Agent skill

Matchms

by aipoch in aipoch/medical-research-skills

Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows.

MITAuto-check passedData & Analytics

Install Matchms

skills CLI

$ npx skills add aipoch/medical-research-skills --skill matchms -a claude-code

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

GitHub CLI

$ gh skill install aipoch/medical-research-skills matchms --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/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'scientific-skills/Data Analysis/matchms' .claude/skills/matchms && 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 "matchms" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms into .claude/skills/matchms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matchms", 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/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms

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 aipoch/medical-research-skills --skill matchms -a codex

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

GitHub CLI

$ gh skill install aipoch/medical-research-skills matchms --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/'scientific-skills/Data Analysis/matchms' .agents/skills/matchms && 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 "matchms" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms into .agents/skills/matchms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matchms", 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 aipoch/medical-research-skills --skill matchms -a cursor

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

GitHub CLI

$ gh skill install aipoch/medical-research-skills matchms --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/'scientific-skills/Data Analysis/matchms' .cursor/skills/matchms && 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 "matchms" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms into .cursor/skills/matchms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matchms", 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/aipoch/medical-research-skills.git --path 'scientific-skills/Data Analysis/matchms'

--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 aipoch/medical-research-skills --skill matchms -a gemini-cli

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

GitHub CLI

$ gh skill install aipoch/medical-research-skills matchms --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/aipoch/medical-research-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/'scientific-skills/Data Analysis/matchms' .gemini/skills/matchms && 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 "matchms" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms into .gemini/skills/matchms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matchms", 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 aipoch/medical-research-skills matchms

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 aipoch/medical-research-skills --skill matchms -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/'scientific-skills/Data Analysis/matchms' .github/skills/matchms && 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 "matchms" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms into .github/skills/matchms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matchms", 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 aipoch/medical-research-skills --skill matchms -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 aipoch/medical-research-skills matchms --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/'scientific-skills/Data Analysis/matchms' .opencode/skills/matchms && 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 "matchms" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Data%20Analysis/matchms into .opencode/skills/matchms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matchms", 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: matchms
GitHub stars: 2k
Token cost: ~1.7k tokens
SKILL.md length: 688 words
Files: 6 (incl. scripts, references)
Skills in repo: 567
Repo updated: Sep 17, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows.

Works in 5 steps: When to Use → Key Features → Dependencies → …
You need reproducible spectral filtering and similarity scoring for metabolomics workflows
SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 6 more sections
Runs Python scripts from its folder; calls python

What it does

Matchms is an agent skill from aipoch/medical-research-skills. Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `matchms_audit_result_v1.json`, `references/filtering.md` and `references/similarity.md`).

It sits in Data & Analytics, covering Data analysis. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

You need reproducible spectral filtering and similarity scoring for metabolomics workflows
Tasks that involve Data analysis

Example prompts

“/matchms”

Requirements

Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

When to Use
Key Features
Dependencies
Example Usage
Implementation Details

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. 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
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

Matchms loads about 1.7k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 688 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~1.9k

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 aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 688 words, ~1,746 tokens.

Download SKILL.mdSave it as .claude/skills/matchms/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: matchms
description: Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows.
license: MIT
author: AIPOCH

Source: https://github.com/aipoch/medical-research-skills

Matchms Skill

When to Use

Use this skill when you need process, clean, and compare mass spectrometry (ms/ms) spectra with matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows in a reproducible workflow.
Use this skill when a data analytics task needs a packaged method instead of ad-hoc freeform output.
Use this skill when the user expects a concrete deliverable, validation step, or file-based result.
Use this skill when scripts/similarity_pipeline.py is the most direct path to complete the request.
Use this skill when you need the matchms package behavior rather than a generic answer.

Key Features

Scope-focused workflow aligned to: Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows.
Packaged executable path(s): scripts/similarity_pipeline.py.
Reference material available in references/ for task-specific guidance.
Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

Python: 3.10+. Repository baseline for current packaged skills.
Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.

