New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pacsomatic

by K-Dense-AI in K-Dense-AI/scientific-agent-skills

Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs.

MITAuto-check passedResearch & Science

Install Pacsomatic

skills CLI
$ npx skills add K-Dense-AI/scientific-agent-skills --skill pacsomatic -a claude-code

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

GitHub CLI
$ gh skill install K-Dense-AI/scientific-agent-skills pacsomatic --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/K-Dense-AI/scientific-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pacsomatic .claude/skills/pacsomatic && 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
pacsomatic
GitHub stars
48k
Used in
1 other repo
Token cost
~1.6k tokens
SKILL.md length
605 words
Files
7 (incl. scripts, references)
Skills in repo
153
Repo updated
First seen
Licence
MIT

At a glance

Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs.

  • Works in 7 steps: Obtain distinct tumor and normal BAM… → Confirm PacBio HiFi read groups and… → Generate artifacts with --dry-run. This… → …
  • Pacsomatic run preparation and execution
  • SKILL.md covers When to use, Workflow, Examples and Verification and references
  • Runs Python scripts from its folder; calls python and uv

What it does

Pacsomatic is an agent skill from K-Dense-AI/scientific-agent-skills. Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs. Supports samplesheet generation, pinned Nextflow launch artifacts, local checks, LSF/Slurm/PBS Pro/SGE launcher submission, and startup troubleshooting. Use for pacsomatic run preparation and execution, not general short-read somatic analysis or medical imaging PACS.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `config.yaml`, `references/agent-playbook.md` and `references/config-and-output.md`). Compatibility notes: Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow =24.04.2, a compatible Java runtime (current Nextflow supports Java…

It sits in Research & Science, covering Bioinformatics, Reproducible research and Clinical and healthcare research. It works with Nextflow. The repository describes itself as: Turn any AI agent into an AI Scientist. The 1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific… The licence is MIT.

When your agent uses it

  • Pacsomatic run preparation and execution
  • Not general short-read somatic analysis
  • Medical imaging PACS

Example prompts

  • “Use the pacsomatic skill to prepare and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs”
  • “/pacsomatic”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow >=24.04.2, a compatible Java runtime (current Nextflow supports Java 17-26), the selected container runtime and optionally a scheduler. Network access is needed for uncached pipeline code, plugins, references and containers.

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Obtain distinct tumor and normal BAM paths, patient ID, distinct sample IDs,
  2. Confirm PacBio HiFi read groups and sample identity from acquisition metadata;
  3. Generate artifacts with --dry-run. This performs helper checks and writes
  4. Review samplesheet, generated params YAML, script, pipeline revision, profiles,
  5. For execution, select the actual runtime with --use-current-path or an
  6. Use --run only for requested execution. For HPC, distinguish the outer
  7. Report artifact paths, revision, checks/warnings, run type, submission ID if

What it can do on your machine

Read from SKILL.md and the folder at commit 92ace75. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    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.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow >=24.04.2, a compatible Java runtime (current Nextflow supports Java 17-26), the selected container runtime and optionally a scheduler. Network access is needed for uncached pipeline code, plugins, references and containers.

    From compatibility in the SKILL.md frontmatter.

Context cost

Pacsomatic loads about 1.6k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 605 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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); the scripts in this folder are not scanned.

SKILL.md

The full file from K-Dense-AI/scientific-agent-skills at commit 92ace75, republished under its MIT licence (© K-Dense-AI). 605 words, ~1,620 tokens.

