writer

    oxbshw/LLM-Agents-Ecosystem-Handbook

    A skill your agent uses when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered, and the chosen path.

    552 GitHub stars~476 tokensUpdated 3 mo ago
    Auto-check passed

  • Sprint Planner

    oxbshw/LLM-Agents-Ecosystem-Handbook

    A skill your agent uses when planning the next sprint — turns ticket intake + team capacity into a planned sprint with explicit non-goals.

    552 GitHub stars~429 tokensUpdated 3 mo ago
    Auto-check passed

  • Incident Postmortem

    oxbshw/LLM-Agents-Ecosystem-Handbook

    Use after an incident is resolved — drafts a blameless postmortem from timeline notes, alerts, and chat threads.

    552 GitHub stars~461 tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Dataset Profiler

What does Dataset Profiler do?

A skill your agent uses when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis. Dataset Profiler is an agent skill from oxbshw/LLM-Agents-Ecosystem-Handbook. Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.

When should I use Dataset Profiler?

Dataset Profiler fits situations like: first encountering a new dataset — produces a structured profile (schema; gotchas) before any analysis.

How do I install Dataset Profiler in Claude Code?

Run `npx skills add oxbshw/LLM-Agents-Ecosystem-Handbook --skill dataset-profiler -a claude-code`. Or copy the skill folder (skills/catalog/dataset-profiler in oxbshw/LLM-Agents-Ecosystem-Handbook) into .claude/skills/dataset-profiler in your project. Claude Code loads it when a task matches its description.

How do I install Dataset Profiler in Codex?

Run `npx skills add oxbshw/LLM-Agents-Ecosystem-Handbook --skill dataset-profiler -a codex`. Or copy the skill folder (skills/catalog/dataset-profiler in oxbshw/LLM-Agents-Ecosystem-Handbook) into .agents/skills/dataset-profiler in your project. Codex loads it when a task matches its description.

Can I use Dataset Profiler 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 oxbshw/LLM-Agents-Ecosystem-Handbook --skill dataset-profiler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dataset-profiler, .gemini/skills/dataset-profiler, .github/skills/dataset-profiler and .opencode/skills/dataset-profiler in your project.

What does Dataset Profiler need to run?

SKILL.md names no scripts, command-line tools or credentials: Dataset Profiler is instructions for the agent only.

Does Dataset Profiler 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 Dataset Profiler 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 Dataset Profiler use?

Dataset Profiler is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dataset Profiler use?

About 492 tokens (SKILL.md is roughly 2k 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 197 tokens, read only when the agent opens those files.

What are the alternatives to Dataset Profiler?

Skills that share tags, products or a category with Dataset Profiler: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), ExecuTorch Binary Size Reduction (pytorch/executorch, 5.1k stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and Cuda (technillogue/ptx-isa-markdown, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dataset Profiler?

oxbshw (a GitHub user) maintains it in oxbshw/LLM-Agents-Ecosystem-Handbook, which has 552 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 30, 2026.

Source: oxbshw/LLM-Agents-Ecosystem-Handbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.