[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DATREHABNAQE14KA6TVNKF":3,"skill-same:01M6DATREHABNAQE14KA6TVNKF":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DATREHABNAQE14KA6TVNKF","tooluniverse-neuroscience",null,"Neuroscience research and reasoning workflows using ToolUniverse tools. Covers computational neuroscience (rate models, integrate-and-fire neurons, synaptic plasticity, network dynamics), neuroanatomy (cortical regions, basal ganglia, cerebellum, brainstem, model organism connectomes), neurophysiology (ion channels, action potentials, synaptic transmission), neural circuits (E\u002FI balance, oscillations, central pattern generators), synaptic dynamics (STDP, short-term plasticity, neuromodulation), neurodegenerative diseases (Alzheimer's, Parkinson's, ALS, Huntington's), and clinical neurology (cranial nerves, stroke localization, neuromuscular disorders). Use when researchers ask about brain regions, neural computation, firing rates, synaptic plasticity, connectomics, neurodegeneration, or clinical neurological questions.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-neuroscience\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"tooluniverse neuroscience","neuroscience","models","clinical","computational","action potentials","brain","neurons","pattern","cerebellum","research","Neural","integrate","use","short","ask","model","network","reasoning","workflows","2026-11-10 10:12:30",false,"---\nname: tooluniverse-neuroscience\ndescription: Neuroscience research and reasoning workflows using ToolUniverse tools. Covers computational neuroscience (rate models, integrate-and-fire neurons, synaptic plasticity, network dynamics), neuroanatomy (cortical regions, basal ganglia, cerebellum, brainstem, model organism connectomes), neurophysiology (ion channels, action potentials, synaptic transmission), neural circuits (E\u002FI balance, oscillations, central pattern generators), synaptic dynamics (STDP, short-term plasticity, neuromodulation), neurodegenerative diseases (Alzheimer's, Parkinson's, ALS, Huntington's), and clinical neurology (cranial nerves, stroke localization, neuromuscular disorders). Use when researchers ask about brain regions, neural computation, firing rates, synaptic plasticity, connectomics, neurodegeneration, or clinical neurological questions.\n---\n\n# Neuroscience Research Skill\n\n**KEY PRINCIPLES**: LOOK UP, DON'T GUESS — use PubMed\u002FEuropePMC for neuroanatomy facts, WormBase for C. elegans connectome data, UniProt for neural protein properties. Verify claims with literature before answering. Use Python computation for quantitative neuroscience problems.\n\n---\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any neuroscience fact — brain region function, neural circuit connectivity, ion channel properties, neurotransmitter receptor subtypes — SEARCH databases first. A PubMed-verified answer is always more reliable than reasoning from memory. This is especially critical for neuroanatomy, where structures have precise boundaries and connectivity patterns that are easy to confuse.\n\n---\n\n## 1. Computational Neuroscience Reasoning\n\n### Rate-Based Models\n- Firing rate of a neuron: r = f(I - theta), where I = total synaptic input, theta = threshold, f = transfer function (sigmoid, ReLU, or threshold-linear)\n- Balanced excitation\u002Finhibition: in cortical networks, excitatory and inhibitory inputs are large but nearly cancel, leaving a small net drive\n- Population rate equations: tau * dr\u002Fdt = -r + f(W*r + I_ext), where W = connectivity matrix\n- Steady-state analysis: set dr\u002Fdt = 0, solve r = f(W*r + I_ext) — use fixed-point iteration or Newton's method\n\n### Integrate-and-Fire Neurons\n- Membrane voltage dynamics: tau_m * dV\u002Fdt = -(V - V_rest) + R_m * I(t)\n- When V reaches threshold V_th: emit spike, reset to