fsl-tool
Use this skill whenever the user wants to process neuroimaging data with FSL (FMRIB Software Library), covering structural MRI, functional MRI (fMRI), and diffusion MRI (dMRI/DTI). Triggers include: 'use FSL', 'FSL processing', 'fsl_anat', 'FEAT', 'MELODIC', 'eddy', 'bedpostx', 'probtrackx', 'BET', 'FAST', 'FLIRT', 'FNIRT', 'run FSL pipeline'. This skill is the NeuroClaw interface-layer wrapper for FSL: checks installation, generates execution plan with concrete shell commands, waits for explicit confirmation, then routes all commands through claw-shell.
npx skills add BioTender-max/awesome-bio-agent-skills --skill fsl-tool --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# FSL Tool ## Overview FSL is a comprehensive library of analysis tools for MRI, fMRI, and diffusion brain imaging. This skill provides a safe, unified interface for the three core modalities in NeuroClaw: - Structural MRI (T1w, T2w, FLAIR) - Functional MRI (task-based and resting-state) - Diffusion MRI (DTI / dMRI) **Workflow**: 1. Check if FSL is installed (`fslversion`). 2. If not installed → call `dependency-planner` to generate installation plan. 3. Analyze input files and propose concrete shell commands with parameter explanations. 4. Present full numbered plan + estimated time + risks. 5. Wait for explicit user confirmation (“YES”, “execute”, “proceed”). 6. Execute all commands safely via `claw-shell`. 7. Summarize outputs and suggest next steps. **Research use only.** ## Core Modalities and Common Shell Commands ### 1. Structural MRI ```bash # One-click structural preprocessing (strongly recommended) fsl_anat -i T1w.nii.gz -o T1w_anat --clobber # -i : input T1w file # -o : output folder name # --clobber : overwrite existing files (commonly used) # Brain extraction (BET) bet T1w.nii.gz T1w_brain -m -f 0.5 # -m : output brain mask (_mask.nii.gz) # -f : brain extraction thresh
- Overview
- Core Modalities and Common Shell Commands
- 1. Structural MRI
- 2. Functional MRI
- 3. Diffusion MRI
- Quick Reference
- Installation
- Important Notes & Limitations
- When to Call This Skill
- Complementary / Related Skills
- More Advanced Features
- Post-Execution Verification (Harness Integration)
One-click structural preprocessing (strongly recommended) fsl_anat -i T1w.nii.gz -o T1w_anat --clobber Brain extraction (BET) bet T1w.nii.gz T1w_brain -m -f 0.5 Tissue segmentation + bias correction fast -t 1 -n 3 -H 0.1 -I 4 -l 20.0 -o T1w_fast T1w_brain Linear + nonlinear registration to MNI152 flirt -in T1w_brain -ref $FSLDIR/data/standard/MNI152_T1_2mm_brain -out T1w_to_MNI -omat T1w_to_MNI.mat -dof 12 fnirt --in=T1w_brain --aff=T1w_to_MNI.mat --cout=T1w_to_MNI_warp --config=T1_2_MNI152_2mm Subcortical segmentation
What does the fsl-tool skill do?
Use this skill whenever the user wants to process neuroimaging data with FSL (FMRIB Software Library), covering structural MRI, functional MRI (fMRI), and diffusion MRI (dMRI/DTI). Triggers include: 'use FSL', 'FSL processing', 'fsl_anat', 'FEAT', 'MELODIC', 'eddy', 'bedpostx', 'probtrackx', 'BET', 'FAST', 'FLIRT', 'FNIRT', 'run FSL pipeline'. This skill is the NeuroClaw interface-layer wrapper for FSL: checks installation, generates execution plan with concrete shell commands, waits for explicit confirmation, then routes all commands through claw-shell.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill fsl-tool --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
