Agent skill

Trackplot

Generate sashimi-style genome visualization plots (coverage, line, heatmap, IGV read-by-read, HiC, circRNA, motif) from BAM/bigWig/depth/HiC inputs.

BSD-3-ClauseAuto-check passedResearch & Science

Install Trackplot

skills CLI

$ npx skills add ygidtu/trackplot --skill trackplot -a claude-code

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

GitHub CLI

$ gh skill install ygidtu/trackplot trackplot --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/ygidtu/trackplot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/trackplot .claude/skills/trackplot && 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/

Paste into Claude Code

Install the "trackplot" agent skill from https://github.com/ygidtu/trackplot/tree/main/skills/trackplot into .claude/skills/trackplot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trackplot", 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

$skill-installer install https://github.com/ygidtu/trackplot/tree/main/skills/trackplot

Type 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.

skills CLI

$ npx skills add ygidtu/trackplot --skill trackplot -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ygidtu/trackplot trackplot --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ygidtu/trackplot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/trackplot .agents/skills/trackplot && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "trackplot" agent skill from https://github.com/ygidtu/trackplot/tree/main/skills/trackplot into .agents/skills/trackplot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trackplot", 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.

skills CLI

$ npx skills add ygidtu/trackplot --skill trackplot -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ygidtu/trackplot trackplot --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ygidtu/trackplot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/trackplot .cursor/skills/trackplot && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "trackplot" agent skill from https://github.com/ygidtu/trackplot/tree/main/skills/trackplot into .cursor/skills/trackplot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trackplot", 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

$ gemini skills install https://github.com/ygidtu/trackplot.git --path skills/trackplot

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ygidtu/trackplot --skill trackplot -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ygidtu/trackplot trackplot --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ygidtu/trackplot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/trackplot .gemini/skills/trackplot && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "trackplot" agent skill from https://github.com/ygidtu/trackplot/tree/main/skills/trackplot into .gemini/skills/trackplot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trackplot", 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.

GitHub CLI

$ gh skill install ygidtu/trackplot trackplot

Installs 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).

skills CLI

$ npx skills add ygidtu/trackplot --skill trackplot -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ygidtu/trackplot.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/trackplot .github/skills/trackplot && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "trackplot" agent skill from https://github.com/ygidtu/trackplot/tree/main/skills/trackplot into .github/skills/trackplot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trackplot", 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.

skills CLI

$ npx skills add ygidtu/trackplot --skill trackplot -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ygidtu/trackplot trackplot --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ygidtu/trackplot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/trackplot .opencode/skills/trackplot && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "trackplot" agent skill from https://github.com/ygidtu/trackplot/tree/main/skills/trackplot into .opencode/skills/trackplot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trackplot", 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: trackplot
GitHub stars: 109
Token cost: ~1.9k tokens
SKILL.md length: 620 words
Files: 3 (incl. references)
Skills in repo: 1
Repo updated: Sep 26, 2026
First seen: Oct 7, 2026
Licence: BSD-3-Clause

At a glance

Generate sashimi-style genome visualization plots (coverage, line, heatmap, IGV read-by-read, HiC, circRNA, motif) from BAM/bigWig/depth/HiC inputs.

The user wants to plot NGS data over a genomic region
SKILL.md covers When to choose which track, Installation, Region format (required) and Common CLI workflow (density /…, plus 5 more sections
Calls pip, docker and conda
Intron-shrinkage plots

What it does

Trackplot is an agent skill from ygidtu/trackplot. Generate sashimi-style genome visualization plots (coverage, line, heatmap, IGV read-by-read, HiC, circRNA, motif) from BAM/bigWig/depth/HiC inputs. Use when the user wants to plot NGS data over a genomic region, make sashimi or intron-shrinkage plots, strand density, single-cell barcode-split density, protein domain tracks, or publish-ready PDF/PNG/SVG figures for a locus. Covers CLI usage, config TSV file formats, Docker, and the Python Plot chain API. Use when the user says trackplot, sashimi plot, coverage…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/config_files.md` and `references/python_api.md`).

It sits in Research & Science, covering Bioinformatics. It works with Python and Docker. The repository describes itself as: trackplot is a tool for visualizing various next-generation sequencing (NGS) data, including DNA-seq, RNA-seq, single-cell RNA-seq and full-length sequencing datasets. The licence is BSD-3-Clause.