V_reset, enter refractory period tau_ref\n- Firing rate for constant input: r = 1 \u002F (tau_ref + tau_m * ln((R_m*I - V_reset) \u002F (R_m*I - V_th))) [valid when R_m*I > V_th]\n- For sub-threshold input: neuron requires fluctuations (noise) to fire — noise-driven regime\n- Key variants: LIF (leaky), EIF (exponential), AdEx (adaptive exponential), Izhikevich (2D with recovery variable)\n\n### Synaptic Plasticity\n- **STDP** (Spike-Timing-Dependent Plasticity):\n  - Pre-before-post (positive dt): LTP (potentiation) — synapse strengthened\n  - Post-before-pre (negative dt): LTD (depression) — synapse weakened\n  - Window shape: typically exponential decay with tau_+ ~ 20ms (LTP) and tau_- ~ 20ms (LTD)\n- **Hebbian learning**: \"cells that fire together wire together\" — correlation-based; unstable without normalization\n- **BCM theory**: sliding threshold — low postsynaptic activity → LTD, high → LTP; threshold slides with average activity\n- **Homeostatic plasticity**: synaptic scaling adjusts all synapses multiplicatively to maintain target firing rate\n\n### Network Dynamics\n- **Mean-field theory**: replace individual neurons with population-averaged firing rates; self-consistency equation r = f(J*r*sqrt(K) + I_ext) where K = number of connections\n- **Balanced networks**: E\u002FI balance emerges when sqrt(K)*J ~ O(1); firing rate ~ (mu - theta) \u002F tau where mu = mean input, theta = threshold\n- **Chaos transition**: in random networks, chaos onset at g_c = 1 (gain parameter); above g_c, autocorrelation decays, Lyapunov exponent > 0\n- **Oscillations**: gamma (30-80 Hz) from E-I loops (PING model), theta (4-8 Hz) from slower inhibition or hippocampal circuits, alpha (8-12 Hz) from thalamo-cortical loops\n\n### Quantitative Problem-Solving Strategy\n1. Identify the model type (single neuron, network, plasticity rule)\n2. Write down the governing equations with all parameters\n3. **ALWAYS use Python** for multi-step calculations — do not attempt mental arithmetic\n4. Check units: voltages in mV, currents in nA or pA, time constants in ms, rates in Hz\n5. Sanity check: cortical firing rates are typically 1-20 Hz; tau_m ~ 10-20 ms; V_th ~ -50 mV\n\n---\n\n## 2. Neuroanatomy Reasoning\n\n### CRITICAL: Look Up Neuroanatomy\nBrain region functions, boundaries, and connectivity are precise anatomical facts. When asked about specific regions, nuclei, or tracts:\n1. Search PubMed or EuropePMC with specific anatomical terms\n2. For connectivity: search \"[region A] projection [region B]\" or \"[region] afferents efferents\"\n3. For function: search \"[region] lesion\" or \"[region] function review\"\n\n### Human Brain — Major Divisions\n- **Cerebral cortex**: frontal (motor, executive), parietal (somatosensory, spatial), temporal (auditory, memory), occipital (visual)\n- **Basal ganglia**: caudate + putamen (striatum) → GPi\u002FSNr (output) → thalamus; direct pathway (facilitate movement) vs indirect pathway (suppress movement); dopamine from SNc modulates both\n- **Cerebellum**: coordination, timing, motor learning; receives mossy fibers (pontine nuclei) and climbing fibers (inferior olive); Purkinje cells are sole output of cerebellar cortex\n- **Brainstem**: midbrain (superior\u002Finferior colliculi, substantia nigra, red nucleus), pons (pontine nuclei, respiratory centers), medulla (cardiovascular\u002Frespiratory centers, cranial nerve nuclei)\n- **Thalamus**: relay station — every sensory modality (except olfaction) synapses here before cortex; also receives cortical feedback (corticothalamic loops)\n- **Hippocampus**: declarative memory formation; trisynaptic circuit: EC → DG → CA3 → CA1 → EC; place cells, grid cells\n\n### Model Organism Neuroanatomy\n- **C. elegans**: 302 neurons, complete connectome mapped; use `WormBase_search` for gene expression, neuron identity, connectivity data\n- **Drosophila**: mushroom body (learning\u002Fmemory), antennal lobe (olfaction), central complex (navigation); ~100,000 neurons; FlyWire connectome\n- **Zebrafish**: transparent larvae for whole-brain imaging; Mauthner cells (escape response); use `Alliance_search_genes` for orthologs\n- **Mouse**: Allen Brain Atlas for gene expression; use PubMed for circuit tracing studies (rabies virus, optogenetics)\n\n### Reasoning Pattern for \"Where in the Brain?