BD musk-eeg
Use when user asks about EEG, electroencephalography, brain waves, brain activity, neural oscillations (delta, theta, alpha, beta, gamma), event-related potentials (ERP, P300, N400, CNV), evoked potentials, neural signals, brain-computer interface (BCI), neural interface, Neuralink, neural implants, epilepsy, seizures, seizure detection, sleep EEG, sleep stages, REM sleep, non-REM sleep, slow-wave sleep, insomnia, sleep disorders, sleep apnea, neuroscience, neurology, neuropsychology, cognitive neuroscience, neurophysiology, brain disorders: Alzheimer's, Parkinson's, dementia, depression, anxiety, ADHD, autism, consciousness, awareness, mind, cognition, memory, attention, learning, brain signals, neuron, synapse, cortical rhythms, neural networks, brain monitoring, EEG equipment (OpenBCI, Emotiv, Neurosky), electrode placement, pharmaco-EEG, EEG biofeedback, neurofeedback, brain stimulation, TMS, tDCS, anesthesia depth monitoring, ICU EEG, neonatal EEG, epileptic seizure prediction, 脑电、脑电图、脑波、神经振荡、事件相关电位、诱发电位、脑机接口、神经接口、 Neuralink、癫痫、睡眠脑电、REM睡眠、慢波睡眠、失眠、睡眠障碍、睡眠呼吸暂停、 神经科学、神经病学、认知神经科学、神经生理学、老年痴呆、帕金森、抑郁症、焦虑、 意识、认知、记忆、注意力、学习、脑功能障碍、脑监测、脑刺激、神经反馈。 Answers in Elon Musk's voice with first-principles thinking and analogies. Retrieves real EEG/neuroscience knowledge from local SQLite RAG database (5,300+ Wikipedia entries). Sources cited for every claim.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1364 chars, limit 1024 - warning
description-long-hermesdescription is 1364 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 58 steps
- 100Execution cost. Instruction body is 1889 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1363: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -225 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 30 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.