Hugging Face Tokenizers
Orchestra-Research/AI-Research-SKILLs
Shows how to load, train and use fast Hugging Face tokenizers, with BPE, WordPiece and Unigram models, padding, truncation and alignment tracking.
Build, inspect, prepare, generate and export Overmind datasets in Data Workshop.
Install Overmind Datasets
$ npx skills add overmind-core/overmind --skill overmind-datasets -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install overmind-core/overmind overmind-datasets --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/overmind-core/overmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/overmind/skills/overmind-datasets .claude/skills/overmind-datasets && 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 "overmind-datasets" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-datasets into .claude/skills/overmind-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-datasets", 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/overmind-core/overmind/tree/main/overmind/skills/overmind-datasetsType 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 overmind-core/overmind --skill overmind-datasets -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install overmind-core/overmind overmind-datasets --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .agents/skills && cp -r skills-src/overmind/skills/overmind-datasets .agents/skills/overmind-datasets && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "overmind-datasets" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-datasets into .agents/skills/overmind-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-datasets", 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 overmind-core/overmind --skill overmind-datasets -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install overmind-core/overmind overmind-datasets --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/overmind/skills/overmind-datasets .cursor/skills/overmind-datasets && 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 "overmind-datasets" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-datasets into .cursor/skills/overmind-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-datasets", 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/overmind-core/overmind.git --path overmind/skills/overmind-datasets--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 overmind-core/overmind --skill overmind-datasets -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install overmind-core/overmind overmind-datasets --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/overmind/skills/overmind-datasets .gemini/skills/overmind-datasets && 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 "overmind-datasets" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-datasets into .gemini/skills/overmind-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-datasets", 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 overmind-core/overmind overmind-datasetsInstalls 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 overmind-core/overmind --skill overmind-datasets -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .github/skills && cp -r skills-src/overmind/skills/overmind-datasets .github/skills/overmind-datasets && 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 "overmind-datasets" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-datasets into .github/skills/overmind-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-datasets", 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 overmind-core/overmind --skill overmind-datasets -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install overmind-core/overmind overmind-datasets --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/overmind/skills/overmind-datasets .opencode/skills/overmind-datasets && 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 "overmind-datasets" agent skill from https://github.com/overmind-core/overmind/tree/main/overmind/skills/overmind-datasets into .opencode/skills/overmind-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "overmind-datasets", 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
overmind-datasets- GitHub stars
- 597
- Token cost
- ~875 tokens
- SKILL.md length
- 433 words
- Files
- 3 (incl. assets)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Build, inspect, prepare, generate and export Overmind datasets in Data Workshop.
- Trace-to-data workflows
- SKILL.md covers Land and inspect, Prepare through the workshop and Hand off the version
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Semantic repair proposals and train/eval preparation
What it does
Overmind Datasets is an agent skill from overmind-core/overmind. Build, inspect, prepare, generate and export Overmind datasets in Data Workshop. Use for trace-to-data workflows, dataset cells, semantic repair proposals and train/eval preparation; model-specific tokenization belongs to Training.
Its SKILL.md is about 880 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including assets (for example `agents/openai.yaml`).
It sits in AI & LLM Engineering, covering Natural language processing and Proposals and quotes. The repository describes itself as: The platform for continuously improving AI agents. The licence is AGPL-3.0.
When your agent uses it
- Trace-to-data workflows
- Semantic repair proposals and train/eval preparation
- Model-specific tokenization belongs to Training
Example prompts
- “/overmind-datasets”
What it can do on your machine
Read from SKILL.md and the folder at commit 3dec73c. 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
Overmind Datasets loads about 875 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 433 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 overmind-core/overmind at commit 3dec73c, republished under its AGPL-3.0 licence (© overmind-core). 433 words, ~875 tokens.
Download SKILL.mdSave it as
.claude/skills/overmind-datasets/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- overmind-datasets
- description
- Build, inspect, prepare, generate and export Overmind datasets in Data Workshop. Use for trace-to-data workflows, dataset cells, semantic repair proposals and train/eval preparation; model-specific tokenization belongs to Training.
Overmind Datasets
Start with list_projects and choose the intended accessible project. For an
account connection, pass its project_id on every project tool and resource
URI query; follow returned links. Project API keys retain their narrower access.
Prepare a usable dataset version with evidence for its intended consumer. Use
the chosen MCP project from overmind://project/current?project_id=ID. Resolve existing
datasets with list_datasets; names are not unique, so continue with returned UUIDs.
Land and inspect
Use create_dataset_from_traces for a requested trace selection, with either
explicit IDs or the supported filters/search. For local files, use the native
upload-dataset-file prompt or read overmind://dataset-upload and follow its
CLI handoff. MCP does not transport file bytes or require credentials in chat.
Poll the returned dataset work with get_job(kind=dataset_run, id=...), then
inspect_dataset. Inspect the source and active task-family profiles, downstream
requirements, cell chain, measured contracts, quality coverage and recent chat.
Use query_dataset for bounded read-only checks on table t; one sample does
not establish the meaning of every task family.
A dataset has one intent and a chain of cells. A ran cell is a readable version; consumers pin the selected cell. Keep train and held-out evaluation identities separate, including duplicate groups and synthetic seed lineage.
Show full SKILL.md (236 more words)Show less
Prepare through the workshop
Use message_dataset_agent for requested name, intent, capability or cell
changes. Specify the target task, supplied evidence, required output shape and
consumer. Preparation means supported transformations, audit, repairs and a
recheck of the changed version; an audit-only request does not authorize edits.
