В каталоге 182 820 навыков в 14 категориях.
Einordnung von Wirtschaftstätigkeiten nach der Taxonomie-VO (EU) 2020/852 – Taxonomiefähigkeit und Taxonomiekonformität...
Complete Eureka V6.1 Context Engineering suite with observability, structured output, and hybrid memory
Audit an existing evaluation workflow and produce severity-ranked findings with concrete next actions. Use when inheriti...
Internal /ace:run step — Method reference for calibrating -eval rubrics against ground truth.
Traditional software metrics (accuracy, F1) fail to capture the quality of LLM outputs. Evaluation frameworks like Ragas...
Find AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark fa...
Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison betwee...
Write LLM-as-judge evaluator prompts for AI products. Use this skill whenever you need to evaluate semantic properties o...
Improves prompt, skill, or instruction text in scored rounds against locked eval cases, with a frozen grader hash, repli...
Design a scoring rubric and LLM-as-judge prompt to evaluate the quality of an AI feature's output. Use when asked to cre...
Guide for evaluation — inline evaluators, Inspect AI integration, and custom evaluators for measuring training progress....
Build and run evals for LLM and agent systems: golden datasets, LLM-as-a-judge with bias control, trajectory/step/outcom...
Measure model performance on test datasets. Use when assessing accuracy, precision, recall, and other metrics.
Evaluate one or more traces against an existing Truesight live evaluation. Use when a deployed live evaluation already e...
Scores whether a produced image satisfies the original natural-language instruction. Use after any capability Skill prod...
Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating...
Evaluate trained machine learning models with the right metrics and comparison logic. Use for benchmark review, threshol...
Use when evaluating AI model outputs, prompts, and LLM application quality in .NET. Covers Microsoft.Extensions.AI.Evalu...
Expert in temporal event detection, spatio-temporal clustering (ST-DBSCAN), and photo context understanding. Use for det...
The PyWry event system — namespaced events, request/response round-trips, widget IDs, component IDs, and how tool result...
Use when channel conversations must survive session death and /compact — SessionEnd + PreCompact hooks flush raw message...
Select the cache eviction algorithm that fits the workload's observed access distribution,
Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail.
Evidently AI skill for data drift detection, model performance monitoring, target drift analysis, and automated reportin...
EdgeVLA - Open-source edge vision-language-action model for robotics. Standardizes Open-X Embodiment datasets for consis...
Push the LLM to reconsider refine and improve its recent output. Use when the user asks for advanced elicitation.
analyst agent
architect agent
dev agent
evo-master agent
Orchestrate HITL triage of review findings using parallel agents. Use when the user says 'triage these findings' or 'run...
Review LLM workflow step prompts for known failure modes (silent ignoring, negation fragility, scope creep, etc). Use wh...
Orchestrates group discussions between all installed EVO agents, enabling natural multi-agent conversations. Use when us...
pm agent
qa agent
quick-flow-solo-dev agent
sm agent
tech-writer agent
ux-designer agent
Self-improving skill system for Pi Agent development. Features self-evolution (accumulate knowledge), self-correction (f...
将 .codex/evolution/signals.local.jsonl 或兼容旧队列中的纠偏信号整理成需要用户批准的 harness 演进提案。用于会话开始、用户反复纠正之后，或规则/技能显得陈旧、重复、缺失时。
Run autonomous improvement loops.
Population-based evolutionary search for code optimization. Maintains k candidates, evaluates against a fitness function...
Evolve instincts into skills and commands
Cluster related instincts and promote high-confidence ones to learned skills
프로젝트 변화를 감지하고 .claude 설정을 진화시킵니다. 새로운 의존성, 아키텍처 패턴 변경, 코드베이스 성장에 맞춰 rules와 context를 업데이트합니다. Use when project has change...
Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session hist...
Turn a repeated failure pattern into a system improvement. Outputs a concrete proposal for constraints, docs, or automat...
核心进化技能。在开发结束时调用，自动分析对话历史，将“项目进化资产”沉淀到 EVOLVE.md，并将平台特有的 AI 行为教训写入 CLAUDE.md / GEMINI.md / AGENTS.md / CURSOR.md，实现可审计、可复...
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution
View Self-Evolving Loop session status, history, and memory metrics
Use Exa AI for neural search, content retrieval, and automated deep research. Requires EXA_API_KEY.
Search the web with Exa AI — neural search, content extraction, similar page discovery, quick research with citations, a...
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find...
Wenn es um Examensprognose / JPA-Statistik in Jurastudium geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortma...
Examensvorbereitungs-Fragen für 1. und 2. Staatsexamen erstellen: Anwendungsfall Student will Examenswissen durch geziel...
直前の回答のうち分かりにくい箇所を、具体例を複数挙げて言い直す。効くのは打った1回だけ。人間が「具体例を挙げて」と頼み直す代わりに打つ。
Distributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DISTRIBUTE BY...
Execute or resume an approved kotgent structured plan using coordinated worker sessions, worktrees, independent review a...
EXECUTION PHASE - Run tasks via isolated subagents. Requires completed task DAG from plan phase.
Orchestrate an agent team to execute the user's task. Checks for agent teams support, presents pre-execution review, spa...
Execute a PLAN.md task by task as an orchestrator, dispatching each task, verifying its postcondition against observable...
Execute pending Claude Code Tasks in dependency order with wave-based concurrent execution and adaptive verification. Su...
A high-precision implementation mode for the Claude-type AI to execute the plan with zero errors.
Manage DAG execution lifecycles including start, stop, pause, resume, and cleanup. Activate on 'execution lifecycle', 's...
TDD-paired Gantt-style execution with compact waves. Each story gets tester agent (writes tests) BEFORE implementation a...
Expense Management (EXM) domain index - employee expense claims and their approvals, expense categories and policies, ex...
跑实验并记录 provenance：先写假设和成功判据，跑时记录 git hash、完整 resolved config 和 seed，跑完把结论写回 research-log.md 并标 [AI-DRAFT] 与 [source: run...
Habilidade inspirada no HKUDS OpenSpace para gerir "Security Experience Trips" e evoluir o conhecimento coletivo do SOC.
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight c...
You are a coding standards expert specializing in experiment configuration with hydra yaml.
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition...
Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track exp...
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted...
Meta-orchestration system that connects all Agent Experts for seamless workflow execution.
Expert-level guidance for creating high-quality Claude Code skills. Use alongside Anthropic's skill-creator when creatin...
Design YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, def...
/============================================================================/
Always explain your reasoning before making changes Use when configuring AI agent workflows and patterns. Agent Behavior...
Require the learner to explain a concept in their own words before the AI evaluates or extends it. Ensures the AI works...
See the main Model Explainability skill for comprehensive XAI coverage.
Make AI model decisions interpretable and transparent. Use for: implementing SHAP for feature importance analysis, using...
Turns a script into a narrated explainer ad staged on one constant background and cut as a single continuous camera jour...
Create high-quality animated explainer visuals for essays and blog posts. Use when the user wants to visualize concepts,...
Build this skill enables AI assistant to provide interpretability and explainability for machine learning models. it is...
Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one app...
RLM-style recursive memory exploration - dynamically navigate the memory graph
Navigate and understand codebase structure using the knowledge graph
Manual invocation only; use only when the user explicitly requests `explore-dnn-model` by name. Explore how to run a giv...
Discover and install useful Claude Code plugins for your project. Recommends based on your tech stack.