指定薬剤・適応・国・データベース特性に基づき、PubMed/Web検索で先行RWD研究・RCT・ガイドラインを調査し、 エビデンスランドスケープを要約する。JMDC/MDV等クレームDBとの差別化観点を必ず含める。
Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.
Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail. — from general/agents-skills-meta
Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail. — from majiayu000/claude-skill-registry
Build, audit, and render evidence-dependence subgraphs from claim/premise/context data produced by LKM, Gaia, paper extraction, knowledge graphs, or manually supplied…
Orchestrates systematic reviews, scoping reviews, evidence maps, meta-analyses, umbrella reviews, and AI-assisted evidence synthesis.
Validates audit evidence artifacts for completeness, timeliness, relevance, and authenticity. Reviews screenshots, logs, configurations, and policies against control requirements.
Use when a claim you are checking turns on the contents of a spreadsheet (.xlsx/.xlsm/.csv) — what a cell's formula is, what it evaluates to, which cells a rollout changed, or…
Evidently AI skill for data drift detection, model performance monitoring, target drift analysis, and automated reporting for ML systems in production.
Evidenz: Internationaler Bezug und Schnittstellen: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung.
Bewertet die Qualitaet und Belastbarkeit der vorgelegten Belege fuer eine Marktabgrenzung: interne Unternehmensdokumente Kundenverhaltensdaten Marktdaten Elastizitaeten Diversion…
Diseñar y operar reportería, KPIs, auditoría y trazabilidad de EVINKA. Usar cuando haya que definir métricas operativas, construir vistas gerenciales, mapear entidades y eventos,…
Expert in Ethereum Virtual Machine internals - gas optimization, assembly/Yul, opcode-level optimization, and low-level EVM patternsUse when "evm, gas optimization, yul, inline…
Manage EVM wallets across Ethereum, Arbitrum, Base, Polygon, BSC, and Optimism. Check native and ERC20 token balances, transfer tokens, view transaction history, manage token…
Migrate a component from @ebay/ebayui-core (Marko 5) to @evo-web/marko (Marko 6). Receives the ebayui-core component name as the argument (e.g. /evo-migrate-marko ebay-button).
Review LLM workflow step prompts for known failure modes (silent ignoring, negation fragility, scope creep, etc).
Simulate evolutionary game dynamics — run replicator equations, compute fixation probabilities, visualize phase portraits and population trajectories, and analyze evolutionary…
Open the evo-agent-team dashboard in your default web browser. Detects the OS and uses the appropriate open command.
Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks about DNA/RNA/protein sequence likelihood, editing, design, or…
当用户搜索 EvoLink 替代、evolink.ai、模型路由、AI Gateway、fallback、多供应商聚合时使用。专门完成多模型路由策略：按成本、速度或成功率建立可解释路由和回退链，不把一个模型默认用于所有任务。输出任务分类、COST/SPEED/SUCCESS 路由矩阵、回退图和预算护栏，再用同一批非生产样本比较现有平台与…
Nova 자체를 진화시킬 때 사용한다. — MUST TRIGGER: /nova:evolve 호출, 외부 기술 동향을 Nova에 반영해야 할 때, Nova 메타-개선(규칙/스킬/훅 구조 변경) 작업.
Complete WhatsApp automation via Evolution API v2.3 - instances, messages (text/media/polls/lists/buttons/status), groups, labels, chatbots…
统一进化资产模型与自进化闭环核心。定义 Gene（策略 DNA）、Capsule（已验证经验快照）、 EvolutionEvent（追加式事件日志）三层资产模型，实现 Detect→Select→Replay→Validate→Solidify→Reuse 闭环，使 agent 遇到已知问题时先复用已验证经验，跳过重新试错。
面向 AI Agent 的自我进化引擎，直击"重复犯错、从沉默误学、记忆压缩丢失、进化无法衡量"四大痛点. 通过自反思机制、纠错学习、模式晋升机制，让 Agent 从每次交互中积累可复用经验，而非每次会话从零开始.
面向 AI Agent 的基础自我进化引擎，提供纠错学习与反污染防线两大核心能力. 用户明确纠正时记录到纠错日志，召回时优先注入，避免重复犯错. 反污染防线确保永不从沉默推断偏好，单次纠错不晋升永久规则. 基础分层记忆架构（热层加纠错层）降低 token 消耗. 适用于 AI 编程助手避免重复犯错、个人项目经验沉淀等轻量场景.
面向 AI Agent 的自我进化引擎，直击"重复犯错、从沉默误学、记忆压缩丢失、进化无法衡量"四大痛点。通过自反思、纠错学习、模式晋升机制，让 Agent 从每次交互中积累可复用经验，而非每次会话从零开始。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策.