\" Questions\n1. Identify the function asked about (motor, sensory, memory, emotion, language)\n2. Map to candidate regions from general knowledge\n3. VERIFY with PubMed search: \"[function] brain region fMRI\" or \"[function] lesion study\"\n4. Check for lateralization (language → usually left hemisphere)\n5. Distinguish cortical vs subcortical involvement\n\n---\n\n## 3. Clinical Neurology Reasoning\n\n### Cranial Nerve Examination\n- Map symptom → nerve → nucleus → lesion site:\n  - CN I (olfactory): anosmia — cribriform plate fracture, frontal lobe lesion\n  - CN II (optic): visual field defects — optic nerve, chiasm, tract, radiation, cortex\n  - CN III (oculomotor): ptosis, \"down and out\" eye — midbrain, posterior communicating artery aneurysm\n  - CN IV (trochlear): difficulty looking down-and-in — dorsal midbrain\n  - CN V (trigeminal): facial sensation loss, jaw deviation — pons, Meckel's cave\n  - CN VI (abducens): medial strabismus — pons (long intracranial course, vulnerable to raised ICP)\n  - CN VII (facial): upper vs lower face weakness distinguishes UMN (forehead spared) vs LMN (all ipsilateral)\n  - CN VIII (vestibulocochlear): hearing loss, vertigo — peripheral vs central distinction critical\n  - CN IX-X (glossopharyngeal, vagus): dysphagia, uvula deviation\n  - CN XI (accessory): SCM and trapezius weakness\n  - CN XII (hypoglossal): tongue deviation toward lesion side\n\n### Stroke Localization\n- **Anterior circulation** (ICA, MCA, ACA): MCA → contralateral face\u002Farm > leg weakness, aphasia (dominant), neglect (non-dominant); ACA → contralateral leg > arm weakness\n- **Posterior circulation** (vertebrobasilar): brainstem signs (cranial nerve palsies + crossed signs), cerebellar ataxia, visual field defects\n- **Cortical vs subcortical**: cortical → higher function deficits (aphasia, neglect, agnosia); subcortical (lacunar) → pure motor\u002Fsensory without cortical signs\n- **Key rule**: crossed signs (ipsilateral face + contralateral body) = brainstem lesion\n\n### Upper vs Lower Motor Neuron\n| Feature | UMN Lesion | LMN Lesion |\n|---------|-----------|-----------|\n| Tone | Increased (spastic) | Decreased (flaccid) |\n| Reflexes | Hyperreflexia, Babinski+ | Hyporeflexia\u002Fareflexia |\n| Atrophy | Minimal (disuse) | Prominent, early |\n| Fasciculations | Absent | Present |\n| Distribution | Pyramidal pattern | Specific nerve\u002Froot |\n\n### Neurodegenerative Disease Patterns\n- **Alzheimer's**: amyloid plaques + tau tangles; hippocampus → entorhinal cortex → neocortex; episodic memory loss first\n- **Parkinson's**: alpha-synuclein in substantia nigra pars compacta; dopamine depletion → bradykinesia, rigidity, resting tremor; search `UniProt_search` for SNCA, LRRK2, PARK7\n- **ALS**: upper AND lower motor neuron signs; TDP-43 pathology; SOD1, C9orf72 genes\n- **Huntington's**: CAG repeat expansion in HTT; caudate atrophy; chorea, psychiatric symptoms, cognitive decline\n\n### Reasoning Pattern for Clinical Neuro Questions\n1. Localize the lesion: what neurological structure explains ALL the findings?