Migrate
guhcostan/claude-mega-brain
Scan the project and migrate existing documentation into OKF format.
Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced.
Install Datachain Core
$ npx skills add datachain-ai/datachain --skill datachain-core -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install datachain-ai/datachain datachain-core --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/datachain-ai/datachain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/datachain/skill/core .claude/skills/datachain-core && 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 "datachain-core" agent skill from https://github.com/datachain-ai/datachain/tree/main/src/datachain/skill/core into .claude/skills/datachain-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datachain-core", 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/datachain-ai/datachain/tree/main/src/datachain/skill/coreType 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 datachain-ai/datachain --skill datachain-core -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install datachain-ai/datachain datachain-core --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/datachain-ai/datachain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/datachain/skill/core .agents/skills/datachain-core && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "datachain-core" agent skill from https://github.com/datachain-ai/datachain/tree/main/src/datachain/skill/core into .agents/skills/datachain-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datachain-core", 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 datachain-ai/datachain --skill datachain-core -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install datachain-ai/datachain datachain-core --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/datachain-ai/datachain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/datachain/skill/core .cursor/skills/datachain-core && 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 "datachain-core" agent skill from https://github.com/datachain-ai/datachain/tree/main/src/datachain/skill/core into .cursor/skills/datachain-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datachain-core", 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/datachain-ai/datachain.git --path src/datachain/skill/core--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 datachain-ai/datachain --skill datachain-core -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install datachain-ai/datachain datachain-core --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/datachain-ai/datachain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/datachain/skill/core .gemini/skills/datachain-core && 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 "datachain-core" agent skill from https://github.com/datachain-ai/datachain/tree/main/src/datachain/skill/core into .gemini/skills/datachain-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datachain-core", 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 datachain-ai/datachain datachain-coreInstalls 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 datachain-ai/datachain --skill datachain-core -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/datachain-ai/datachain.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/datachain/skill/core .github/skills/datachain-core && 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 "datachain-core" agent skill from https://github.com/datachain-ai/datachain/tree/main/src/datachain/skill/core into .github/skills/datachain-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datachain-core", 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 datachain-ai/datachain --skill datachain-core -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install datachain-ai/datachain datachain-core --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/datachain-ai/datachain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/datachain/skill/core .opencode/skills/datachain-core && 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 "datachain-core" agent skill from https://github.com/datachain-ai/datachain/tree/main/src/datachain/skill/core into .opencode/skills/datachain-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "datachain-core", 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
datachain-core- GitHub stars
- 2.8k
- Token cost
- ~423 tokens
- SKILL.md length
- 206 words
- Files
- 2
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced.
- Works in 3 steps: If dc-knowledge/index.md exists, read it… → When the user's task overlaps with an… → Bucket access: anonymous or…
- Knowledge Management work in your project
- SKILL.md covers Scope of this skill and Before writing any pipeline code
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Datachain Core is an agent skill from datachain-ai/datachain. Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.
Its SKILL.md is about 420 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `SDK.md`).
It sits in Knowledge Management. It works with Pydantic. The repository describes itself as: The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure. The licence is Apache-2.0.
When your agent uses it
- Knowledge Management work in your project
Example prompts
- “/datachain-core”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- If dc-knowledge/index.md exists, read it first.
- When the user's task overlaps with an existing dataset, read its .md under dc-knowledge/datasets/ for schema, code patterns, and lineage.
- Bucket access: anonymous or authenticated? Check dc-knowledge/buckets/ for a .md file with anon: true/false in frontmatter. If none, run…
What it can do on your machine
Read from SKILL.md and the folder at commit cbb008d. 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
Datachain Core loads about 423 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 206 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 datachain-ai/datachain at commit cbb008d, republished under its Apache-2.0 licence (© datachain-ai). 206 words, ~423 tokens.
Download SKILL.mdSave it as
.claude/skills/datachain-core/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- datachain-core
- description
- Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.
Read {skill_dir}/SDK.md in full before answering DataChain SDK questions or generating DataChain Python code. It holds the SDK rules: API usage, UDF signatures, settings, delta semantics, materialization patterns, saving, exporting. The last section below holds the steps that need a local checkout and the dc-knowledge/ knowledge base.
Scope of this skill
SDK.md owns how DataChain code is written — API usage, UDF signatures, the shape of a saved dataset, saving and exporting. It is self-sufficient on its own.
The datachain-knowledge skill owns the knowledge base at dc-knowledge/: what datasets already exist, what each one holds, how long a run will take, and keeping that record current. When it is loaded, it drives the session and calls the rules here to write the code.
