Operate and maintain the local Symphony factory from this repository checkout. Use this skill when monitoring the live factory, repairing stalled runs, handling PR review and CI follow-up, or improving the operator loop itself.
Use at every gate checkpoint and periodically during experiments to verify that project progress matches the target venue's requirements in terms of experiment scale, novelty depth, and evidence quality
Use when core experiments or analyses are complete and results need to be organized into a coherent report for user review before paper writing
Iterative keep/discard experiment workflow over one explicitly configured repo, editable file, run command, and metric rule. Any agent may use it, but the `autoresearch` specialist is the default owner for sustained experiment-loop work.
Comprehensive collection of 128+ ready-to-use scientific skills for Claude enabling research across biology, chemistry, medicine, genomics, and advanced analysis domains.
Autonome Verbesserung nach dem Autoresearch-Paradigma (Karpathy). Zwei Modi: (1) Skill-Modus — optimiert eine SKILL.md durch iterative Mutation und Evaluation. (2) Generic-Modus — optimiert beliebige Dateien gegen jede mechanische Metrik (Testabdeckung, Bundle-Size, Lighthouse-Score, Docker-Image-Größe, etc.). Zwei Ausführungsmodi: Auto (vollautonomer Loop, ideal für Overnight-Runs) und Guided (interaktiv, User entscheidet bei jedem Schritt mit). Führt einen Experiment-Loop durch: analysieren → Hypothese bilden → mutieren → verifizieren → Score messen → keep/revert → wiederholen. Kann über Nacht als Scheduled Task laufen und liefert morgens einen Experiment-Report. IMMER verwenden bei: Skill autonom verbessern, Skill optimieren ohne manuelles Feedback, Skill optimieren mit Feedback, Autoresearch, autonomer Verbesserungsloop, Skill-Evolution, overnight optimization, Skill-Experiment, "lass den Skill über Nacht besser werden", Skill-Score verbessern, automatische Skill-Iteration, Code-Metrik verbessern, Testabd
Verify observability posture — audit monitoring coverage, find blind spots, prioritize gaps. Use when asked "is monitoring sufficient", "observability review", "are we covered", or "pre-launch monitoring check".
Testing reconnaissance — inventory all tests, frameworks, coverage, CI integration, and assess testing maturity for project takeover. Use when asked to "understand the tests", "testing assessment", "what's tested", or "test inventory".
Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".
Observability reconnaissance — inventory what monitoring exists, map coverage, highlight blind spots. Use when asked "what monitoring exists", "observability assessment", or "what can we see".
Write Verilog-A behavioral modules for analog/mixed-signal IC design (Cadence Virtuoso / Spectre). Covers 12 circuit categories. TRIGGER FIRST (before evas-sim) when the user needs to write or generate a new .va file. Key trigger phrases: "write", "create", "generate", "code", "implement" + "Verilog-A / veriloga / va / .va / behavioral model". Also triggers on: review/fix Verilog-A, "behavioral model", "veriloga", "analog HDL", circuit spec → behavioral model, "voltage-domain", "current-domain". Do NOT defer to evas-sim for authoring — evas-sim is for running an already-written file.
Observability reconnaissance — inventory what monitoring exists, map coverage, highlight blind spots. Use when asked "what monitoring exists", "observability assessment", or "what can we see".
Version, test, promote, and roll back prompts like production artifacts. Use when managing prompt lifecycle, prompt variants, few-shot changes, rubric alignment, baseline comparisons, and safe prompt release workflows across models or environments.
编排组合监控：集中度、相关性/风格暴露、流动性、情景压力等，整合成一份监控报告。当用户要求“全面诊断/持续监控我的组合”时使用。
Testing reconnaissance — inventory all tests, frameworks, coverage, CI integration, and assess testing maturity for project takeover. Use when asked to "understand the tests", "testing assessment", "what's tested", or "test inventory".
Verify observability posture — audit monitoring coverage, find blind spots, prioritize gaps. Use when asked "is monitoring sufficient", "observability review", "are we covered", or "pre-launch monitoring check".
Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional waves when gaps are identified, then synthesizes findings. Use when asked to research, investigate, compare options, find best practices, or gather comprehensive information from the web.\n\nThoroughness: quick for factual lookups | medium for focused topics | thorough for comparisons/evaluations (waves continue while critical gaps remain) | very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.
Multi-specialist collaborative analysis to understand how features, functions, or components work
MDOODZ governing equations and numerical methods — conservation of momentum (Stokes), energy, and mass, constitutive relations, non-dimensionalisation and scaling, marker-in-cell advection, free surface algorithm, pure shear ALE mode, and theoretical background.
Code-to-physics glossary for MDOODZ — variable names, struct fields, function names mapped to physical meaning, equations, SI units, grid naming conventions, creep mechanism abbreviations, and solver process stages.
MDOODZ mechanical anisotropy module — director-based fabric tracking, anisotropy factors (δ_n, δ_s), viscous transverse isotropy, ViscosityConciseAniso, finite strain evolution, anisotropic rifting methodology, and anisotropy scenario examples.
Analyzes datasets to extract insights, identify patterns, and create visualizations. This skill should be used when users want to explore data, perform statistical analysis, identify trends, or visualize patterns in structured data.
Metalearning skill that helps master any topic efficiently by identifying critical 20% material, building expert vocabulary, and creating research-backed learning roadmaps. Auto-trigger when user says "learn [topic]", "help me learn [topic]", "I want to learn [topic]", or asks for guidance on understanding a new subject. Supports comprehensive plans, interactive guidance, or minimalist just-in-time delivery.
Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.
