dataset-finder
Find and rank datasets for a replication or ML task by requirements, license, and availability.
Skill by TQuang122
Chalk Labs
Need help deploying dataset-finder?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tquang122-dataset-finder
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, ml, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/dataset-finder
What's inside
- Skill name
dataset-finder- Description
- Find and rank datasets for a replication or ML task by requirements, license, and availability. Use when the user needs training or evaluation data and asks which dataset to use.
- License
- MIT
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Dataset Finder Turn a task description into a ranked dataset shortlist with access paths. Workflow: 1. Pin requirements first: task type, modality, minimum size, license constraints, and needed splits (train/dev/test). 2. Search Hugging Face datasets (`hf_dataset_info` and related tools) plus web search for gated or domain-specific sources (Kaggle, Papers with Code, official releases). 3. Evaluate each candidate: license compatibility with the user's use, size and split availability, recency and maintenance status, and adoption in comparable work. 4. Record a ranked table (dataset, source URL or ID, license, size/splits, why it fits or does not) as an artifact. Never recommend scraping a gated or login-walled source without saying so. 5. Hand the top pick to `replication` or `ml-training-recipe` with its access path and license note. Agents used: `evidence-scout` (for broad dataset sweeps) Output: ranked dataset table in `outputs/`.
From TQuang122/hypatia, MIT.
More from TQuang122/hypatia
- 0.598score
alpha-research
TQuang122
Search, read, and query research papers via Hypatia's alphaXiv-backed alpha tools.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
research-ideation
TQuang122
Brainstorm a small, evidence-aware set of research directions when the user explicitly asks to explore ideas, find a fresh angle, or get unstuck.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
research-diagrams
TQuang122
Create concise, evidence-grounded Mermaid diagrams for research explanations, method comparisons, workflows, and architectures.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
research-wiki
TQuang122
Use when the current workspace contains `wiki/` and a research task could benefit from prior project synthesis, or the user asks to maintain that wiki.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
autoresearch
TQuang122
Run persistent bounded benchmark experiments or lineage-linked experiment trees with shared budgets, observed metrics, receipts, and pause/resume.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
citation-export
TQuang122
Export the Sources section of a cited research draft to a BibTeX (.bib) file.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
session-search
TQuang122
Search prior Hypatia session transcripts on disk.
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 10, 2026 (21 days ago)
- Last release
- Oct 16, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/TQuang122/hypatia
- Website
- tquang122.github.io/hypatia/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TQuang122
- 0.598score
alpha-research
TQuang122
Search, read, and query research papers via Hypatia's alphaXiv-backed alpha tools.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
research-ideation
TQuang122
Brainstorm a small, evidence-aware set of research directions when the user explicitly asks to explore ideas, find a fresh angle, or get unstuck.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
research-diagrams
TQuang122
Create concise, evidence-grounded Mermaid diagrams for research explanations, method comparisons, workflows, and architectures.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
research-wiki
TQuang122
Use when the current workspace contains `wiki/` and a research task could benefit from prior project synthesis, or the user asks to maintain that wiki.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
autoresearch
TQuang122
Run persistent bounded benchmark experiments or lineage-linked experiment trees with shared budgets, observed metrics, receipts, and pause/resume.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
citation-export
TQuang122
Export the Sources section of a cited research draft to a BibTeX (.bib) file.
SkillAFreshness: A★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get dataset-finder running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
dataset-finder skill. Agent Mart. https://agentmart.dev/skills/tquang122-dataset-finder (last updated 2026-10-24)