Before writing any pipeline code
- If
dc-knowledge/index.mdexists, read it first. - When the user's task overlaps with an existing dataset, read its
.mdunderdc-knowledge/datasets/for schema, code patterns, and lineage. - Bucket access: anonymous or authenticated? Check
dc-knowledge/buckets/for a.mdfile withanon: true/falsein frontmatter. If none, rundatachain bucket status <uri>to detect. Ifdeniedornot found, stop and ask the user.
Never create or modify files under dc-knowledge/ — that directory is owned by the knowledge skill.
© datachain-ai, 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
SKILL.md and 1 other file in src/datachain/skill/core of datachain-ai/datachain.
- SKILL.md
- SDK.md
Open the folder on GitHubat commit cbb008d
Compare with similar skills
Datachain Core 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 |
|---|---|---|---|---|---|---|
| Datachain Core this skilldatachain-ai/datachain | 2.8k | — | ~423 | Automated safety check: Pass | Apache-2.0 | |
| Migrateguhcostan/claude-mega-brain | 126 | — | ~975 | Automated safety check: Pass | MIT | |
| Export TemplateHurricaHjz/second-yourself | 114 | — | ~4.8k | Automated safety check: Warn | MIT | |
| Obsidian CLIAtmosphere/atmosphere | 3.8k | 13 repos | ~795 | Automated safety check: Pass | Apache-2.0 | |
| Ima Knowledge Basecountbot-ai/CountBot | 782 | — | ~506 | Automated safety check: Pass | MIT | |
| Research Lintiusztinpaul/ai-research-os-workshop | 179 | — | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
Export Template
HurricaHjz/second-yourself
Sync THIS LLM-Wiki framework with its public GitHub repo, ONE direction per run: --push (vault → repo) publishes your framework; --pull (repo → vault) updates your framework from a newer repo version.
Obsidian CLI
Atmosphere/atmosphere
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.
Ima Knowledge Base
countbot-ai/CountBot
通过 IMA OpenAPI 处理知识库任务。支持知识库内容搜索、命中详情查看、条目浏览、列出知识库、上传文件、导入网页。用户提到知识库、资料库、上传到知识库、导入网页、搜知识库时使用。
Research Lint
iusztinpaul/ai-research-os-workshop
Health-check a research directory produced by /research. An agent skill from iusztinpaul/ai-research-os-workshop.
ModelViz Scientific Plots
hrdZhu/modelviz-skill
Turns your CSV or Excel data and a plain-language request into a publication-style scientific chart by adapting a catalog template, then checks and repairs it.
More from datachain-ai/datachain
Datachain Knowledge
datachain-ai/datachain
A skill your agent uses whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure…
Related
Works with
Categories
Questions about Datachain Core
What does Datachain Core do?
Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. Datachain Core is an agent skill from datachain-ai/datachain. Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced.
When should I use Datachain Core?
Datachain Core fits situations like: knowledge Management work in your project.
How do I install Datachain Core in Claude Code?
Run `npx skills add datachain-ai/datachain --skill datachain-core -a claude-code`. Or copy the skill folder (src/datachain/skill/core in datachain-ai/datachain) into .claude/skills/datachain-core in your project. Claude Code loads it when a task matches its description.
How do I install Datachain Core in Codex?
Run `npx skills add datachain-ai/datachain --skill datachain-core -a codex`. Or copy the skill folder (src/datachain/skill/core in datachain-ai/datachain) into .agents/skills/datachain-core in your project. Codex loads it when a task matches its description.
Can I use Datachain Core 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 datachain-ai/datachain --skill datachain-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/datachain-core, .gemini/skills/datachain-core, .github/skills/datachain-core and .opencode/skills/datachain-core in your project.
What does Datachain Core need to run?
SKILL.md names no scripts, command-line tools or credentials: Datachain Core is instructions for the agent only. Our summary lists: Python 3.
Does Datachain Core 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 Datachain Core 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 Datachain Core use?
Datachain Core 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 Datachain Core use?
About 423 tokens (SKILL.md is roughly 1.7k 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 Datachain Core?
Skills that share tags, products or a category with Datachain Core: Migrate (guhcostan/claude-mega-brain, 126 stars), Export Template (HurricaHjz/second-yourself, 114 stars), Obsidian CLI (Atmosphere/atmosphere, 3.8k stars) and Ima Knowledge Base (countbot-ai/CountBot, 782 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Datachain Core?
datachain-ai (a GitHub organization) maintains it in datachain-ai/datachain, which has 2,823 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.
Source: datachain-ai/datachain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.