When your agent uses it

The user wants to plot NGS data over a genomic region
Intron-shrinkage plots
Single-cell barcode-split density
Protein domain tracks

Example prompts

“/trackplot”

Requirements

Python 3
Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 56b69b1. 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:
- pip
- docker
- conda
- uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- trackplot.readthedocs.io
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

Trackplot loads about 1.9k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 149 tokens; SKILL.md has 620 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~149
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~4.2k

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 ygidtu/trackplot at commit 56b69b1, republished under its BSD-3-Clause licence (© ygidtu). 620 words, ~1,947 tokens.

Download SKILL.mdSave it as .claude/skills/trackplot/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: trackplot
description: Generate sashimi-style genome visualization plots (coverage, line, heatmap, IGV read-by-read, HiC, circRNA, motif) from BAM/bigWig/depth/HiC inputs. Use when the user wants to plot NGS data over a genomic region, make sashimi or intron-shrinkage plots, strand density, single-cell barcode-split density, protein domain tracks, or publish-ready PDF/PNG/SVG figures for a locus. Covers CLI usage, config TSV file formats, Docker, and the Python Plot chain API. Use when the user says trackplot, sashimi plot, coverage plot for a locus, or chr:start-end:strand plotting with bigWig or BAM.
license: BSD-3-Clause. LICENSE.txt has full terms.

trackplot

trackplot is a pure-Python (>=3.8) sashimi-plot / locus-visualization framework. It draws coverage, line, heatmap, individual-read (IGV), HiC, circRNA and motif tracks for a single genomic region, and emits journal-ready PDF/PNG/SVG. Input is given as tab-separated config files; output is one figure where each track maps to one config file.

Repo: https://github.com/ygidtu/trackplot · Docs: https://trackplot.readthedocs.io · DOI: 10.1371/journal.pcbi.1011477

When to choose which track

User wants	Use
Coverage/sashimi of BAM or bigWig over a locus (junctions shown)	`--density`
Multi-sample coverage as lines (time course, conditions)	`--line`
Several samples side-by-side coverage blocks	`--heatmap`
Individual aligned reads, incl. long-read m6A/polyA marks	`--igv`
2D contact matrix / HiC	`--hic`
Gene model, exon/intron, protein domains, custom beds	`-r` annotation + `--domain` / `--interval`
Circular RNA / back-splice highlight	`--density` + `--stroke` + `--link`

For config-file formats (exact columns) and the Python chain API, see references/config_files.md and references/python_api.md.

Installation

Fastest (Linux/macOS x86 with glibc):

bash

pip install trackplot                 # bigWig/bigBed/HiC support is optional, see below

Optional extras (enable formats that otherwise error out):

bash

pip install pybigwig hicmatrix        # bigWig, bigBed, and .hic / .h5

Other supported installs: bioconda (conda install -c bioconda -c conda-forge trackplot), source (pip install -e .), uv (uv sync), AppImage (Linux/WSL x86_64 only), Docker.

Platform caveats (from upstream docs):

Windows, Apple-Silicon macOS and other ARM hosts often cannot install via PyPI/conda because of pysam/pybigwig/hicmatrix wheels. Use the Docker image there.
If multi-processing causes segment fault, rerun with -p 1 or use Docker.
If you see Please install pyBigWig and hicmatrix, install the optional extras above.

bash

# Docker (recommended on macOS/ARM/Windows)
docker pull ygidtu/trackplot
docker run --rm -v $PWD:$PWD -w $PWD ygidtu/trackplot --help

Region format (required)

Every plot targets one region with -e:

chromosome_id:start:end:strand      e.g.  chr1:1270656-1284730:+

Strand is + or -. For strand-aware density use --density-by-strand.

Common CLI workflow (density / sashimi plot)

bash

trackplot \
  -e chr1:1270656-1284730:+ \
  -r example/example.sorted.gtf.gz \
  --density example/density_list.tsv \
  --show-junction-num \
  -o figure.pdf \
  --dpi 300 --width 10 --height 1 \
  -p 4

-r/--annotation: GTF/GFF (both transcript and exon tags must be present). Sorted + bgzipped+tabix is fine but not required.
--density / --line / --heatmap / --igv / --hic: each takes a config TSV path. Add as many different track types as needed in one invocation.
-o/--output: pdf, png, svg, jpg all supported. Journal PDF: use vector; for large heatmaps/sites pass --raster to shrink file size / speed up rendering.

Frequently used options

--show-junction-num / --show-mean-junction-num: annotate intron junction read counts.
-t/--threshold: drop low-abundance junctions (min count).
--show-site: draw read-start position (site) marks on the density.
--focus 100-200:300-400: highlight a region; --stroke a-b:c-d@color-label: bottom stroke line; --link a-b:c-d@color: bottom link between two sites; --sites 12,34,56: comma-separated indicator lines.
--intron-scale 0.5 / --exon-scale 1: shrink/expand introns (fixed introns: scale > 1).
--domain: add protein domain track from UniProt/Ensembl (needs network) or --local-domain <folder> (UCSC bigBed).
--interval <bed.tsv>: add custom feature track to the annotation.
--log [0|2|10|zscore]: log-transform the y axis. --normalize-format [count|cpm|rpkm]: normalize BAM.
--color-factor N: color by a categorical column of the config file (LUAD|red → label LUAD, color red).
--width/--height/--dpi/--backend/--font-size/--title/--font: output/figure styling.

Show full SKILL.md (230 more words)Show less

Single-cell BAM (barcode-split density/line)

Requires a barcode list and tags (10x default: --barcode-tag CB --umi-tag UB):

bash

trackplot \
  -e chr1:1270656-1284730:+ \
  -r example/example.sorted.gtf.gz \
  --density example/density_list.tsv \
  --barcode example/barcode_list.tsv \
  --group-by-cell \
  -o sc.pdf

Barcode list columns: bam barcode cell_type(optional) color(optional).

Config-file formats (tab-separated)

Header line starts with #; comment/blank lines ignored. Columns:

# density     # filepath  category   label(optional)  color(optional)
# line        # filepath  category   group(optional)  color(optional)
# heatmap     # filepath  category   group(optional)  color(optional)
# igv         # filepath  category   label(optional)  color(optional)
# hic         # filepath  category   label(optional)  color(optional)  transform(optional)  depth(optional)  domain(optional)
# interval    # file_location  label
# custom-junction  junctions  <bam-or-aliases...>   then   <junction-id>  <count-per-column...>

category is one of bam, bw, bed, depth, hic, igv, bed3/6/12, etc.
For bam in density/line/heatmap you may append library / total-read columns; see references/config_files.md for the full column table.

Docker usage notes

Absolute paths required inside the container. Convert relative config paths:

bash

grep -v '^#' example/density_list.tsv | while read l; do echo "$PWD/${l}"; done > abspath.tsv
docker run -v $PWD:$PWD -w $PWD --rm ygidtu/trackplot -e chr1:...:... --density abspath.tsv -o out.pdf

Mount your data dir with -v and set -w to it so paths match.

Web UI (optional)

Start a local server for a browser-based plot builder:

bash

trackplot --start-server --host 127.0.0.1 --port 5000 --plots ./plots     # --plots required for AppImage
# docker: docker run -v $PWD/example:/data -v $PWD/plots:/plots -p 5000:5000 ygidtu/trackplot --start-server --data /data --plots /plots

Region must match chromosome_id:start_site-end_site:strand.

Troubleshooting

#REF!-like import errors / pysam build issues → use Docker (see platform caveats).
Missing bigWig/HiC support → pip install pybigwig hicmatrix.
Protein domains missing in output → avoid Cairo backend for --domain; use Agg/PDF.
Slow PDF/SVG with heatmaps/sites → add --raster.
Want reproducibility / no shell escaping → prefer the Python chain API; see references/python_api.md.

Do not

Do not pass a region without strand; do not omit -r when junctions/annotation is expected.
Do not hardcode coverage values in Python then plot them — let trackplot read BAM/bigWig directly.
Do not expect vite build-style type checks here; this is a plotting tool, not a web framework.

Files

SKILL.md and 2 other files (references) in skills/trackplot of ygidtu/trackplot.

SKILL.md
references/config_files.md
references/python_api.md

Open the folder on GitHubat commit 56b69b1

Compare with similar skills

Trackplot 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.