\n2. Single lesion principle: prefer one lesion that explains everything over multiple lesions\n3. Determine mechanism: vascular (sudden onset), inflammatory (subacute), degenerative (gradual), neoplastic (progressive with mass effect)\n4. VERIFY with literature if uncertain about anatomy or presentation\n\n---\n\n## 4. Neurophysiology Reasoning\n\n### Action Potential\n- Resting potential ~ -70 mV (K+ equilibrium ≈ -90 mV, Na+ ≈ +60 mV, weighted by conductances)\n- Nernst equation: E_ion = (RT\u002FzF) * ln([ion]_out \u002F [ion]_in) ≈ 61.5\u002Fz * log10([out]\u002F[in]) mV at 37C\n- Goldman equation for resting potential: accounts for relative permeabilities of Na+, K+, Cl-\n- AP phases: depolarization (Na+ channels open) → overshoot → repolarization (K+ channels open, Na+ inactivate) → hyperpolarization (K+ channels slow to close)\n- Refractory periods: absolute (no stimulus can fire) ~ 1 ms; relative (stronger stimulus needed) ~ 2-4 ms\n\n### Synaptic Transmission\n- Chemical synapse: AP → Ca2+ entry (N-type, P\u002FQ-type channels) → vesicle fusion (SNARE complex) → neurotransmitter release → postsynaptic receptor binding\n- Excitatory: glutamate → AMPA (fast, Na+\u002FK+), NMDA (slow, Ca2+, voltage-dependent Mg2+ block)\n- Inhibitory: GABA → GABA_A (fast, Cl-), GABA_B (slow, K+, G-protein coupled); glycine in spinal cord\n- Neuromodulators: dopamine, serotonin, norepinephrine, acetylcholine — volume transmission, slower, alter circuit gain\n\n---\n\n## 5. Available Tools\n\n| Tool | Use For | Key Parameters |\n|------|---------|---------------|\n| `PubMed_search_articles` | Neuroanatomy facts, clinical neurology, circuit studies | `query`, `limit` |\n| `EuropePMC_search_articles` | Broader literature including preprints | `query`, `limit` |\n| `WormBase_search` | C. elegans neurons, connectome, gene expression | `query` |\n| `Alliance_search_genes` | Cross-species gene search (mouse, fly, fish, worm) | `query` |\n| `UniProt_search` | Neural proteins (ion channels, receptors, disease genes) | `query`, `organism` |\n| `proteins_api_search` | Protein features, domains, variants | `query` |\n| `NCBI_search_gene` | Gene info, orthologs, expression | `query` |\n| `ClinVar_search_variants` | Neurological disease variants | `gene`, `condition` |\n| `GWAS_search_associations` | Neurological trait associations | `query` |\n| `Orphanet_search_diseases` | Rare neurological diseases | `query` |\n| `KEGG_get_pathway` | Neural signaling pathways | `pathway_id` |\n| `OpenTargets_search_target` | Drug targets in neurological diseases | `query` |\n\n### Tool Selection Strategy\n1. **Neuroanatomy question**: PubMed first — search \"[structure] [function\u002Fconnectivity]\"\n2. **Ion channel \u002F receptor question**: UniProt — search protein name with organism\n3. **Disease gene question**: ClinVar + GWAS + Orphanet\n4. **Connectome \u002F circuit question**: WormBase (C. elegans), PubMed (other organisms)\n5. **Computational question**: Write Python code — do not guess numerical answers\n6. **Clinical neurology question**: PubMed + reasoning frameworks above; verify anatomy before answering\n\n---\n\n## 6. C. elegans Connectome Lookups\n\nFor C. elegans neural circuit questions, ALWAYS use `WormBase_search` to look up specific synapse and connectivity data. Do not guess neural connections from general knowledge.\n- **ASJ neuron projections**: the main projection target of ASJ axons is PVQ (verified in WormBase connectome data), NOT AIA. Always check actual synapse counts rather than inferring from circuit diagrams.\n- Search WormBase with the specific neuron name to get its pre\u002Fpostsynaptic partners and projection targets.\n\n## 7. Common Pitfalls\n\n- **Confusing brain regions**: The hippocampus is NOT in the frontal lobe. The substantia nigra is in the midbrain, NOT the basal ganglia (though functionally linked). Always verify.\n- **Mixing up neurotransmitter receptors**: GABA_A is ionotropic (Cl-), GABA_B is metabotropic (G-protein). NMDA requires both glutamate AND glycine\u002FD-serine co-agonist.\n- **Wrong units in computation**: Membrane time constants are in ms (not seconds). Firing rates are in Hz (spikes\u002Fs). Conductances are in nS or mS\u002Fcm2.