Agent skill

Retinal Mosaic Data

by isetbio in isetbio/isetbio

Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics.

MITAuto-check passedBackend & APIs

Install Retinal Mosaic Data

skills CLI
$ npx skills add isetbio/isetbio --skill retinal-mosaic-data -a claude-code

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

GitHub CLI
$ gh skill install isetbio/isetbio retinal-mosaic-data --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/isetbio/isetbio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/retinal-mosaic-data .claude/skills/retinal-mosaic-data && 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
retinal-mosaic-data
GitHub stars
115
Token cost
~1.5k tokens
SKILL.md length
655 words
Files
2
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics.

  • A task concerns files under data/datafiles/cones
  • SKILL.md covers Overview, Identify the Data Type Before…, Follow the Actual Construction… and Choose the Smallest Correct…, plus 1 more section
  • Calls rg
  • Data/datafiles/rgc/lattices

What it does

Retinal Mosaic Data is an agent skill from isetbio/isetbio. Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics. Use when a task concerns files under data/datafiles/cones, data/datafiles/rgc/lattices, ganglioncells/mosaics, mosaic-loading APIs, or cone-to-RGC connectivity.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Backend & APIs, covering Caching. The repository describes itself as: Tools for modeling image systems engineering in the human visual system front end. The licence is MIT.

When your agent uses it

  • A task concerns files under data/datafiles/cones
  • Data/datafiles/rgc/lattices
  • Ganglioncells/mosaics
  • Mosaic-loading APIs

Example prompts

  • “/retinal-mosaic-data”

What it can do on your machine

Read from SKILL.md and the folder at commit d2924c2. 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

    Shell commands in SKILL.md call:

    • rg

    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

Retinal Mosaic Data loads about 1.5k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 655 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 isetbio/isetbio at commit d2924c2, republished under its MIT licence (© isetbio). 655 words, ~1,473 tokens.

Download SKILL.mdSave it as .claude/skills/retinal-mosaic-data/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
retinal-mosaic-data
description
Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics. Use when a task concerns files under data/datafiles/cones, data/datafiles/rgc/lattices, ganglioncells/mosaics, mosaic-loading APIs, or cone-to-RGC connectivity.

Retinal Mosaic Data

Overview

Distinguish geometric source lattices from completed retinal circuit models. Preserve the established cMosaic and mRGCMosaic APIs while using “cone-to-RGC retinal circuit” for a model that includes both cells and their connectivity.

Identify the Data Type Before Editing a Loader

DataLocationContentsRole
Cone latticeSDR cone_lattices/; local gallery data/datafiles/cones/lattices/Retina-wide cone RF-center positionsCrop geometry used to construct a cMosaic. Resolved by retinalattice.import.sourceLatticeFile.
RGC latticeSDR mrgc_lattices/; local gallery data/datafiles/rgc/lattices/Retina-wide midget-RGC RF-center positionsCrop destination geometry used to generate an RGC mosaic. Same resolver.
Serialized cone mosaicSDR cone_mosaics/A local, complete cMosaicLoad through mosaicLoad for a precomputed cone realization.
Pre-baked RGC mosaicSDR mrgc_on_circuits/; local gallery ganglioncells/mosaics/ONmRGC/A local mRGCMosaic, its input cMosaic, and computed connectivity/model dataLoad through mRGCMosaic.loadPrebakedMosaic, which resolves via sdrPrebakedCircuitFile.
Compute-ready RGC mosaicExternal resource directory selected by getpref('isetbio').rgcResourcesA further prepared mRGCMosaic used by optimization workflowsLoad through loadComputeReadyRGCMosaic. Not part of the SDR deposit.

The four SDR collections are cached under data/sdr/isetbio-mosaics/, which Git ignores. The local galleries above are empty in a fresh checkout; a file generated locally into one of them takes precedence over the deposited copy. See sdr-mosaic-data for the deposit, cache, and legacy-filename contract, and docs/sdr-mosaic-data.md for the user-facing account.

Do not confuse “mosaic” in a filename with a completed circuit. A lattice contains positions, not cone types, cone–RGC wiring, receptive-field weights, or response gains. A pre-baked mRGCMosaic contains these circuit elements and its input cone mosaic.

