Use when generating elite GSAP-heavy frontend pages with strict AIDA structure, wide hero typography, and gapless bento grids.

Use when designing expensive agency-grade interfaces with premium fonts, spatial rhythm, soft depth, and fluid microinteractions.

High-level technical SEO and site architecture auditor. Invoke to scan local or live environments for indexing, crawl budget, and structural errors.

Use when creating raw industrial or tactical telemetry UIs with rigid grids, stark typography, CRT effects, and high-density data.

Expert in LangGraph - the production-grade framework for building

Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.

Expert guide for configuring Odoo Accounting: chart of accounts, journals, fiscal positions, taxes, payment terms, and bank reconciliation.

Expert in Odoo access control: ir.model.access.csv, record rules (ir.rule), groups, and multi-company security patterns.

>

Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules.

Codified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier quality management in regulated manufacturing.

This skill should be used when the user asks for patterns, best practices, creation, or fixing of Sankhya dashboards using HTML, JSP, Java, and SQL.

Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples.

Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.

Automate Snowflake data warehouse operations -- list databases, schemas, and tables, execute SQL statements, and manage data workflows via the Composio MCP integration.

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.

Operations management and lean production techniques for turning inputs into outputs under variability. Covers the Toyota Production System, seven wastes, just-in-time, kanban, jidoka, single-minute die exchange, 5 Whys, value stream mapping, bottleneck theory, and the distinction between mass production and flexible production. Use when diagnosing operational waste, designing production flows, setting up quality systems, or comparing batch-and-queue to one-piece flow.

Algorithms and data structures from first principles through advanced analysis. Covers sorting (bubble, insertion, selection, merge, quick, heap, radix), searching (linear, binary, BFS, DFS, Dijkstra, A*), fundamental data structures (arrays, linked lists, stacks, queues, hash tables, trees, heaps, graphs, tries), complexity analysis (Big-O, Big-Omega, Big-Theta, amortized), recurrence relations, and algorithm design paradigms (divide-and-conquer, greedy, dynamic programming, backtracking). Use when analyzing, selecting, implementing, or comparing algorithms and data structures.

Supervised and unsupervised learning, bias-variance tradeoff, cross-validation, decision trees, ensemble methods, neural network fundamentals, and the practitioner's workflow from problem framing through deployment. Covers classification, regression, clustering, dimensionality reduction, regularization, hyperparameter tuning, and evaluation metrics. Use when building predictive models, selecting algorithms, or understanding the machine learning pipeline.

Climate physics, forcing, feedback, and attribution. Covers the greenhouse effect and radiative forcing, climate sensitivity, fast and slow feedbacks, the paleoclimate record, detection and attribution science, regional climate impacts, and the distinction between weather, climate variability, and forced climate change. Use when reasoning about global warming mechanisms, interpreting temperature or CO2 records, evaluating attribution claims for extreme events, or distinguishing signal from natural variability.

Persist progress for long-running jobs (batched LLM calls, large ingestions, multi-hour syncs) so that a context reset, crash, or interrupt doesn't lose work. Use whenever a job iterates over N items and completing item K matters independently. Provides a resumable.mjs library pattern plus the skill's invocation heuristics.

Schools of historical thought, methodology debates, and the philosophy of history. Covers the major historiographical traditions (Annales, Marxist, feminist, postcolonial, subaltern, world-systems), their methodological commitments, their contributions and limitations, and the enduring debates about objectivity, narrative, and the nature of historical knowledge. Use when evaluating how different historians approach the same subject, understanding why historical interpretations change over time, or assessing the theoretical framework underlying a historical argument.

Applying motion study and time analysis to household work. Based directly on Lillian Gilbreth's *The Home-Maker and Her Job* and *Cheaper by the Dozen*, this skill covers the therblig-motion catalog, task decomposition, batch processing, parallelism, routine chart design, and the ergonomics of work surfaces. Use when diagnosing why a household is running out of time, designing a weekly routine, teaching task sharing to children, or reducing the friction of any repeated household task.

Diagnosis of why structural materials fail — ductile overload, brittle cleavage, fatigue, creep, stress-corrosion cracking, hydrogen embrittlement, and corrosion. Covers Griffith fracture mechanics, the ductile-to-brittle transition, the S-N and Paris fatigue frameworks, fractographic interpretation, and the J.E. Gordon view that strength, stiffness, and toughness are distinct properties that must be understood together to prevent collapse.

Proof writing and verification techniques for mathematical reasoning. Covers 13 proof strategies with canonical worked examples — direct, contrapositive, contradiction, cases, WLOG, vacuous/trivial, biconditional, counterexample, existence (constructive and non-constructive), uniqueness, induction (weak, strong, structural), pigeonhole/double-counting, and diagonal argument/invariants. Use when writing, verifying, or selecting proof strategies for any mathematical claim.

Provides monitoring and observability best practices covering the three pillars (logs, metrics, traces), OpenTelemetry instrumentation, Prometheus/Grafana dashboards, SLO-based alerting, and APM strategies. Use when setting up monitoring, observability, prometheus, grafana, opentelemetry, alerting, tracing, logging, metrics, dashboards, SLOs, or APM.