\n- **Assuming all neurons fire fast**: Cortical neurons fire at 1-20 Hz on average; only specific cell types (e.g., fast-spiking interneurons) sustain >100 Hz.\n- **Ignoring lateralization**: Language is left-lateralized in ~95% of right-handers. Spatial attention is right-lateralized. Always consider which hemisphere.\n","# Neuroscience Research Skill\n\n**KEY PRINCIPLES**: LOOK UP, DON'T GUESS — use PubMed\u002FEuropePMC for neuroanatomy facts, WormBase for C. elegans connectome data, UniProt for neural protein properties. Verify claims with literature before answering. Use Python computation for quantitative neuroscience problems.\n\n---\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any neuroscience fact — brain region function, neural circuit connectivity, ion channel properties, neurotransmitter receptor subtypes — SEARCH databases first. A PubMed-verified answer is always more reliable than reasoning from memory. This is especially critical for neuroanatomy, where structures have precise boundaries and connectivity patterns that are easy to confuse.\n\n---\n\n## 1. Computational Neuroscience Reasoning\n\n### Rate-Based Models\n- Firing rate of a neuron: r = f(I - theta), where I = total synaptic input, theta = threshold, f = transfer function (sigmoid, ReLU, or threshold-linear)\n- Balanced excitation\u002Finhibition: in cortical networks, excitatory and inhibitory inputs are large but nearly cancel, leaving a small net drive\n- Population rate equations: tau * dr\u002Fdt = -r + f(W*r + I_ext), where W = connectivity matrix\n- Steady-state analysis: set dr\u002Fdt = 0, solve r = f(W*r + I_ext) — use fixed-point iteration or Newton's method\n\n### Integrate-and-Fire Neurons\n- Membrane voltage dynamics: tau_m * dV\u002Fdt = -(V - V_rest) + R_m * I(t)\n- When V reaches threshold V_th: emit spike, reset to V_reset, enter refractory period tau_ref\n- Firing rate for constant input: r = 1 \u002F (tau_ref + tau_m * ln((R_m*I - V_reset) \u002F (R_m*I - V_th))) [valid when R_m*I > V_th]\n- For sub-threshold input: neuron requires fluctuations (noise) to fire — noise-driven regime\n- Key variants: LIF (leaky), EIF (exponential), AdEx (adaptive exponential), Izhikevich (2D with recovery variable)\n\n### Synaptic Plasticity\n- **STDP** (Spike-Timing-Dependent Plasticity):\n  - Pre-before-post (positive dt): LTP (potentiation) — synapse strengthened\n  - Post-before-pre (negative dt): LTD (depression) — synapse weakened\n  - Window shape: typically exponential decay with tau_+ ~ 20ms (LTP) and tau_- ~ 20ms (LTD)\n- **Hebbian learning**: \"cells that fire together wire together\" — correlation-based; unstable without normalization\n- **BCM theory**: sliding threshold — low postsynaptic activity → LTD, high → LTP; threshold slides with average activity\n- **Homeostatic plasticity**: synaptic scaling adjusts all synapses multiplicatively to maintain target firing rate\n\n### Network Dynamics\n- **Mean-field theory**: replace individual neurons with population-averaged firing rates; self-consistency equation r = f(J*r*sqrt(K) + I_ext) where K = number of connections\n- **Balanced networks**: E\u002FI balance emerges when sqrt(K)*J ~ O(1); firing rate ~ (mu - theta) \u002F tau where mu = mean input, theta = threshold\n- **Chaos transition**: in random networks, chaos onset at g_c = 1 (gain parameter); above g_c, autocorrelation decays, Lyapunov exponent > 0\n- **Oscillations**: gamma (30-80 Hz) from E-I loops (PING model), theta (4-8 Hz) from slower inhibition or hippocampal circuits, alpha (8-12 Hz) from thalamo-cortical loops\n\n### Quantitative Problem-Solving Strategy\n1. Identify the model type (single neuron, network, plasticity rule)\n2. Write down the governing equations with all parameters\n3. **ALWAYS use Python** for multi-step calculations — do not