Register zarr positions into the Computational Imaging Database on Airtable, write channelsmetadata/experimentmetadata to zarr .zattrs, or bulk-update Airtable records via MCP.
$ npx skills add mehta-lab/VisCy --skill airtable-register -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mehta-lab/VisCy airtable-register --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/mehta-lab/VisCy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/airtable-register .claude/skills/airtable-register && 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 "airtable-register" agent skill from https://github.com/mehta-lab/VisCy/tree/main/.claude/skills/airtable-register into .claude/skills/airtable-register/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airtable-register", 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/mehta-lab/VisCy/tree/main/.claude/skills/airtable-registerType 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 mehta-lab/VisCy --skill airtable-register -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mehta-lab/VisCy airtable-register --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mehta-lab/VisCy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/airtable-register .agents/skills/airtable-register && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "airtable-register" agent skill from https://github.com/mehta-lab/VisCy/tree/main/.claude/skills/airtable-register into .agents/skills/airtable-register/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airtable-register", 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 mehta-lab/VisCy --skill airtable-register -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mehta-lab/VisCy airtable-register --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mehta-lab/VisCy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/airtable-register .cursor/skills/airtable-register && 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 "airtable-register" agent skill from https://github.com/mehta-lab/VisCy/tree/main/.claude/skills/airtable-register into .cursor/skills/airtable-register/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airtable-register", 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/mehta-lab/VisCy.git --path .claude/skills/airtable-register--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 mehta-lab/VisCy --skill airtable-register -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mehta-lab/VisCy airtable-register --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mehta-lab/VisCy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/airtable-register .gemini/skills/airtable-register && 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 "airtable-register" agent skill from https://github.com/mehta-lab/VisCy/tree/main/.claude/skills/airtable-register into .gemini/skills/airtable-register/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airtable-register", 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 mehta-lab/VisCy airtable-registerInstalls 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 mehta-lab/VisCy --skill airtable-register -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mehta-lab/VisCy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/airtable-register .github/skills/airtable-register && 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 "airtable-register" agent skill from https://github.com/mehta-lab/VisCy/tree/main/.claude/skills/airtable-register into .github/skills/airtable-register/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airtable-register", 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 mehta-lab/VisCy --skill airtable-register -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mehta-lab/VisCy airtable-register --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mehta-lab/VisCy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/airtable-register .opencode/skills/airtable-register && 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 "airtable-register" agent skill from https://github.com/mehta-lab/VisCy/tree/main/.claude/skills/airtable-register into .opencode/skills/airtable-register/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airtable-register", 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.
airtable-registerRegister zarr positions into the Computational Imaging Database on Airtable, write channelsmetadata/experimentmetadata to zarr .zattrs, or bulk-update Airtable records via MCP.
Airtable Register is an agent skill from mehta-lab/VisCy. Register zarr positions into the Computational Imaging Database on Airtable, write channelsmetadata/experimentmetadata to zarr .zattrs, or bulk-update Airtable records via MCP. Use when the user asks to "register a dataset", "register zarr positions", "update airtable from zarr", "write metadata to zarr", "run register on", "sync airtable", "populate channel markers", "update airtable records", "backfill fields", or "fill in missing fields". Also use for Marker Registry questions.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Data & Analytics, covering DataFrames. It works with Airtable, Zarr and Model Context Protocol. The repository describes itself as: computer vision models for single-cell phenotyping. The licence is BSD-3-Clause.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4b62365. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
uvFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
AIRTABLE_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Airtable Register loads about 1.9k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 563 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.
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.
The full file from mehta-lab/VisCy at commit 4b62365, republished under its BSD-3-Clause licence (© mehta-lab). 563 words, ~1,923 tokens.
.claude/skills/airtable-register/SKILL.md (or your agent's skills folder).Manages bidirectional metadata sync between OME-Zarr datasets and the Computational Imaging Database on Airtable, and supports bulk field updates via MCP.
app8vqaoWyOwa0sB5 (Computational Imaging Database)tblaFzrDMlVZHPZIjtblu0Rbj9OnLl7vJftblVZhRA48tDMWj8UtblmP8l2GmpCeERyDapplications/airtable/scripts/write_experiment_metadata.pyapplications/airtable/src/airtable_utils/registration.pyapplications/airtable/src/airtable_utils/schemas.pyapplications/airtable/src/airtable_utils/database.pypackages/viscy-data/src/viscy_data/channel_utils.pyMAX_CHANNELS = 8 (defined in schemas.py)AIRTABLE_API_KEY and AIRTABLE_BASE_ID must be set in environmentReads zarr metadata and writes per-FOV records to Airtable.