Download SKILL.mdSave it as .claude/skills/pacsomatic/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
pacsomatic
description
Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs. Supports samplesheet generation, pinned Nextflow launch artifacts, local checks, LSF/Slurm/PBS Pro/SGE launcher submission, and startup troubleshooting. Use for pacsomatic run preparation and execution, not general short-read somatic analysis or medical imaging PACS.
compatibility
Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow >=24.04.2, a compatible Java runtime (current Nextflow supports Java 17-26), the selected container runtime and optionally a scheduler. Network access is needed for uncached pipeline code, plugins, references and containers.
license
MIT
metadata.version
1.4
metadata.skill-author
Beifang Niu
metadata.contributors
Haidong, Wenchao
metadata.upstream-pipeline
https://github.com/nf-core/pacsomatic
metadata.upstream-revision
24c84cb371b0339c1d65a4de9451671945e19772
metadata.last-reviewed
2026-10-01

pacsomatic

When to use

Use scripts/run_pacsomatic.py to prepare one matched PacBio HiFi tumor/normal pair, generate a samplesheet and reproducible launch artifacts, and launch locally or submit the Nextflow driver to a scheduler. The pipeline realigns input BAMs; this helper targets unaligned HiFi BAMs and optional PacBio .pbi indexes. Do not substitute short reads or treat a BAM filename as evidence of platform, matched identity, or methylation information.

The reviewed upstream dev commit is 24c84cb371b0339c1d65a4de9451671945e19772. GitHub had no releases or tags on 2026-10-01, despite the internal manifest saying 1.0.0. The helper pins that commit by default for nf-core/pacsomatic; it does not invent a release tag. This is a source-reviewed development workflow, not a clinically validated assay. See references/pacsomatic_guide.md for sources and scientific checks.

Workflow

  1. Obtain distinct tumor and normal BAM paths, patient ID, distinct sample IDs, output directory, and exactly one reference mode: --fasta or --genome. IDs and BAM/PBI/FASTA paths must have no whitespace. Local inputs must be nonempty regular files. Remote BAM/PBI/FASTA URIs are passed through without downloading or authenticating; use managed filesystem/cloud credentials, never embed secrets or signed URLs in generated files.
  2. Confirm PacBio HiFi read groups and sample identity from acquisition metadata; confirm that MM/ML modification tags needed for methylation have been retained. Verify reference sequence/contig compatibility for every annotation resource.
  3. Generate artifacts with --dry-run. This performs helper checks and writes files, but does not invoke the pipeline, validate BAM contents, check remote availability, resolve every pipeline parameter, or verify biological suitability. Missing runtime tools are warnings here. --dry-run cannot be combined with --run/--submit, cloning, or environment creation.
  4. Review samplesheet, generated params YAML, script, pipeline revision, profiles, and branch-specific resources/skips. Existing artifacts require explicit --overwrite; input files can never be artifact targets. config.yaml is an operator reference, not an automatically loaded configuration file.
  5. For execution, select the actual runtime with --use-current-path or an existing --conda-env. Load cluster modules before invoking the helper; --module-load only repeats those commands in the generated script. No Conda YAML is bundled; creating an environment needs --conda-env-file explicitly.
  6. Use --run only for requested execution. For HPC, distinguish the outer launcher scheduler (--executor) from Nextflow's per-task process.executor, configured by a site profile or --nextflow-config. Driver CPU/memory requests do not constrain task resources. Read references/config-and-output.md.
  7. Report artifact paths, revision, checks/warnings, run type, submission ID if present, and a concrete next QC or failure-triage step. Scheduler acceptance is not pipeline completion. Keep the output directory and work/cache state stable for --resume; scripts run with the output directory as their cwd.
Show full SKILL.md (185 more words)Show less

Examples

Run these from the repository root. Paths and site settings are illustrative; local tests use synthetic placeholders only, not human genomic data.

bash
python skills/pacsomatic/scripts/run_pacsomatic.py \
  --tumor-bam /data/P001_T.bam --normal-bam /data/P001_N.bam \
  --patient-id P001 --tumor-sample-id P001_T --normal-sample-id P001_N \
  --outdir /results/P001 --fasta /refs/GRCh38.fa \
  --profile apptainer --use-current-path --dry-run

After reviewing artifacts, a Slurm launch can use the same inputs plus the following options (replace --dry-run with --run):

text
--executor slurm --queue compute --project my_account
--cpus 2 --memory-gb 8 --walltime 48:00
--nextflow-config /configs/slurm.config --overwrite --run

Those resources are for the driver, assuming the reviewed infrastructure config sets process.executor = 'slurm' and suitable task queue/resources. The helper normalizes 48:00 to Slurm 48:00:00 (48 hours). Do not add a sanger profile unless actually using that institution's LSF infrastructure.

Custom pipeline parameters go in --params-file; infrastructure goes in --nextflow-config (-c). The helper's explicit input/outdir/reference options win over params-file values. --extra-args is tokenized and shell-quoted, but cannot override these managed inputs/configuration options. Keep paths inside external params/config files absolute because the launcher cwd is the outdir.

Verification and references

bash
uv run skills-ref validate skills/pacsomatic
python tests/run_all.py --isolated pacsomatic

The standard-library suite checks local artifact behavior, path protections, CLI modes, runtime failures and mocked scheduler submissions. Native Nextflow checks use a tiny local workflow; they do not establish that pacsomatic's full containerized scientific pipeline succeeds on a given dataset or cluster.

© K-Dense-AI, 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 6 other files (scripts, references) in skills/pacsomatic of K-Dense-AI/scientific-agent-skills.

  • SKILL.md
  • LICENSE
  • config.yaml
  • references/agent-playbook.md
  • references/config-and-output.md
  • references/pacsomatic_guide.md
  • scripts/run_pacsomatic.py

Open the folder on GitHubat commit 92ace75

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in K-Dense-AI/scientific-agent-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Pacsomatic 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.

Pacsomatic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pacsomatic this skillK-Dense-AI/scientific-agent-skills48k1 repos~1.6kAutomated safety check: PassMIT
LaminDB Biological Data Managementdavila7/claude-code-templates33k12 repos~3.6kAutomated safety check: PassMIT
Latchbio Integrationdavila7/claude-code-templates33k11 repos~2.4kAutomated safety check: PassMIT
Repro EnforcerClawBio/ClawBio1.2k3 repos~413Automated safety check: PassMIT
Nfcore Rnaseq WrapperClawBio/ClawBio1.2k1 repos~8.9kAutomated safety check: PassMIT
Bio Workflow Management Cwl WorkflowsGPTomics/bioSkills1.2k1 repos~4.6kAutomated safety check: PassMIT

Similar skills

  • LaminDB Biological Data Management

    davila7/claude-code-templates

    Manages biological datasets with LaminDB: versioned artifacts, run lineage, ontology-based annotation, schema validation and links to workflow managers and ML tools.

    33k GitHub starsUsed in 12 repos~3.6k tokens
    Research & ScienceAuto-check passed

  • Latchbio Integration

    davila7/claude-code-templates

    Latch platform for bioinformatics workflows. An agent skill from davila7/claude-code-templates.

    33k GitHub starsUsed in 11 repos~2.4k tokens
    Research & ScienceAuto-check passed

  • Repro Enforcer

    ClawBio/ClawBio

    Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.

    1.2k GitHub starsUsed in 3 repos~413 tokens
    Research & ScienceAuto-check passed

  • Nfcore Rnaseq Wrapper

    ClawBio/ClawBio

    Wrapper skill for running nf-core/rnaseq bulk RNA-seq preprocessing from FASTQ or BAM inputs with strict preflight, reproducibility outputs, and downstream handoff to ClawBio bulk RNA-seq DE skills.

    1.2k GitHub starsUsed in 1 repo~8.9k tokens
    Research & ScienceAuto-check passed

  • Bio Workflow Management Cwl Workflows

    GPTomics/bioSkills

    Authors portable, strongly-typed bioinformatics pipelines in the Common Workflow Language (CWL v1.2) as CommandLineTool/Workflow/ExpressionTool documents, validated with cwltool and run at scale on…

    1.2k GitHub starsUsed in 1 repo~4.6k tokens
    Research & ScienceAuto-check passed

  • Bio Workflow Management Nf Core Pipelines

    GPTomics/bioSkills

    Runs and configures curated nf-core community Nextflow pipelines (rnaseq, sarek, atacseq, methylseq, ampliseq, taxprofiler, fetchngs) reproducibly, pinning the pipeline revision with -r and…

    1.2k GitHub starsUsed in 1 repo~4.1k tokens
    Research & ScienceAuto-check passed

More from K-Dense-AI/scientific-agent-skills

All 153 skills in this repo

  • 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
    Auto-check passed

  • Analytical Method Validation Planner

    K-Dense-AI/scientific-agent-skills

    Plans, runs, and documents analytical method validation, verification, or transfer studies under ICH Q2(R2)/Q14, USP, ICH M10, CLSI EP, or ISO/IEC 17025.