attempt mental arithmetic\n4. Check units: voltages in mV, currents in nA or pA, time constants in ms, rates in Hz\n5. Sanity check: cortical firing rates are typically 1-20 Hz; tau_m ~ 10-20 ms; V_th ~ -50 mV\n\n---\n\n## 2. Neuroanatomy Reasoning\n\n### CRITICAL: Look Up Neuroanatomy\nBrain region functions, boundaries, and connectivity are precise anatomical facts. When asked about specific regions, nuclei, or tracts:\n1. Search PubMed or EuropePMC with specific anatomical terms\n2. For connectivity: search \"[region A] projection [region B]\" or \"[region] afferents efferents\"\n3. For function: search \"[region] lesion\" or \"[region] function review\"\n\n### Human Brain — Major Divisions\n- **Cerebral cortex**: frontal (motor, executive), parietal (somatosensory, spatial), temporal (auditory, memory), occipital (visual)\n- **Basal ganglia**: caudate + putamen (striatum) → GPi\u002FSNr (output) → thalamus; direct pathway (facilitate movement) vs indirect pathway (suppress movement); dopamine from SNc modulates both\n- **Cerebellum**: coordination, timing, motor learning; receives mossy fibers (pontine nuclei) and climbing fibers (inferior olive); Purkinje cells are sole output of cerebellar cortex\n- **Brainstem**: midbrain (superior\u002Finferior colliculi, substantia nigra, red nucleus), pons (pontine nuclei, respiratory centers), medulla (cardiovascular\u002Frespiratory centers, cranial nerve nuclei)\n- **Thalamus**: relay station — every sensory modality (except olfaction) synapses here before cortex; also receives cortical feedback (corticothalamic loops)\n- **Hippocampus**: declarative memory formation; trisynaptic circuit: EC → DG → CA3 → CA1 → EC; place cells, grid cells\n\n### Model Organism Neuroanatomy\n- **C. elegans**: 302 neurons, complete connectome mapped; use `WormBase_search` for gene expression, neuron identity, connectivity data\n- **Drosophila**: mushroom body (learning\u002Fmemory), antennal lobe (olfaction), central complex (navigation); ~100,000 neurons; FlyWire connectome\n- **Zebrafish**: transparent larvae for whole-brain imaging; Mauthner cells (escape response); use `Alliance_search_genes` for orthologs\n- **Mouse**: Allen Brain Atlas for gene expression; use PubMed for circuit tracing studies (rabies virus, optogenetics)\n\n### Reasoning Pattern for \"Where in the Brain?\" Questions\n1. Identify the function asked about (motor, sensory, memory, emotion, language)\n2. Map to candidate regions from general knowledge\n3. VERIFY with PubMed search: \"[function] brain region fMRI\" or \"[function] lesion study\"\n4. Check for lateralization (language → usually left hemisphere)\n5. Distinguish cortical vs subcortical involvement\n\n---\n\n## 3. Clinical Neurology Reasoning\n\n### Cranial Nerve Examination\n- Map symptom → nerve → nucleus → lesion site:\n  - CN I (olfactory): anosmia — cribriform plate fracture, frontal lobe lesion\n  - CN II (optic): visual field defects — optic nerve, chiasm, tract, radiation, cortex\n  - CN III (oculomotor): ptosis, \"down and out\" eye — midbrain, posterior communicating artery aneurysm\n  - CN IV (trochlear): difficulty looking down-and-in — dorsal midbrain\n  - CN V (trigeminal): facial sensation loss, jaw deviation — pons, Meckel's cave\n  - CN VI (abducens): medial strabismus — pons (long intracranial course, vulnerable to raised ICP)\n  - CN VII (facial): upper vs lower face weakness distinguishes UMN (forehead spared) vs LMN (all ipsilateral)\n  - CN VIII (vestibulocochlear): hearing loss, vertigo — peripheral vs central distinction critical\n  - CN IX-X (glossopharyngeal, vagus): dysphagia, uvula deviation\n  - CN XI (accessory): SCM and trapezius weakness\n  - CN XII (hypoglossal): tongue deviation toward lesion side\n\n### Stroke Localization\n- **Anterior circulation** (ICA, MCA, ACA): MCA → contralateral face\u002Farm > leg