Fields written by register:
data_path — full path to zarr positionchannel_{i}_name — zarr channel names (up to 8)channel_{i}_marker — protein marker, derived from Marker Registryt_shape, c_shape, z_shape, y_shape, x_shape — array dimensionspixel_size_xy_um, pixel_size_z_um — from zarr coordinate transformsMarker derivation rules:
"Phase3D", "BF", "DIC")"nuclei_prediction")"TOMM20", "SEC61B")# Dry run first (always recommended)
uv run --package airtable-utils \
applications/airtable/scripts/write_experiment_metadata.py \
register --dry-run /path/to/dataset.zarr/*/*/*
# Register all positions
uv run --package airtable-utils \
applications/airtable/scripts/write_experiment_metadata.py \
register /path/to/dataset.zarr/*/*/*
# Single position
uv run --package airtable-utils \
applications/airtable/scripts/write_experiment_metadata.py \
register /path/to/dataset.zarr/A/1/000000
# Override dataset name (when zarr stem doesn't match Airtable)
uv run --package airtable-utils \
applications/airtable/scripts/write_experiment_metadata.py \
register --dataset my_dataset /path/to/dataset.zarr/*/*/*After registration, the CLI prints a Parquet Readiness report that flags any fields still needed before a flat parquet cell index can be built. Fields are split by source:
register): data_path, channel_N_name, channel_N_marker, pixel_size_xy_um, pixel_size_z_umtracks_path, perturbation, time_interval_min, hours_post_perturbation, cell_typeIf any platemap fields are missing, the report shows what to fill in and how (Airtable UI or MCP bulk update).
Writes channels_metadata and experiment_metadata to zarr .zattrs.
uv run --package airtable-utils \
applications/airtable/scripts/write_experiment_metadata.py \
write /path/to/dataset.zarr/*/*/*{
"Phase3D": {
"channel_type": "labelfree",
"biological_annotation": {"marker": "Phase3D"}
},
"raw GFP EX488 EM525-45": {
"channel_type": "fluorescence",
"biological_annotation": {
"marker": "TOMM20",
"marker_type": "protein_tag",
"fluorophore": null
}
}
}{
"perturbations": [
{"name": "ZIKV", "type": "unknown", "hours_post": 48.0, "moi": 5.0}
],
"time_sampling_minutes": 15.0
}For updating fields that don't come from zarr (e.g. tracks_path, organelle, manually-curated fields).
Process:
mcp__airtable__list_records using filterByFormulamcp__airtable__update_records (max 10 per call, send all batches in parallel)Pagination warning: mcp__airtable__list_records returns ~100 records max per call. If count equals ~100, re-query with tighter filters.
| Field | Description | Written by register? |
|---|---|---|
dataset | Experiment name | on create |
well_id | Well path (e.g. B/2) | on create |
fov | FOV identifier | on create |
data_path | Path to HCS OME-Zarr position | yes |
tracks_path | Path to tracking zarr | no (manual/MCP) |
channel_0_name .. channel_7_name | Zarr channel names | yes |
channel_0_marker .. channel_7_marker | Protein marker per channel | yes |
t_shape .. x_shape | Array dimensions | yes |
pixel_size_xy_um | Physical XY pixel size (um) | yes |
pixel_size_z_um | Physical Z pixel size (um) | yes |
marker | Well-level primary marker | template copy |
organelle | Target organelle | template copy |
perturbation | Perturbation applied | template copy |
cell_type | Cell type (e.g. A549) | template copy |
cell_state | Condition label | template copy |
time_interval_min | Minutes between frames | template copy |
hours_post_perturbation | HPI at imaging start | template copy |
moi | Multiplicity of infection | template copy |
fluorescence_modality | Imaging modality | template copy |
Table tblmP8l2GmpCeERyD — maps constructs to protein markers.
| Field | Type | Example |
|---|---|---|
marker-fluorophore | text (primary) | TOMM20-GFP |
channel_name_aliases | text | GFP, FITC |
marker | text | TOMM20 |
Matching is substring-based: "GFP" in "raw GFP EX488 EM525-45" -> match.