Provides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures. Use when designing agent systems, configuring MCP servers, setting up agent teams, or when user mentions 'MCP', 'A2A', 'agent orchestration', 'multi-agent', 'swarm', 'agent team', 'LangGraph', 'CrewAI', 'AutoGen'.

Provides Kubernetes resource management, Helm chart patterns, service mesh configuration, and autoscaling strategies. Covers HPA, VPA, KEDA, operators, security contexts, and namespace isolation. Use when user mentions 'kubernetes', 'k8s', 'helm', 'istio', 'linkerd', 'service mesh', 'HPA', 'VPA', 'KEDA', 'pod security', 'resource quotas', 'operators'.

Provides platform engineering best practices for Internal Developer Platforms (IDPs), golden paths, service catalogs, and developer experience. Use when building developer platforms, configuring Backstage, designing self-service workflows, or when user mentions 'platform engineering', 'backstage', 'golden path', 'IDP', 'developer portal', 'service catalog', 'DevEx', 'platform team', 'self-service'.

Interpretive methods for analyzing literary texts including fiction, poetry, drama, and creative nonfiction. Covers narrative elements (character, plot, setting, point of view, theme), literary devices (symbolism, imagery, irony, foreshadowing, allusion), critical lenses (formalist, reader-response, historical, feminist, postcolonial, psychoanalytic, Marxist), close reading of prose and poetry, intertextuality and influence, and the relationship between form and meaning. Use when interpreting literary texts, analyzing author craft, applying critical lenses, discussing theme and symbolism, or exploring how literary form creates meaning.

Summarizing and visualizing data through measures of center, spread, shape, and position. Covers mean, median, mode, range, IQR, variance, standard deviation, percentiles, z-scores, five-number summaries, and graphical displays (histograms, box plots, stem-and-leaf, dot plots, scatter plots). Emphasizes choosing the right summary for the data's shape and scale. Use when summarizing datasets, choosing visualizations, computing summary statistics, or interpreting distributions.

Modeling relationships between variables using regression. Covers simple linear regression, multiple regression, polynomial regression, logistic regression, model fitting (least squares, maximum likelihood), residual analysis, model diagnostics, R-squared, adjusted R-squared, multicollinearity, variable selection, and the Box-Jenkins dictum that all models are wrong but some are useful. Use when predicting outcomes, quantifying relationships, building predictive models, or diagnosing model fit.

Route user intent to GSD commands. Explicit /gsd: commands bypass routing -- read `.claude/commands/gsd/[command].md` directly.

>

OpenStack Horizon web dashboard skill. Use when deploying, customizing, or troubleshooting the OpenStack web UI. Covers panel customization, session management, multi-domain support, theme branding, TLS configuration, and common dashboard failure modes including login issues, missing panels, and static asset problems.

Mathematical verification for physical calculations: unit tracking algebra (exponent maps), PhysicalQuantity pattern for compound units, SI/Imperial mixed-unit handling, Buckingham pi theorem for dimensionless groups, and common engineering dimensionless numbers. Activates for unit verification, dimensional consistency checks, scaling analysis, and calculation validation across all infrastructure domains.

Water-based fluid system design: pipe sizing (Darcy-Weisbach, Hazen-Williams), flow rates, pressure drops, CDU selection for DTC cooling, pump curves, and ASHRAE TC 9.9 water class enforcement. Activates for cooling loop design, plumbing calculations, CDU selection, pump sizing, and hydraulic system validation.

>

Upload and process data into local Weaviate collections with support for single objects, batch uploads, and multi-modal content

Unified code intelligence — Skeleton Index (zero-dep, <4s) + AST knowledge graph (CodeGraph) + architecture diagrams (Mermaid) + smart context builder. Pre-indexes code structure so AI agents understand any codebase instantly. 95% token compression for onboarding. 30% fewer tokens for deep analysis.

Skill Chain Engine — compose skills into automated pipelines. One task triggers multi-skill workflows with progress tracking, auto-detection, and step management.

Pick up a workstream across sessions. Load context, find texture, align, then go. Use when jumping back into something that has history.

Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate. Use this when you want to execute the end-to-end ML pipeline or re-run it after data or code changes.

You are the **Builder** — John Carmack's philosophy applied to execution. You take a Council Plan and implement it task by task, following the dependency order, loading the relevant expert's reference

Helm 包管理

Systematic research engine with anti-hallucination safeguards and source quality tiering.

当需要把本仓库 pipelines/skills 下的所有 skills 安装到系统级（默认同时安装到 Codex: ~/.codex/skills 和 Claude Code: ~/.claude/skills），以便在任意项目/对话中可被发现与调用时使用。使用 MD5 哈希进行版本控制，仅安装有更新的 skills；支持强制覆盖安装、指定单一目标安装和远程安装模式（--remote --check/--auto）。

Analyze HubSpot pipeline momentum — deal velocity, stage conversions, win/loss patterns, and stall detection

>-

CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use when context reaches 80%, switching models, ending sessions, user says save, quicksave, handoff, transfer, continue later, /qs, /context, or needs session continuity.