weakness, aphasia (dominant), neglect (non-dominant); ACA → contralateral leg > arm weakness\n- **Posterior circulation** (vertebrobasilar): brainstem signs (cranial nerve palsies + crossed signs), cerebellar ataxia, visual field defects\n- **Cortical vs subcortical**: cortical → higher function deficits (aphasia, neglect, agnosia); subcortical (lacunar) → pure motor\u002Fsensory without cortical signs\n- **Key rule**: crossed signs (ipsilateral face + contralateral body) = brainstem lesion\n\n### Upper vs Lower Motor Neuron\n| Feature | UMN Lesion | LMN Lesion |\n|---------|-----------|-----------|\n| Tone | Increased (spastic) | Decreased (flaccid) |\n| Reflexes | Hyperreflexia, Babinski+ | Hyporeflexia\u002Fareflexia |\n| Atrophy | Minimal (disuse) | Prominent, early |\n| Fasciculations | Absent | Present |\n| Distribution | Pyramidal pattern | Specific nerve\u002Froot |\n\n### Neurodegenerative Disease Patterns\n- **Alzheimer's**: amyloid plaques + tau tangles; hippocampus → entorhinal cortex → neocortex; episodic memory loss first\n- **Parkinson's**: alpha-synuclein in substantia nigra pars compacta; dopamine depletion → bradykinesia, rigidity, resting tremor; search `UniProt_search` for SNCA, LRRK2, PARK7\n- **ALS**: upper AND lower motor neuron signs; TDP-43 pathology; SOD1, C9orf72 genes\n- **Huntington's**: CAG repeat expansion in HTT; caudate atrophy; chorea, psychiatric symptoms, cognitive decline\n\n### Reasoning Pattern for Clinical Neuro Questions\n1. Localize the lesion: what neurological structure explains ALL the findings?\n2. Single lesion principle: prefer one lesion that explains everything over multiple lesions\n3. Determine mechanism: vascular (sudden onset), inflammatory (subacute), degenerative (gradual), neoplastic (progressive with mass effect)\n4. VERIFY with literature if uncertain about anatomy or presentation\n\n---\n\n## 4. Neurophysiology Reasoning\n\n### Action Potential\n- Resting potential ~ -70 mV (K+ equilibrium ≈ -90 mV, Na+ ≈ +60 mV, weighted by conductances)\n- Nernst equation: E_ion = (RT\u002FzF) * ln([ion]_out \u002F [ion]_in) ≈ 61.5\u002Fz * log10([out]\u002F[in]) mV at 37C\n- Goldman equation for resting potential: accounts for relative permeabilities of Na+, K+, Cl-\n- AP phases: depolarization (Na+ channels open) → overshoot → repolarization (K+ channels open, Na+ inactivate) → hyperpolarization (K+ channels slow to close)\n- Refractory periods: absolute (no stimulus can fire) ~ 1 ms; relative (stronger stimulus needed) ~ 2-4 ms\n\n### Synaptic Transmission\n- Chemical synapse: AP → Ca2+ entry (N-type, P\u002FQ-type channels) → vesicle fusion (SNARE complex) → neurotransmitter release → postsynaptic receptor binding\n- Excitatory: glutamate → AMPA (fast, Na+\u002FK+), NMDA (slow, Ca2+, voltage-dependent Mg2+ block)\n- Inhibitory: GABA → GABA_A (fast, Cl-), GABA_B (slow, K+, G-protein coupled); glycine in spinal cord\n- Neuromodulators: dopamine, serotonin, norepinephrine, acetylcholine — volume transmission, slower, alter circuit gain\n\n---\n\n## 5. Available Tools\n\n| Tool | Use For | Key Parameters |\n|------|---------|---------------|\n| `PubMed_search_articles` | Neuroanatomy facts, clinical neurology, circuit studies | `query`, `limit` |\n| `EuropePMC_search_articles` | Broader literature including preprints | `query`, `limit` |\n| `WormBase_search` | C. elegans neurons, connectome, gene expression | `query` |\n| `Alliance_search_genes` | Cross-species gene search (mouse, fly, fish, worm) | `query` |\n| `UniProt_search` | Neural proteins (ion channels, receptors, disease genes) | `query`, `organism` |\n| `proteins_api_search` | Protein features, domains, variants | `query` |\n| `NCBI_search_gene` | Gene info, orthologs, expression | `query` |\n| `ClinVar_search_variants` | Neurological disease variants | `gene`, `condition` |\n| `GWAS_search_associations` | Neurological