Follow the Actual Construction Path

Use this dependency order when reasoning about synthesis:

text
cone lattice → cMosaic
RGC lattice  ─┘
                → cone-to-mRGC connectivity → mRGCMosaic circuit model

Key implementation points:

  • cMosaic normally crops a cone lattice in retinalattice.import.finalConePositions.
  • retinalattice.import.finalMRGCPositions crops an RGC lattice.
  • RGCMosaicConstructor.compute.componentsForRFcenterConnectivity accepts a supplied cMosaic, builds cone-to-RGC center connectivity with coneToMidgetRGCConnector, and returns the components used to instantiate mRGCMosaic('withComponents', components).
  • RGCMosaicConstructor.compute.centerConnectedMosaic is the usual high-level pipeline, but it creates its own compatible input cone mosaic; it is not a general public wrapper for a caller-supplied cMosaic.
  • mRGCMosaic is the established class name. Do not rename it merely because its instances model a circuit.

When building a workflow around an arbitrary cMosaic, validate compatible eye, retinal coordinate transforms, eccentricity/extent, and extra cone support for RGC surrounds. Do not reuse precomputed connectivity after changing the input cone positions or cone types.

Show full SKILL.md (282 more words)Show less

Choose the Smallest Correct Loader Change

  • Use mosaicLoad for the serialized cone-mosaic library. Its legacy parameter and filename calls select a manifest record and fetch it on demand; use mosaicLoad('list') to discover available cone mosaics. Do not overload the cMosaic constructor’s existing name parameter: it is a human-readable label, not a resource identifier.
  • Use mRGCMosaic.loadPrebakedMosaic for the pre-baked ON-mRGC circuit models. Preserve its parameter-to-filename convention and its cropping behavior. The filename it builds is the lookup key into the deposit, because the published circuit metadata lost the sign of the x eccentricity; do not switch to selecting by eccentricity and size.
  • Use mRGCMosaic.loadComputeReadyRGCMosaic only for the configured external compute-ready resource set; it currently relies on ISETBio preferences.
  • Keep the lattices available for any workflow that regenerates a mosaic. A pre-baked file cannot replace them as a general source of geometry.

For remote or on-demand data work, use ISETCam’s ieWebGet rather than adding another downloader. Keep public loaders and their cache paths stable; resolve or fetch an absent resource beneath them. Require a stable deposit path, filename, byte size, checksum, and data-format/version metadata before removing a bundled asset.

Inspect and Validate

  • Search all call sites before relocating data or changing a loader: rg -n "mosaicLoad|loadPrebakedMosaic|loadComputeReadyRGCMosaic|finalConePositions|finalMRGCPositions".
  • Inspect representative MAT-file variables before writing migration logic; do not infer content from filenames.
  • Update data-path tests if their contract deliberately changes. All four collections have been migrated, so a test must not assert that a bundled lattice or circuit exists on disk.
  • Validate both a first fetch/load and a cache-hit load, plus a clear error when the resource is unavailable. For circuit generation, verify dimensions and cone/RGC counts of the connectivity matrices as well as successful construction.

© isetbio, 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 in .github/skills/retinal-mosaic-data of isetbio/isetbio.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit d2924c2

Compare with similar skills

Retinal Mosaic Data 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.

Retinal Mosaic Data compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retinal Mosaic Data this skillisetbio/isetbio115—~1.5kAutomated safety check: PassMIT
Stripe Projectsfossasia/eventyay1.7k5 repos~2kAutomated safety check: NotesApache-2.0
FoundatioFoundatioFx/Foundatio2.1k—~3.9kAutomated safety check: PassApache-2.0
Wp Block Themesgambitph/Stackable3513 repos~985Automated safety check: PassGPL-3.0
Wp Performancegambitph/Stackable3513 repos~1.5kAutomated safety check: PassGPL-3.0
Effect Portable Patternsmillionco/expect3.6k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • Stripe Projects

    fossasia/eventyay

    A skill your agent uses when the user wants to provision infrastructure or third-party services using Stripe Projects.

    1.7k GitHub starsUsed in 5 repos~2k tokens
    Backend & APIsAuto-check: notes
  • Foundatio

    FoundatioFx/Foundatio

    A skill your agent uses when working with Foundatio infrastructure abstractions for .NET -- caching, queuing, messaging, file storage, distributed locking, or background jobs.