Example Usage

bash

cd "20260316/scientific-skills/Data Analytics/matchms"
python -m py_compile scripts/similarity_pipeline.py
python scripts/similarity_pipeline.py --help

Example run plan:

Confirm the user input, output path, and any required config values.
Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
Run python scripts/similarity_pipeline.py with the validated inputs.
Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
Primary implementation surface: scripts/similarity_pipeline.py.
Reference guidance: references/ contains supporting rules, prompts, or checklists.
Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

1. When to Use

Use this skill when you need to:

Import and harmonize MS/MS spectra from common community formats (e.g., MGF/MSP) before analysis.
Clean spectra (peak filtering, intensity normalization) to improve downstream similarity scoring and identification.
Compute spectral similarity (Cosine/Modified Cosine/Fingerprint-based) for library matching or clustering.
Build reproducible, configurable processing pipelines for metabolomics projects.
Compare many spectra efficiently (all-vs-all or query-vs-library) and store/inspect score outputs.

2. Key Features

Import/Export support: Read spectra from mzML, mzXML, MGF, MSP, and JSON (depending on installed readers).
Filtering & harmonization: Metadata standardization, peak cleaning, intensity normalization, and other reusable filters.
Similarity scoring:
- Cosine similarity (Greedy/Hungarian variants)
- Modified Cosine (accounts for precursor mass shifts)
- Fingerprint-based similarities (when molecular fingerprints are available)
Pipeline composition: Chain filters and scoring steps into repeatable workflows.

Additional reference material (if present in the repository):

Filters: references/filtering.md
Similarity: references/similarity.md
Workflows: references/workflows.md

Show full SKILL.md (239 more words)Show less

3. Dependencies

matchms (version depends on your environment; pin in your project, e.g., matchms>=0.20,<1.0)
numpy (e.g., numpy>=1.20)
scipy (e.g., scipy>=1.7)
rdkit (optional; required for chemistry/fingerprint-related functionality, version varies by distribution)

4. Example Usage

A minimal, runnable example that loads spectra from an MGF file and computes pairwise cosine scores:

python

from matchms.importing import load_from_mgf
from matchms import calculate_scores
from matchms.similarity import CosineGreedy

def main():
    # Load spectra from an MGF file
    spectra = list(load_from_mgf("data.mgf"))

    # Compute similarity scores (all-vs-all)
    scores = calculate_scores(
        references=spectra,
        queries=spectra,
        similarity_function=CosineGreedy()
    )

    # Iterate over computed scores
    for (reference_idx, query_idx, score, n_matches) in scores:
        print(
            f"ref={reference_idx:>3} query={query_idx:>3} "
            f"cosine={score:.4f} matches={n_matches}"
        )

if __name__ == "__main__":
    main()

5. Implementation Details

Data model: Matchms operates on Spectrum objects containing peak m/z and intensity arrays plus metadata (e.g., precursor m/z, charge, compound name/identifier).
Filtering stage: Typical pipelines apply filters to:
- standardize/repair metadata fields,
- remove noise peaks (e.g., by intensity threshold or m/z window rules),
- normalize intensities (commonly to a maximum of 1.0 or to unit norm). See references/filtering.md for filter patterns and recommended sequences.
Cosine similarity (Greedy/Hungarian):
- Peaks are matched within an m/z tolerance (implementation-specific defaults; configure via the similarity class parameters).
- Greedy matching selects best available peak matches iteratively.
- Hungarian matching solves an assignment problem to maximize total match score under one-to-one constraints.
Modified Cosine:
- Extends cosine matching by allowing peak alignment with a precursor mass shift, improving matching for related compounds/adducts.
- Typically requires precursor m/z metadata to be present and consistent.
Fingerprint similarity (optional):
- Requires molecular fingerprints (often derived via RDKit) and compares spectra/compounds using fingerprint similarity metrics.
- Use when you have structure annotations or can compute fingerprints reliably.
Workflow reproducibility:
- Prefer explicit, ordered filter chains and pinned dependency versions.
- Store configuration (tolerances, normalization choices, filters used) alongside results for traceability. See references/workflows.md for pipeline organization guidance.

Files

SKILL.md and 5 other files (scripts, references) in scientific-skills/Data Analysis/matchms of aipoch/medical-research-skills.

SKILL.md
matchms_audit_result_v1.json
references/filtering.md
references/similarity.md
references/workflows.md
scripts/similarity_pipeline.py

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Matchms 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.

Matchms compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Matchms this skillaipoch/medical-research-skills	2k	—	~1.7k	Automated safety check: Pass	MIT	21 days ago
Exploratory Data Analysisspacering-net/codeg	3.8k	15 repos	~3.6k	Automated safety check: Pass	MIT	yesterday
Excel and CSV Data Analysisbytedance/deer-flow	83k	4 repos	~2.2k	Automated safety check: Pass	MIT	today
Exploratory Data AnalysisOleafly/Oleafly	206	3 repos	~3.4k	Automated safety check: Notes	MIT	today
Python Executorcortega26/chile-hub	113	2 repos	~1.5k	Automated safety check: Pass	MIT	today
Agentic Kaggle WorkflowFrankS-IntelLab/agentic-kaggle-skill	188	—	~4k	Automated safety check: Pass	MIT	3 mo ago

Similar skills

Exploratory Data Analysis
spacering-net/codeg
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.
3.8k GitHub starsUsed in 15 repos~3.6k tokens
Data & AnalyticsAuto-check passed
Excel and CSV Data Analysis
bytedance/deer-flow
Analyzes uploaded Excel and CSV files with SQL through DuckDB, producing schema inspections, statistical summaries and exports to CSV, JSON or Markdown.
83k GitHub starsUsed in 4 repos~2.2k tokens
Data & AnalyticsAuto-check passed
Exploratory Data Analysis
Oleafly/Oleafly
Perform bounded, local exploratory analysis of explicitly supported scientific files.
206 GitHub starsUsed in 3 repos~3.4k tokens
Data & AnalyticsAuto-check: notes
Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
113 GitHub starsUsed in 2 repos~1.5k tokens
Data & AnalyticsAuto-check passed
Agentic Kaggle Workflow
FrankS-IntelLab/agentic-kaggle-skill
Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.
188 GitHub stars~4k tokensUpdated 3 mo ago
Data & AnalyticsAuto-check passed
Yichen Wecom Local Vault
mcncarl/yichen-skills
Read, decrypt, query, search, and export local WeCom/企业微信 5.x desktop databases on macOS into a private read-only vault.
4.3k GitHub stars~1.3k tokensUpdated 4 days ago
Data & AnalyticsAuto-check passed

Questions about Matchms

What does Matchms do?

Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows. Matchms is an agent skill from aipoch/medical-research-skills. Process, clean, and compare mass spectrometry (MS/MS) spectra with Matchms; use when you need reproducible spectral filtering and similarity scoring for metabolomics workflows.

When should I use Matchms?

Matchms fits situations like: you need reproducible spectral filtering and similarity scoring for metabolomics workflows; tasks that involve Data analysis.

How do I install Matchms in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill matchms -a claude-code`. Or copy the skill folder (scientific-skills/Data Analysis/matchms in aipoch/medical-research-skills) into .claude/skills/matchms in your project. Claude Code loads it when a task matches its description.

How do I install Matchms in Codex?

Run `npx skills add aipoch/medical-research-skills --skill matchms -a codex`. Or copy the skill folder (scientific-skills/Data Analysis/matchms in aipoch/medical-research-skills) into .agents/skills/matchms in your project. Codex loads it when a task matches its description.

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

What does Matchms need to run?

Going by SKILL.md and its folder, Matchms needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Matchms 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 Matchms 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 Matchms use?

Matchms 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 Matchms use?

About 1.7k tokens (SKILL.md is roughly 7k 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 156 tokens, read only when the agent opens those files.

What are the alternatives to Matchms?

Skills that share tags, products or a category with Matchms: Exploratory Data Analysis (spacering-net/codeg, 3.8k stars), Excel and CSV Data Analysis (bytedance/deer-flow, 83k stars), Exploratory Data Analysis (Oleafly/Oleafly, 206 stars) and Python Executor (cortega26/chile-hub, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Matchms?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,974 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.

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

Install Matchms

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Matchms Skill

When to Use

Key Features

Dependencies

Example Usage

Implementation Details

1. When to Use

2. Key Features

3. Dependencies

4. Example Usage

5. Implementation Details

Files

Compare with similar skills

Similar skills

More from aipoch/medical-research-skills

Related

Questions about Matchms