trait associations | `query` |\n| `Orphanet_search_diseases` | Rare neurological diseases | `query` |\n| `KEGG_get_pathway` | Neural signaling pathways | `pathway_id` |\n| `OpenTargets_search_target` | Drug targets in neurological diseases | `query` |\n\n### Tool Selection Strategy\n1. **Neuroanatomy question**: PubMed first — search \"[structure] [function\u002Fconnectivity]\"\n2. **Ion channel \u002F receptor question**: UniProt — search protein name with organism\n3. **Disease gene question**: ClinVar + GWAS + Orphanet\n4. **Connectome \u002F circuit question**: WormBase (C. elegans), PubMed (other organisms)\n5. **Computational question**: Write Python code — do not guess numerical answers\n6. **Clinical neurology question**: PubMed + reasoning frameworks above; verify anatomy before answering\n\n---\n\n## 6. C. elegans Connectome Lookups\n\nFor C. elegans neural circuit questions, ALWAYS use `WormBase_search` to look up specific synapse and connectivity data. Do not guess neural connections from general knowledge.\n- **ASJ neuron projections**: the main projection target of ASJ axons is PVQ (verified in WormBase connectome data), NOT AIA. Always check actual synapse counts rather than inferring from circuit diagrams.\n- Search WormBase with the specific neuron name to get its pre\u002Fpostsynaptic partners and projection targets.\n\n## 7. Common Pitfalls\n\n- **Confusing brain regions**: The hippocampus is NOT in the frontal lobe. The substantia nigra is in the midbrain, NOT the basal ganglia (though functionally linked). Always verify.\n- **Mixing up neurotransmitter receptors**: GABA_A is ionotropic (Cl-), GABA_B is metabotropic (G-protein). NMDA requires both glutamate AND glycine\u002FD-serine co-agonist.\n- **Wrong units in computation**: Membrane time constants are in ms (not seconds). Firing rates are in Hz (spikes\u002Fs). Conductances are in nS or mS\u002Fcm2.\n- **Assuming all neurons fire fast**: Cortical neurons fire at 1-20 Hz on average; only specific cell types (e.g., fast-spiking interneurons) sustain >100 Hz.\n- **Ignoring lateralization**: Language is left-lateralized in ~95% of right-handers. Spatial attention is right-lateralized. Always consider which hemisphere.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-neuroscience","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-neuroscience",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-neuroscience",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-neuroscience","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-neuroscience\u002FSKILL.md",true,[],[70,91,120,147,161,177],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":44},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[77,78,79,80,81,82,83,84,85,37,86,87,88,89,90],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":100,"publishedAt":44},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[101,102,103,104,105,106,107,108,109,110,111,112,113,114,37,115,116,117,118,119],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":132,"publishedAt":44},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[133,134,135,136,137,138,139,140,141,142,102,143,144,145,146],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":44},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[149,154,155,156,157,158,159,160],"setup","report","project","installation","project setup","issues","state",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":44},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[167],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},[163,169,82,170,171,172,37,173,174,175,176],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":178,"name":154,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":44},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[154,156,117,183,158,184],"files","interactive"]