The register command writes all fields needed to build a flat parquet cell index:
channel_{i}_name -> parquet channel_namechannel_{i}_marker -> parquet markerpixel_size_xy_um, pixel_size_z_um -> parquet pixel size columnsdata_path -> parquet store_pathFor organelle_dynamics datasets:
data_path: /hpc/projects/intracellular_dashboard/organelle_dynamics/{EXP}/2-assemble/{EXP}.zarr
tracks_path: /hpc/projects/intracellular_dashboard/organelle_dynamics/{EXP}/1-preprocess/label-free/3-track/{EXP}_cropped.zarrOther families (organelle_box, viral-sensor) have non-standard structures — check filesystem.
© mehta-lab, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/airtable-register of mehta-lab/VisCy.
Open the folder on GitHubat commit 4b62365
Airtable Register 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 |
|---|---|---|---|---|---|---|
| Airtable Register this skillmehta-lab/VisCy | 104 | — | ~1.9k | Automated safety check: Pass | BSD-3-Clause | |
| Retentioneering Product Analyticsretentioneering/retentioneering-tools | 925 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Investigate Datawalkthru-earth/geocoding-playground | 153 | — | ~935 | Automated safety check: Pass | CC-BY-4.0 | |
| Downloading Batch Export FilesPostHog/posthog | 40k | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| Setup Polarchmonitor/chmonitor | 299 | — | ~1.1k | Automated safety check: Warn | GPL-3.0 | |
| Ray Data for ML PipelinesOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~1.8k | Automated safety check: Pass | MIT |
retentioneering/retentioneering-tools
Analyze event logs, clickstreams, user paths, product funnels, retention, behavioral segments, transition graphs, step matrices, sequence patterns, and customer journeys using Retentioneering.
walkthru-earth/geocoding-playground
Investigates geocoder data quality issues by querying live S3 parquet files via MotherDuck MCP.
PostHog/posthog
Export PostHog events, persons, sessions, or the results of a HogQL query on demand and download the resulting files.
chmonitor/chmonitor
Interactive onboarding wizard to set up Polar payment integration from scratch.
Orchestra-Research/AI-Research-SKILLs
Uses Ray Data to read, transform and write large datasets across a cluster for ML training and batch inference, with streaming execution and optional GPU steps.
davila7/claude-code-templates
Chunked N-D arrays for cloud storage. An agent skill from davila7/claude-code-templates.
mehta-lab/VisCy
Prepare datasets for training on VAST storage (NFS - VAST rechunked zarr v3 pipeline).
mehta-lab/VisCy
Query Airtable MCP to fetch experiment metadata and generate a DynaCLR collection YAML for training
mehta-lab/VisCy
Develop, deploy, and maintain the DynaCell virtual-staining HuggingFace demo hosted at biohub/dynacell (ZeroGPU).
Works with
Categories
Register zarr positions into the Computational Imaging Database on Airtable, write channelsmetadata/experimentmetadata to zarr .zattrs, or bulk-update Airtable records via MCP. Airtable Register is an agent skill from mehta-lab/VisCy.zattrs, or bulk-update Airtable records via MCP.
Airtable Register fits situations like: the user asks to register a dataset; register zarr positions; update airtable from zarr; write metadata to zarr.
Run `npx skills add mehta-lab/VisCy --skill airtable-register -a claude-code`. Or copy the skill folder (.claude/skills/airtable-register in mehta-lab/VisCy) into .claude/skills/airtable-register in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mehta-lab/VisCy --skill airtable-register -a codex`. Or copy the skill folder (.claude/skills/airtable-register in mehta-lab/VisCy) into .agents/skills/airtable-register in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mehta-lab/VisCy --skill airtable-register -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/airtable-register, .gemini/skills/airtable-register, .github/skills/airtable-register and .opencode/skills/airtable-register in your project.
Going by SKILL.md and its folder, Airtable Register needs the command-line tools its instructions call (uv) and credentials named AIRTABLE_API_KEY. Our summary lists: A credential in AIRTABLE_API_KEY.
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Airtable Register is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Airtable Register: Retentioneering Product Analytics (retentioneering/retentioneering-tools, 925 stars), Investigate Data (walkthru-earth/geocoding-playground, 153 stars), Downloading Batch Export Files (PostHog/posthog, 40k stars) and Setup Polar (chmonitor/chmonitor, 299 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mehta-lab (a GitHub organization) maintains it in mehta-lab/VisCy, which has 104 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 9, 2026.
Source: mehta-lab/VisCy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
