← Back to Skills Marketplace
Protein Phylogeny
by
Billwanttobetop
· GitHub ↗
· v1.5.0
· MIT-0
86
Downloads
0
Stars
0
Active Installs
9
Versions
Install in OpenClaw
/install protein-phylogeny
Description
Comprehensive protein family phylogenetic analysis workflow with quality control, conservation analysis, coevolution network analysis, and publication-ready...
Usage Guidance
This package mostly looks like a legit protein phylogeny workflow, but before installing or running it you should: (1) open and review scripts/install_dependencies.sh to confirm it installs packages from trusted sources (conda/bioconda, official GitHub releases) and does not download or execute arbitrary code from unknown servers; (2) verify that all helper scripts invoked by the shell scripts actually exist (the QC shell script references several Python helpers that are not visible in the manifest) — missing files could cause fallback behavior or indicate an incomplete package; (3) run the workflow in an isolated environment (container or VM) to limit impact if the install script is unsafe; (4) confirm any network activity (wget, API calls) is to expected bioinformatic services (UniProt, GitHub) and not to private/personal endpoints; and (5) if you need higher assurance, request the full contents of scripts/install_dependencies.sh and the referenced helper Python scripts (filter_by_evidence.py, filter_by_length.py, etc.) so they can be reviewed for unexpected behavior or data exfiltration.
Capability Analysis
Type: OpenClaw Skill
Name: protein-phylogeny
Version: 1.5.0
The skill bundle provides a comprehensive and scientifically plausible bioinformatics pipeline for protein analysis, but it is classified as suspicious due to high-risk capabilities and potential vulnerabilities. The installation script (scripts/install_dependencies.sh) performs high-privilege actions, including using sudo to install system binaries and downloading executable content from GitHub via wget. Additionally, several shell scripts, such as scripts/01_quality_control.sh, lack input sanitization for file paths, creating a risk for shell injection. While the bundle appears to be a legitimate tool with no clear evidence of malicious intent, these risky behaviors and the instruction in SKILL.md for the agent to skip reading the code warrant a cautious classification.
Capability Tags
Capability Assessment
Purpose & Capability
Name, description, high-level workflow and declared dependencies (CD-HIT, MAFFT, trimAl, IQ-TREE, Python, R) are coherent with a protein family phylogenetic analysis tool. The scripts and reference docs describe exactly the expected stages (QC, conservation, coevolution, phylogeny, visualization).
Instruction Scope
The SKILL.md and reference docs instruct the agent to run local scripts (bash scripts and a Python 'complete_analysis.py') which is appropriate. However several automation steps and scripts referenced in the docs (e.g., scripts/filter_by_evidence.py, scripts/filter_by_length.py, scripts/filter_complexity.py, scripts/validate_motifs.py, scripts/validate_final.py) are invoked by scripts/01_quality_control.sh and appear in documentation, yet those helper Python scripts are not present in the visible file manifest. This mismatch means the workflow may fail or hide where logic actually runs. The TESTING.md and other docs also include commands that fetch data from external endpoints (UniProt) — expected for this domain — but the instructions give the agent broad discretion to download and install tools without explicit safeguards.
Install Mechanism
There is no formal install spec for the skill (it is effectively instruction+scripts), which reduces automated risk but requires the user/agent to run scripts/install_dependencies.sh manually. That script's contents were not provided in the excerpts; an install script that installs binaries (or downloads binaries) can be high-risk if it pulls from untrusted URLs. The TESTING.md shows example installation commands that use conda/apt/GitHub releases (reasonable), but you should inspect scripts/install_dependencies.sh before running it.
Credentials
The skill requests no environment variables, credentials, or config paths. The dependencies and external endpoints referenced (UniProt, GitHub releases) are relevant to the stated purpose. No unrelated secrets or broad credential requests are present in the provided materials.
Persistence & Privilege
The skill does not request always:true and has no special persistence or system-wide privilege in the metadata. It is user-invocable and can be run manually; autonomous invocation is allowed (platform default) but not combined with other high-risk indicators here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install protein-phylogeny - After installation, invoke the skill by name or use
/protein-phylogeny - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.0
Complete R implementation for all analyses: conservation_analysis.R (8KB) - Shannon entropy + landscape plot, coevolution_analysis.R (6KB) - NMI + hub detection + MI distribution, plot_tree.R (7KB) - 6 tree layouts, analyze_bootstrap.R (7KB) - bootstrap analysis. Total 24 files, 276KB. Full trilingual coverage: Shell (workflow) + Python (fast analysis) + R (publication figures). Production-ready, zero proprietary data.
v1.4.0
Added complete R implementations: plot_tree.R (7KB) - 6 tree layouts (rectangular, circular, cladogram, unrooted), analyze_bootstrap.R (7KB) - bootstrap analysis and visualization. Total 22 files, 260KB. Complete trilingual implementation: Shell + Python + R. All algorithms validated, zero proprietary data, production-ready.
v1.3.1
Production-ready complete package: (1) Improved install_dependencies.sh with auto-detection and fallback installation. (2) Added TESTING.md with complete validation guide. (3) All 19 files included: 7 docs, 8 shell scripts, 2 Python scripts, 2 guides. Total 232KB. Tested workflow from fresh machine to publication-ready results. Zero proprietary data.
v1.3.0
Added complete Python implementations: complete_analysis.py (17KB) - production-ready code with all algorithms (Shannon entropy, NMI, hub detection, figure generation). Can be used standalone or via shell wrappers. Includes detailed README. Total: 216KB with full algorithm implementations validated on 10+ protein families.
v1.2.1
Security update: Removed all proprietary data and case-specific information. Generic examples only. Complete skill with: (1) 7 algorithm docs (75KB): Shannon entropy, NMI, ML phylogeny, visualization, report. (2) 8 executable scripts (52KB). (3) Full workflow from sequences to publication report. Production-ready, no proprietary information.
v1.2.0
Complete skill with all algorithms and executable scripts. Added: (1) Detailed algorithm docs (80KB): Shannon entropy, NMI, ML phylogeny, visualization, report generation. (2) Executable scripts (50KB): 02_conservation.sh, 03_coevolution.sh, 04_phylogeny.sh, 05_visualize.sh, 06_report.sh. (3) Complete workflow from raw sequences to publication-ready report. Total: 200KB, production-ready.
v1.1.0
Added detailed algorithm documentation: Shannon entropy (conservation), Normalized Mutual Information (coevolution), Maximum Likelihood phylogeny (IQ-TREE). Complete mathematical formulas, implementation code, biological interpretation, and visualization methods.
v1.0.1
v1.0.1: Removed dataset-specific numbers, made fully universal. Works with any protein family (enzymes, receptors, transporters, etc.). Tested on 10+ families with 50-5,000 sequences.
v1.0.0
Initial release: Complete workflow for protein family evolutionary analysis with quality control, conservation, coevolution, and phylogeny. Based on IRED family analysis (3,365 → 456 sequences). Includes 8-stage QC pipeline, publication-ready figures, and comprehensive reports.
Metadata
Frequently Asked Questions
What is Protein Phylogeny?
Comprehensive protein family phylogenetic analysis workflow with quality control, conservation analysis, coevolution network analysis, and publication-ready... It is an AI Agent Skill for Claude Code / OpenClaw, with 86 downloads so far.
How do I install Protein Phylogeny?
Run "/install protein-phylogeny" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Protein Phylogeny free?
Yes, Protein Phylogeny is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Protein Phylogeny support?
Protein Phylogeny is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Protein Phylogeny?
It is built and maintained by Billwanttobetop (@billwanttobetop); the current version is v1.5.0.
More Skills