Artibot Evolution Loop — conceptual guide to the continuous self-improvement cycle that drives GRPO-based learning, pattern extraction, skill refinement, and collective…
Cross-agent gene sharing protocol for exchanging validated evolution patterns between Claude sessions with trust downgrades and local revalidation.
OpenViking-style async self-evolution pipeline. After a session archive, worker classifies observations and writes them to `.agent/memory/{feedback,project,experiences}/`.
把 evolution-inbox 中的审计异常条目转化为可评审的进化提案（规则/技能/插件/路由补丁）。先做系统化问题分析（量化基线→全量聚合→根因分类→优先级排序），再用便宜模型起草、前沿模型评审、人工批准后走既有门禁固化。用于处理 evolution_scan.js 产出的异常条目、复盘高频反模式、把会话经验固化为规则或技能改进。不用于单轮小修改和…
Direct the evolutionary dynamics subdomain — route questions about evolutionary game theory, population dynamics, ESS, replicator dynamics, fitness landscapes, and biological or…
Evolutionary game theory foundations for understanding strategy evolution in populations. Reference when analyzing evolutionarily stable strategies, interpreting classical games…
Multi-objective evolutionary optimization for per-metric percentile cutoffs and intersection-based config selection.
Extract session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings).
Evoluciona una definición de agente existente refinando su persona en el lugar o creando una variante avanzada.
Turn recurring agent lessons, logs, and strategy tweaks into reviewable GEP evolution artifacts that can be applied across supported coding-agent runtimes.
Use after evolve-build has produced build-report.md. Validates the build via four parallel sub-auditors (eval-replay, lint, regression, build-quality) and produces ALL-PASS…
Population-based evolutionary search for code optimization. Maintains k candidates, evaluates against a fitness function, selects survivors, breeds new candidates via LLM mutation…
Run only the Execute phase — carry out a previously created improvement plan. Requires an existing plan.json.
Pre-Scout intent capture phase. Structures vague user goals into intent.md before any subagent budget is spent. Opt-in via EVOLVE_REQUIRE_INTENT=1.
Use after evolve-ship completes. Three sub-reflectors (instinct, gene, failure) run in parallel to extract lessons, update gene pool, and analyze any failures.
Mine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline.
Evoluciona una habilidad existente refinando su contenido en el lugar o creando una variante avanzada.
Evolve SKILL.md files from agent execution traces using a three-stage pipeline: trajectory collection from observed runs, parallel multi-agent patch proposal for error and success…
Use when starting a new evolve-loop cycle and the cycle goal is ambiguous or only described as a one-line objective.
Use when the plan-review verdict is PROCEED (or plan-review is disabled) and code has not yet been written. Writes RED tests first, defining the contract Builder must satisfy.
Entwickelt eine bestehende Teamzusammensetzung weiter, indem ihre Struktur direkt verfeinert oder eine spezialisierte Variante erstellt wird.
Self-iteration of system capabilities, error review and process optimization. A self-evolution engine that analyzes runtime history to identify improvements and applies…
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms.
Audit AI coding-agent configuration against current features and local
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution
Connect to the EvoMap collaborative evolution marketplace. Publish Gene+Capsule bundles, fetch promoted assets, claim bounty tasks, and earn credits via the GEP-A2A protocol.
Use evonest MCP tools to analyze, improve, and evolve a project — observe, plan, execute, verify. Triggers when the user asks to run evonest, analyze code, find improvements,…
Skill ecosystem evolution and automated skill improvement. Triggers on skill ecosystem management, skill quality analysis, and automated skill enhancement.
Create a Website in 4 Minutes Designed to Bring Clients from ChatGPT, Gemini & Modern Search — from satoshistackalotto/skills
Create a Website in 4 Minutes Designed to Bring Clients from ChatGPT, Gemini & Modern Search — from dvcrn/openclaw-skills-marketplace
Evrensel Finans Raporlama projesinin mimarisi, veri akışı, hesap eşleştirmeleri ve bilinen tuzakları hakkında uzman asistan. Kod yazarken bu kuralları uygular.
Run an NPI phase-gate review for EVT, DVT, or PVT — exit criteria per phase, open-issue triage, yield readout, waiver discipline, and a go/no-go call.
EV-Vollzug: Auslandszustellung einstweiliger Verfügungen im IP-Recht nach EuZustVO, HZÜ und HCCH 2019.
Für EV-Vollzug 001: Vollziehungsfrist und Parteizustellung (Paragraf 929 Abs. 2 ZPO): prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel.