segmasker
Bioinformatics tool to mask low-complexity regions in protein sequences.
Install
mkdir -p .claude/skills/segmasker && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12347" && unzip -o skill.zip -d .claude/skills/segmasker && rm skill.zipInstalls to .claude/skills/segmasker
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when identifying and masking low-complexity regions in protein sequences with the SEG algorithm before BLAST or other downstream analyses.Key capabilities
- →Mask low-complexity regions in protein sequences
- →Prepare sequences for `blastp` or `rpsblast`
- →Emit interval masks for downstream tools
- →Generate masked FASTA output
- →Tune SEG algorithm aggressiveness with window, locut, and hicut parameters
How it works
The skill uses the `segmasker` tool to apply the SEG algorithm to protein sequences, identifying and masking low-complexity regions based on specified parameters.
Inputs & outputs
When to use segmasker
- →Mask protein sequences
- →Prepare sequences for BLAST
- →Identify low-complexity regions
About this skill
segmasker
Quick Start
- Command:
segmasker - Local executable:
/home/vimalinx/miniforge3/envs/bio/bin/segmasker - Version: BLAST+ 2.17.0+
- Full reference: See
references/help.md
When To Use This Tool
- Mask low-complexity regions in protein sequences before
blastp,rpsblast, or related protein-domain searches. - Emit interval masks, masked FASTA, or ASN.1/XML mask metadata for downstream tooling.
- Prepare masking information from FASTA or an existing protein BLAST database.
- Prefer
dustmaskerfor nucleotide low-complexity masking.
Common Patterns
# 1) Produce interval-style SEG mask coordinates
segmasker \
-in proteins.fa \
-out proteins.seg.interval \
-outfmt interval
# 2) Emit masked FASTA for downstream protein BLAST
segmasker \
-in proteins.fa \
-out proteins.masked.fa \
-outfmt fasta
# 3) Tune SEG aggressiveness
segmasker \
-in proteins.fa \
-out proteins.masked.fa \
-outfmt fasta \
-window 12 \
-locut 2.2 \
-hicut 2.5
Recommended Workflow
- Decide whether downstream tools want coordinates, masked FASTA, or mask metadata.
- Run with default SEG parameters first; tune
-window,-locut, and-hicutonly if masking is obviously too weak or too strong. - Inspect the masked output before pushing it into alignment or search workflows.
- Keep the unmasked protein FASTA alongside the masked output for traceability.
Guardrails
segmaskeris the protein low-complexity masker; usedustmaskerfor nucleotide data.- The default output format is
interval, not FASTA. - There is no separate hard-masking switch here; choose the output format that your downstream tool expects.
- If FASTA identifiers matter downstream, consider
-parse_seqids.
When not to use it
- →When masking nucleotide low-complexity data
- →When the default output format of `interval` is not desired
- →When a separate hard-masking switch is expected
Limitations
- →It is for protein low-complexity masking, not nucleotide data
- →The default output format is `interval`
- →There is no separate hard-masking switch
How it compares
This skill provides a specialized tool for protein low-complexity masking with configurable parameters and various output formats, unlike generic sequence processing tools.
Compared to similar skills
segmasker side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| segmasker (this skill) | 0 | 4mo | Review | Intermediate |
| llm-evaluation | 6 | 2mo | No flags | Advanced |
| evaluating-llms-harness | 3 | 7mo | Review | Advanced |
| qutip | 4 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by vimalinx
View all by vimalinx →You might also like
llm-evaluation
wshobson
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
evaluating-llms-harness
davila7
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
qutip
davila7
Quantum mechanics simulations and analysis using QuTiP (Quantum Toolbox in Python). Use when working with quantum systems including: (1) quantum states (kets, bras, density matrices), (2) quantum operators and gates, (3) time evolution and dynamics (Schrödinger, master equations, Monte Carlo), (4) open quantum systems with dissipation, (5) quantum measurements and entanglement, (6) visualization (Bloch sphere, Wigner functions), (7) steady states and correlation functions, or (8) advanced methods (Floquet theory, HEOM, stochastic solvers). Handles both closed and open quantum systems across various domains including quantum optics, quantum computing, and condensed matter physics.
torchdrug
davila7
Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.
string-database
davila7
Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.
transformer-lens-interpretability
davila7
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.