    48k GitHub starsUsed in 1 repo~4.9k tokens
    Auto-check: notes

  • Cantera Ignition Delay

    K-Dense-AI/scientific-agent-skills

    Runs Cantera constant-volume or constant-pressure ignition simulations and reports temperature-based ignition delay with mechanism provenance and checks.

    48k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-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
    Auto-check: notes

  • HypoGeniC Hypothesis Generation

    K-Dense-AI/scientific-agent-skills

    Plans and audits runs of the HypoGeniC and HypoRefine packages, which propose hypotheses from labeled text datasets, with local checks before any model call.

    48k GitHub starsUsed in 1 repo~3.6k tokens
    Auto-check: notes

  • ISO Standards Readiness Evidence

    K-Dense-AI/scientific-agent-skills

    Organizes scope, controlled documents, risk files and traceability into draft evidence for human review against ISO 13485, 14971, 17025 and 15189.

    48k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check: notes

Works with

Categories

Questions about Pacsomatic

What does Pacsomatic do?

Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs. Pacsomatic is an agent skill from K-Dense-AI/scientific-agent-skills. Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs.

When should I use Pacsomatic?

Pacsomatic fits situations like: pacsomatic run preparation and execution; not general short-read somatic analysis; medical imaging PACS.

How do I install Pacsomatic in Claude Code?

Run `npx skills add K-Dense-AI/scientific-agent-skills --skill pacsomatic -a claude-code`. Or copy the skill folder (skills/pacsomatic in K-Dense-AI/scientific-agent-skills) into .claude/skills/pacsomatic in your project. Claude Code loads it when a task matches its description.

How do I install Pacsomatic in Codex?

Run `npx skills add K-Dense-AI/scientific-agent-skills --skill pacsomatic -a codex`. Or copy the skill folder (skills/pacsomatic in K-Dense-AI/scientific-agent-skills) into .agents/skills/pacsomatic in your project. Codex loads it when a task matches its description.

Can I use Pacsomatic 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 K-Dense-AI/scientific-agent-skills --skill pacsomatic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pacsomatic, .gemini/skills/pacsomatic, .github/skills/pacsomatic and .opencode/skills/pacsomatic in your project.

What does Pacsomatic need to run?

Going by SKILL.md and its folder, Pacsomatic needs Python for the scripts in its folder and the command-line tools its instructions call (python and uv). Our summary lists: Python 3. Compatibility (from SKILL.md): Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow >=24.04.2, a compatible Java runtime (current Nextflow supports Java 17-26), the selected container runtime and optionally a scheduler. Network access is needed for uncached pipeline code, plugins, references and containers..

Does Pacsomatic access the network?

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.

Is Pacsomatic 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Pacsomatic use?

Pacsomatic is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pacsomatic use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Pacsomatic?

Skills that share tags, products or a category with Pacsomatic: LaminDB Biological Data Management (davila7/claude-code-templates, 33k stars), Latchbio Integration (davila7/claude-code-templates, 33k stars), Repro Enforcer (ClawBio/ClawBio, 1.2k stars) and Nfcore Rnaseq Wrapper (ClawBio/ClawBio, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pacsomatic?

K-Dense-AI (a GitHub organization) maintains it in K-Dense-AI/scientific-agent-skills, which has 48,215 GitHub stars. The repository holds 153 skills in this directory. The repository was last updated on October 5, 2026.

Source: K-Dense-AI/scientific-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.