agentsclimarketplace

Workflow configuration parsing

Skill HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/workflow-configuration-parsing

Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

Install
npx -y skills add HolobiomicsLab/asb-skill-collections --skill workflow-configuration-parsing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when you have a workflow.csv file co-located with sequence.csv in a SmartPeak session directory and need to load a default or custom workflow configuration into an executable command sequence.

The file declares its own license as CC-BY-4.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.6 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

workflow-configuration-parsing

Summary

Parse and validate a workflow configuration file (workflow.csv) to construct an ordered sequence of processing commands that SmartPeak will execute during session initialization. This skill bridges file-based workflow definition and downstream workflow execution.

When to use

You have a workflow.csv file co-located with sequence.csv in a SmartPeak session directory and need to load a default or custom workflow configuration into an executable command sequence. Apply this skill at session startup or when reconfiguring the processing pipeline without rebuilding the application.

When NOT to use

  • Workflow configuration is already loaded in memory as a command object or data structure; parsing is unnecessary.
  • You are modifying workflow steps interactively via SmartPeak GUI; use the GUI workflow editor instead of re-parsing the file.
  • The workflow.csv file is missing or the session directory is not accessible.

Inputs

  • workflow.csv file (text format, one workflow_step command per row)
  • session directory path (co-located with sequence.csv)

Outputs

  • ordered list of validated workflow command names
  • validation report (recognized vs. unrecognized commands)

How to apply

Read the workflow.csv file from the session directory row-by-row and extract the workflow_step command name from each row. Validate each extracted command against the known set of supported workflow commands (e.g., LOAD_RAW_DATA, MAP_CHROMATOGRAMS, EXTRACT_CHROMATOGRAM_WINDOWS, ZERO_CHROMATOGRAM_BASELINE, PICK_MRM_FEATURES, SELECT_FEATURES, STORE_FEATURES). Preserve the row sequence from the file as the execution order. Reject any unrecognized commands and report validation errors. Return the ordered command list for the downstream workflow executor to invoke each step sequentially. The parsing must maintain strict ordering because workflow steps have interdependencies (e.g., raw data must be loaded before chromatogram extraction).

Related tools

Evaluation signals

  • All rows in workflow.csv are successfully parsed and no commands are dropped or reordered.
  • Each extracted command matches one of the known supported workflow commands (validate against the supported set); any unrecognized command is flagged and rejected.
  • The output command list preserves row order exactly as it appears in the CSV file.
  • The workflow executor receives the ordered command list and invokes each step without errors or out-of-sequence execution.
  • Downstream steps (e.g., EXTRACT_CHROMATOGRAM_WINDOWS) succeed only if their prerequisites (e.g., LOAD_RAW_DATA, MAP_CHROMATOGRAMS) appear earlier in the parsed sequence.

Limitations

  • Parsing does not validate semantic correctness of the workflow (e.g., whether the chosen steps are suitable for the data type or experiment type); validation is lexical only.
  • The parser assumes workflow.csv is well-formed (correct delimiters, no malformed rows); handling of corrupted or non-standard CSV formatting is not specified.
  • No changelog or discussion of known parsing edge cases is provided in the source material, limiting guidance on failure modes or version compatibility.

Evidence

  • [other] Read the workflow.csv file from the session directory (co-located with sequence.csv): "Read the workflow.csv file from the session directory (co-located with sequence.csv). 2. Parse each row to extract the workflow_step command name."
  • [other] Validate each command against the known set of supported workflow commands (e.g., LOAD_RAW_DATA, MAP_CHROMATOGRAMS, EXTRACT_CHROMATOGRAM_WINDOWS, ZERO_CHROMATOGRAM_BASELINE, PICK_MRM_FEATURES, SELECT_FEATURES, STORE_FEATURES): "Validate each command against the known set of supported workflow commands (e.g., LOAD_RAW_DATA, MAP_CHROMATOGRAMS, EXTRACT_CHROMATOGRAM_WINDOWS, ZERO_CHROMATOGRAM_BASELINE, PICK_MRM_FEATURES,"
  • [other] Construct an ordered list preserving the row sequence from the file. 5. Return the ordered command list for downstream workflow executor: "Construct an ordered list preserving the row sequence from the file. 5. Return the ordered command list for downstream workflow executor to invoke each step in sequence."
  • [methods] SmartPeak automates processing through an ordered workflow that includes peak detection and integration, calibration curve optimization, and quality control reporting steps: "SmartPeak automates processing through an ordered workflow that includes peak detection and integration, calibration curve optimization, and quality control reporting steps."
  • [readme] Edit the workflow with Edit | Workflow. You have an option to cherry pick the custom workflow or to choose the predefined set of operations.: "Edit the workflow with Edit | Workflow. You have an option to cherry pick the custom workflow or to choose the predefined set of operations."

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.