Trackplot compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Trackplot this skillygidtu/trackplot	109	—	~1.9k	Automated safety check: Pass	BSD-3-Clause	11 days ago
Alphagenome Single Variant Analysisgoogle-deepmind/science-skills	3.2k	2 repos	~3k	Automated safety check: Notes	Apache-2.0	22 days ago
13C Metabolic Flux AnalysisK-Dense-AI/scientific-agent-skills	48k	1 repos	~3.2k	Automated safety check: Pass	MIT	2 days ago
Singlecell Qcxuzhougeng/wisp-science	1k	—	~1.6k	Automated safety check: Pass	AGPL-3.0	today
DiffDock Molecular DockingK-Dense-AI/scientific-agent-skills	48k	1 repos	~3k	Automated safety check: Notes	MIT	2 days ago
UniProt Database Accessdavila7/claude-code-templates	32k	15 repos	~1.7k	Automated safety check: Pass	MIT	today

Similar skills

Alphagenome Single Variant Analysis
google-deepmind/science-skills
Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.
3.2k GitHub starsUsed in 2 repos~3k tokens
Research & ScienceAuto-check: notes
13C Metabolic Flux Analysis
K-Dense-AI/scientific-agent-skills
Estimates reaction fluxes inside cells from steady-state carbon-13 labeling data with a bundled mfapy-based solver, and reports which fluxes the data pin down.
48k GitHub starsUsed in 1 repo~3.2k tokens
Research & ScienceAuto-check passed
Singlecell Qc
xuzhougeng/wisp-science
A skill your agent uses when designing, reviewing, or implementing single-cell RNA-seq QC in Python or R with a human-in-the-loop, data-driven approach.
1k GitHub stars~1.6k tokensUpdated today
Research & ScienceAuto-check passed
DiffDock Molecular Docking
K-Dense-AI/scientific-agent-skills
Predicts how small molecules bind to a protein with DiffDock, covering batch docking, pose ranking by confidence and checks on the results; not for binding affinity.
48k GitHub starsUsed in 1 repo~3k tokens
Research & ScienceAuto-check: notes
UniProt Database Access
davila7/claude-code-templates
Queries the UniProt REST API directly to search proteins, fetch FASTA sequences, map IDs between databases and read Swiss-Prot and TrEMBL entries.
32k GitHub starsUsed in 15 repos~1.7k tokens
Research & ScienceAuto-check passed
Spatial Transcriptomics
QING1105/ezST
End-to-end 10x Visium spatial transcriptomics analysis workflow with staged execution and human review gates.
101 GitHub stars~1.4k tokensUpdated 1 mo ago
Research & ScienceAuto-check passed

Works with

Questions about Trackplot

What does Trackplot do?

Generate sashimi-style genome visualization plots (coverage, line, heatmap, IGV read-by-read, HiC, circRNA, motif) from BAM/bigWig/depth/HiC inputs. Trackplot is an agent skill from ygidtu/trackplot. Generate sashimi-style genome visualization plots (coverage, line, heatmap, IGV read-by-read, HiC, circRNA, motif) from BAM/bigWig/depth/HiC inputs.

When should I use Trackplot?

Trackplot fits situations like: the user wants to plot NGS data over a genomic region; intron-shrinkage plots; single-cell barcode-split density; protein domain tracks.

How do I install Trackplot in Claude Code?

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

How do I install Trackplot in Codex?

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

Can I use Trackplot 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 ygidtu/trackplot --skill trackplot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/trackplot, .gemini/skills/trackplot, .github/skills/trackplot and .opencode/skills/trackplot in your project.

What does Trackplot need to run?

Going by SKILL.md and its folder, Trackplot needs the command-line tools its instructions call (pip, docker, conda and uv). Our summary lists: Python 3; Docker.

Does Trackplot access the network?

SKILL.md names 1 domain. As links in the text: trackplot.readthedocs.io. This is read from the text; nothing was executed.

Is Trackplot 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 Trackplot use?

Trackplot is published under the BSD-3-Clause licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Trackplot use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Trackplot?

Skills that share tags, products or a category with Trackplot: Alphagenome Single Variant Analysis (google-deepmind/science-skills, 3.2k stars), 13C Metabolic Flux Analysis (K-Dense-AI/scientific-agent-skills, 48k stars), Singlecell Qc (xuzhougeng/wisp-science, 1k stars) and DiffDock Molecular Docking (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Trackplot?

ygidtu (a GitHub user) maintains it in ygidtu/trackplot, which has 109 GitHub stars. The repository was last updated on September 26, 2026.

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

Install Trackplot

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

trackplot

When to choose which track

Installation

Region format (required)

Common CLI workflow (density / sashimi plot)

Frequently used options

Single-cell BAM (barcode-split density/line)

Config-file formats (tab-separated)

Docker usage notes

Web UI (optional)

Troubleshooting

Do not

Files

Compare with similar skills

Similar skills

Alphagenome Single Variant Analysis

13C Metabolic Flux Analysis

Singlecell Qc

DiffDock Molecular Docking

UniProt Database Access

Spatial Transcriptomics

Related

Questions about Trackplot