Research 8-Ball: selects one of 20 classic Magic 8-Ball responses at random, logs (question + timestamp + response) to workspace/research-skill4455-last.json for Android sync. Auto-handles secure-sync. Trigger on "research-skill4455".
Research 8-Ball copy: selects and returns one of 20 classic responses at random, logs to workspace/research-skill-4455-last.json for syncing. Handles secure-sync setup. Use for "research-skill-4455" triggers.
ISO 13485 internal audit expertise for medical device QMS. Covers audit planning, execution, nonconformity classification, and CAPA verification. Use for internal audit planning, audit execution, finding classification, external audit preparation, or audit program management.
科学调试专家 - 观察(Observe) -> 假设(Hypothesize) -> 实验(Experiment) -> 修复(Fix)
Monitor and diagnose KarmaCadabra agent swarm health. Use this skill when the user asks to "check agents", "monitor swarm", "check logs", "are agents running", "agent health", "check heartbeats", "view agent status", "what are agents doing", "check IRC", "check balances", or any question about agent operational status. Also use proactively after deployments to verify agents are healthy, or when debugging agent behavior issues.
Test egress and DLP controls using synthetic canary data across authorized exfiltration channels.
Calculate the composition (concentration) of atom probe data. Handles range extraction, ion allocation, and concentration calculation. Use when the user asks about composition, concentration, or chemical analysis.
Laboratory automation toolkit for controlling liquid handlers, plate readers, pumps, heater shakers, incubators, centrifuges, and analytical equipment. Use this skill when automating laboratory workflows, programming liquid handling robots (Hamilton STAR, Opentrons OT-2, Tecan EVO), integrating lab equipment, managing deck layouts and resources (plates, tips, containers), reading plates, or creating reproducible laboratory protocols. Applicable for both simulated protocols and physical hardware control.
Orchestre un cycle complet validate-fix-validate sur le pipeline Argumentum, jusqu'a resolution ou limite d'iterations. Chef d'orchestre des corrections. Appelle pipeline-validate puis pipeline-fix en boucle.
Real-time serial log monitoring for ESP32 and microcontrollers. Capture device output to a file and monitor logs in real-time. Use when debugging embedded devices, investigating crashes, or monitoring device behavior.
Capture requirements, bugs, or issues from free-form input into structured, persistent artifacts. Use when user wants to record a work item quickly without deep validation.
Autonomously improve any skill prompt using a measure-change-test loop inspired by Karpathy's autoresearch. Runs the skill repeatedly, scores output against a yes/no checklist, makes one small change per round, keeps improvements, reverts regressions. Use when the user asks to "improve a skill", "optimize a skill", "autoimprove", "run autoresearch on a skill", or similar requests about iteratively improving skill quality.
Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
Autonomous experiment loop: edit code, commit, run benchmark, extract metrics, keep improvements or revert, repeat forever. Use this skill when the user asks to "run autoresearch", "start an experiment loop", "optimize a metric autonomously", "autonomous experiments", "autoresearch setup", "benchmark loop", "keep/discard experiments", "optimize test speed", "optimize bundle size", "optimize build time", "run experiments overnight", "speed up my tests", "make my build faster", "reduce compile time", "optimize this automatically", "keep trying until it's faster", "run experiments while I sleep", "overnight optimization", "edit-measure-keep loop", "cancel autoresearch", "stop autoresearch", "autoresearch status", "how many experiments", or mentions "autoresearch", "experiment loop", "autonomous optimization". Always use this skill when the user wants to iteratively and autonomously improve any measurable metric — even if they don't use the word "autoresearch". Also use when the user asks about the status of a ru
Control NGBS iCON Smart Home thermostats. Use when the user asks about home temperature, heating, thermostat control, or wants to adjust room temperatures.
蓝牙设备监控 / Bluetooth Device Monitor - 查看Mac已连接的蓝牙设备列表，支持配对、连接、断开操作
Code translation patterns for cross-language repository transpilation including dependency ordering, pattern mapping, confidence scoring, and behavioral equivalence validation. Use for converting codebases between languages, transpilation tasks, and translation confidence assessment.
Track baby sleep, feeding, diapers, and growth via the Huckleberry CLI. Use when the user asks about logging baby activities, starting/stopping sleep, bottle feeding, diaper changes, or growth measurements.
Experimaestro experiment manager best practices and conventions. Use when working with experimaestro tasks, configurations, experiments, launchers, or SLURM job scheduling. Helps write correct Config/Task classes, set up experiments, configure launchers, and follow framework patterns.
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
Search online 3D model repositories (Printables, MakerWorld, etc.), download models, slice with BambuStudio CLI, and send prints to Bambu Lab printers (A1 Mini, P1, etc.). Use when you want to find, prepare, and print 3D models without manual GUI interaction.
Implement an execution-ready plan, task list, and context file set. Keep changes aligned to the artifacts, and verify code, tests, docs, and memory updates before closing the task.