Inspect task_alignment, input_evidence, answer_support and output_schema
findings and their measured coverage. Missing evidence remains unknown. Do not
insert reference answers into inputs or relabel worker outputs as end-to-end
capability outputs. Keep the workshop model-independent.
Semantic replacements require a concrete reviewed proposal. Explain its actual
row examples, counts and coverage effects; call run_dataset(proposal_cell=...)
only for the approved proposal. Poll through the resumed agent turn and inspect
again. awaiting_approval is a decision checkpoint, not a failed generation.
For requested synthetic data, explicitly ask the dataset agent to generate new examples and record their lineage. Do not duplicate rows to hit a target. If a run stops early, report saved rows and remaining work; generated labels are not independently verified ground truth.
Hand off the version
Verify the chosen cell with query_dataset. Report dataset/cell IDs, intent,
row count, coverage and residual findings. Quality findings are advisory; only
unreadable or technically incompatible data blocks the consumer. Do not invent
a quality-approval gate or silently change a selected version.
For download, prefer export-dataset or read overmind://dataset-export for
the local CLI action. Open datasets/{id} under the project's console_url
base, preserving projectId, when the user wants the notebook.
© overmind-core, AGPL-3.0. 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 2 other files (assets) in overmind/skills/overmind-datasets of overmind-core/overmind.
- SKILL.md
- agents/openai.yaml
- assets/icon.png
Open the folder on GitHubat commit 3dec73c
Compare with similar skills
Overmind Datasets 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 |
|---|---|---|---|---|---|---|
| Overmind Datasets this skillovermind-core/overmind | 597 | — | ~875 | Automated safety check: Pass | AGPL-3.0 | |
| Hugging Face TokenizersOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~3.4k | Automated safety check: Pass | MIT | |
| OpenMed Model Card Writermaziyarpanahi/openmed | 5.5k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel | 1.3k | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Comparetaishi-i/awesome-japanese-nlp-resources | 1k | 1 repos | ~4.1k | Automated safety check: Notes | CC0-1.0 | |
| Critic AgentAMD-AGI/Hyperloom | 217 | — | ~3.5k | Automated safety check: Pass | Custom licence |
Similar skills
OpenMed Model Card Writer
maziyarpanahi/openmed
Fills in a model card for an OpenMed clinical NER or de-identification model from its evaluation reports: intended use, metrics, subgroups and limitations.
Gptqmodel Tokenizer Normalization
ModelCloud/GPTQModel
Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.
Compare
taishi-i/awesome-japanese-nlp-resources
Compare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as…
Critic Agent
AMD-AGI/Hyperloom
Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom.
Research
taishi-i/awesome-japanese-nlp-resources
Analyze current trends and challenges in Japanese NLP for a topic.
More from overmind-core/overmind
All 20 skills in this repoAPI Endpoints
overmind-core/overmind
End-to-end workflow for adding or changing a backend API endpoint — which module the serializer and view belong in, URL registration, OpenAPI client regeneration, and typed consumption from the…
Finetuning Model Onboarding
overmind-core/overmind
Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…
Frontend Design
overmind-core/overmind
Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.
MCP
overmind-core/overmind
End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, and required…
PR Etiquette
overmind-core/overmind
How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…
Seed Demo Data
overmind-core/overmind
Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.
Related
Categories
Questions about Overmind Datasets
What does Overmind Datasets do?
Build, inspect, prepare, generate and export Overmind datasets in Data Workshop. Overmind Datasets is an agent skill from overmind-core/overmind. Build, inspect, prepare, generate and export Overmind datasets in Data Workshop.
When should I use Overmind Datasets?
Overmind Datasets fits situations like: trace-to-data workflows; semantic repair proposals and train/eval preparation; model-specific tokenization belongs to Training.
How do I install Overmind Datasets in Claude Code?
Run `npx skills add overmind-core/overmind --skill overmind-datasets -a claude-code`. Or copy the skill folder (overmind/skills/overmind-datasets in overmind-core/overmind) into .claude/skills/overmind-datasets in your project. Claude Code loads it when a task matches its description.
How do I install Overmind Datasets in Codex?
Run `npx skills add overmind-core/overmind --skill overmind-datasets -a codex`. Or copy the skill folder (overmind/skills/overmind-datasets in overmind-core/overmind) into .agents/skills/overmind-datasets in your project. Codex loads it when a task matches its description.
Can I use Overmind Datasets 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 overmind-core/overmind --skill overmind-datasets -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/overmind-datasets, .gemini/skills/overmind-datasets, .github/skills/overmind-datasets and .opencode/skills/overmind-datasets in your project.
What does Overmind Datasets need to run?
SKILL.md names no scripts, command-line tools or credentials: Overmind Datasets is instructions for the agent only.
Does Overmind Datasets 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 Overmind Datasets 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 Overmind Datasets use?
Overmind Datasets is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Overmind Datasets use?
About 875 tokens (SKILL.md is roughly 3.5k 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 Overmind Datasets?
Skills that share tags, products or a category with Overmind Datasets: Hugging Face Tokenizers (Orchestra-Research/AI-Research-SKILLs, 13k stars), OpenMed Model Card Writer (maziyarpanahi/openmed, 5.5k stars), Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars) and Compare (taishi-i/awesome-japanese-nlp-resources, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Overmind Datasets?
overmind-core (a GitHub organization) maintains it in overmind-core/overmind, which has 597 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.
Source: overmind-core/overmind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.