    2.1k GitHub stars~3.9k tokensUpdated today
    Backend & APIsAuto-check passed
  • Wp Block Themes

    gambitph/Stackable

    A skill your agent uses when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style…

    351 GitHub starsUsed in 3 repos~985 tokens
    Backend & APIsAuto-check passed
  • Wp Performance

    gambitph/Stackable

    A skill your agent uses when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers)…

    351 GitHub starsUsed in 3 repos~1.5k tokens
    Backend & APIsAuto-check passed
  • Effect Portable Patterns

    millionco/expect

    Portable Effect patterns for robust promise execution. An agent skill from millionco/expect.

    3.6k GitHub stars~3.7k tokensUpdated 5 mo ago
    Backend & APIsAuto-check passed
  • FastAPI-Redis SDK Development

    redis/fastapi-redis-sdk

    Official

    Guides development on the fastapi-redis-sdk library itself - its connection lifecycle, dependency-injected caching, and async/sync bridging.

    404 GitHub stars~2.5k tokensUpdated 7 days ago
    Backend & APIsAuto-check: notes

More from isetbio/isetbio

All 9 skills in this repo
  • Matlab Environment

    isetbio/isetbio

    Configure or troubleshoot a local MATLAB and VS Code environment for ISETBio.

    115 GitHub stars~558 tokensUpdated 13 days ago
    Auto-check passed
  • Matlab Evaluation

    isetbio/isetbio

    Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation.

    115 GitHub stars~568 tokensUpdated 13 days ago
    Auto-check passed
  • Matlab Testing

    isetbio/isetbio

    Develop, run, diagnose, or report ISETBio MATLAB tests. An agent skill from isetbio/isetbio.

    115 GitHub stars~884 tokensUpdated 13 days ago
    Auto-check passed
  • Create, move, review, publish, or test ISETBio tutorials, examples, and data-generation scripts.

    115 GitHub stars~560 tokensUpdated 13 days ago
    Auto-check passed
  • Sdr Mosaic Data

    isetbio/isetbio

    Create, publish, organize, or fetch the ISETBio retinal mosaic data deposit in the Stanford Digital Repository (SDR).

    115 GitHub stars~1.6k tokensUpdated 13 days ago
    Auto-check passed
  • Matlab Script Review

    isetbio/isetbio

    Review existing ISETBio MATLAB tutorial, example, or demo scripts without implementing behavior.

    115 GitHub stars~655 tokensUpdated 13 days ago
    Auto-check passed

Categories

Questions about Retinal Mosaic Data

What does Retinal Mosaic Data do?

Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics. Retinal Mosaic Data is an agent skill from isetbio/isetbio. Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics.

When should I use Retinal Mosaic Data?

Retinal Mosaic Data fits situations like: A task concerns files under data/datafiles/cones; data/datafiles/rgc/lattices; ganglioncells/mosaics; mosaic-loading APIs.

How do I install Retinal Mosaic Data in Claude Code?

Run `npx skills add isetbio/isetbio --skill retinal-mosaic-data -a claude-code`. Or copy the skill folder (.github/skills/retinal-mosaic-data in isetbio/isetbio) into .claude/skills/retinal-mosaic-data in your project. Claude Code loads it when a task matches its description.

How do I install Retinal Mosaic Data in Codex?

Run `npx skills add isetbio/isetbio --skill retinal-mosaic-data -a codex`. Or copy the skill folder (.github/skills/retinal-mosaic-data in isetbio/isetbio) into .agents/skills/retinal-mosaic-data in your project. Codex loads it when a task matches its description.

Can I use Retinal Mosaic Data 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 isetbio/isetbio --skill retinal-mosaic-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retinal-mosaic-data, .gemini/skills/retinal-mosaic-data, .github/skills/retinal-mosaic-data and .opencode/skills/retinal-mosaic-data in your project.

What does Retinal Mosaic Data need to run?

Going by SKILL.md and its folder, Retinal Mosaic Data needs the command-line tools its instructions call (rg).

Does Retinal Mosaic Data 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 Retinal Mosaic Data 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 Retinal Mosaic Data use?

Retinal Mosaic Data 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 Retinal Mosaic Data use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 Retinal Mosaic Data?

Skills that share tags, products or a category with Retinal Mosaic Data: Stripe Projects (fossasia/eventyay, 1.7k stars), Foundatio (FoundatioFx/Foundatio, 2.1k stars), Wp Block Themes (gambitph/Stackable, 351 stars) and Wp Performance (gambitph/Stackable, 351 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retinal Mosaic Data?

isetbio (a GitHub organization) maintains it in isetbio/isetbio, which has 115 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 25, 2026.

Source: isetbio/isetbio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.