数据与 AI技能

Extract data from web pages using the scrapling Python library — select the appropriate fetcher tier (HTTP, stealth Chromium, or full browser automation) based on target site defenses, configure headless browsing, and extract structured data with CSS selectors. Use when WebFetch is insufficient for JS-rendered pages, anti-bot-protected sites, or structured multi-element extraction requiring DOM traversal.

中文简介正在准备中。当前显示原文说明。

Implement pharmaceutical serialisation and track-and-trace systems compliant with EU FMD, US DSCSA, and other global regulations. Covers unique identifier generation, aggregation hierarchy, EPCIS data exchange, and verification endpoint integration. Use when implementing serialisation for a new product launch, integrating with the EMVS/NMVS, designing DSCSA-compliant transaction exchange, building an EPCIS event repository, or extending serialisation to additional markets (China, Brazil, Russia).

中文简介正在准备中。当前显示原文说明。

Systematically interpret Raman spectra to identify molecular vibrations, assess polarizability-driven selection rules, compare with complementary IR data, and evaluate depolarization ratios for symmetry assignment. Covers Raman-active mode identification, fluorescence interference mitigation, and reference spectrum matching.

中文简介正在准备中。当前显示原文说明。

Set up systematic data labeling workflows using Label Studio or similar tools. Implement quality controls, measure inter-annotator agreement, manage labeler teams, and integrate labeled data into ML training pipelines. Use when starting a supervised ML project that requires labeled training data, when model performance is limited by insufficient labeled examples, when labeling text, images, audio, or video, or when implementing active learning to prioritize the most valuable examples.

中文简介正在准备中。当前显示原文说明。

Generate a project status report by reading existing artifacts (charter, backlog, sprint plan, WBS), calculating metrics, identifying blockers, and summarizing progress with RAG indicators for schedule, scope, budget, and quality. Use at the end of a sprint or reporting period, when stakeholders request a health update, before steering committee or governance meetings, or when a new blocker or risk materializes mid-project.

中文简介正在准备中。当前显示原文说明。

Establish Service Level Objectives (SLO), Service Level Indicators (SLI), and Service Level Agreements (SLA) with error budget tracking, burn rate alerts, and automated reporting using Prometheus and tools like Sloth or Pyrra. Use when defining reliability targets for customer-facing services, balancing feature velocity against system reliability through error budgets, migrating from arbitrary uptime goals to data-driven metrics, or implementing Site Reliability Engineering practices.

中文简介正在准备中。当前显示原文说明。

Decommission a validated computerized system at end-of-life. Covers data retention assessment by regulation, data migration validation (mapping, transformation, reconciliation), archival strategy, access revocation, documentation archival, and stakeholder notification. Use when a validated system is being replaced, reaching end-of-life without replacement, vendor support is discontinued, multiple systems are consolidating, or regulatory changes render a system obsolete.

中文简介正在准备中。当前显示原文说明。

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

中文简介正在准备中。当前显示原文说明。

Conduct a project or sprint retrospective by gathering data from status reports and velocity metrics, structuring what went well and what needs improvement, and generating actionable improvement items with owners and due dates. Use at the end of a sprint, after a project phase or milestone, following a significant incident or success, at a quarterly review of ongoing processes, or before starting a similar project to capture lessons learned.

中文简介正在准备中。当前显示原文说明。

Add an external probabilistic classifier to a decision path without letting it take the path over. Covers finding the externally-graded rows you are already logging, measuring the confidence separation between the overrides it got right and the ones it got wrong, choosing an operating point your data licenses, failing open at the call site, and proving the whole arrangement offline with no API key. Applies to any service returning a score you can order — TypeSafe AI's System One models (Jev) are the worked example. Most of the method transfers to a local model or a second heuristic, with the parts that do not called out where they arise. Use when a rule-based path is wrong often enough to hurt, when someone proposes replacing a heuristic with a model, when a confidence threshold needs a defensible value, or when an oracle already in production has never been graded.

中文简介正在准备中。当前显示原文说明。

Set up a Blender scene programmatically via Python (bpy) with objects, materials, lighting, camera, and environment configuration. Use when creating reproducible 3D visualization scenes, automating product or architectural rendering setup, generating multiple scene variations programmatically, building template scenes for batch rendering workflows, or integrating 3D visualization into data pipelines.

中文简介正在准备中。当前显示原文说明。

Add PUT workflow annotations to source files using the correct language-specific comment prefix. Covers annotation syntax, skeleton generation via put_generate(), multiline annotations, .internal variables, and validation. Supports 30+ languages with automatic comment prefix detection. Use after analyzing a codebase and having an annotation plan, when adding workflow documentation to new or existing source files, or when documenting data pipelines, ETL processes, or multi-step computations.

中文简介正在准备中。当前显示原文说明。

Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature views with transformations, and implement point-in-time correct joins for ML pipelines. Use when managing features for multiple ML models, ensuring training-serving consistency, serving low-latency features for real-time inference, reusing feature definitions across projects, or building a feature catalog for discovery and governance.

中文简介正在准备中。当前显示原文说明。

Defines the structure and implementation of service classes, enforcing the use of interfaces, ServiceImpl classes, DTOs for data transfer, and transactional management.

中文简介正在准备中。当前显示原文说明。

Comprehensive scientific research toolkit with 139 specialized skills for biology, chemistry, medicine, data science, and computational research. Transforms Claude into an AI research assistant with access to scientific databases, analysis tools, and domain-specific workflows.

中文简介正在准备中。当前显示原文说明。

Creates JSON Schema validation files for skills, agents, hooks, workflows, and data structures. Ensures type safety and input validation across the framework.

中文简介正在准备中。当前显示原文说明。

Focuses on pandas-specific rules for data manipulation, including method chaining, data selection using loc/iloc, and groupby operations.

中文简介正在准备中。当前显示原文说明。

Medusa v2 rules and best practices for modular commerce architecture, Workflow SDK, data models, services, and admin customizations.

中文简介正在准备中。当前显示原文说明。

Use when you need to auto-log all tool interactions into a self-organizing vector DB with instant recall. Intercepts interactions, extracts key information, generates embeddings, stores in LanceDB, auto-categorizes, and builds a retrieval index. Inspired by OpenClaw SQLite LCM + summary DAG pattern.

中文简介正在准备中。当前显示原文说明。

Autonomous fixed-budget ML experiment loop — setup, iterative hypothesis testing, git-based keep/discard tracking, and indefinite autonomous execution. Implements the karpathy/autoresearch protocol.

中文简介正在准备中。当前显示原文说明。

Specific optimization strategies for Python scripts working with larger-than-memory datasets via Dask.

中文简介正在准备中。当前显示原文说明。

Orchestrate multi-LLM parallel debate and synthesis. Dispatches prompts to available omega CLI wrappers in parallel, collects independent responses, runs anonymized peer review ranking, and synthesizes via a chairman model. Supports collaboration templates, idle watchdog, inter-agent messaging, worktree isolation, and multi-turn sessions. No server required.

中文简介正在准备中。当前显示原文说明。

Independent LLM judge evaluates task completion separately from the executing agent, catching false success claims by reviewing task goal, actions taken, final state, and evidence. Produces PASS/FAIL with confidence score and reasoning.

中文简介正在准备中。当前显示原文说明。

Transforms vague UI/feature requests into structured, optimized prompts with design system awareness. Use when generating prompts for UI implementation, feature specification, or design-to-code translation. Triggers on tasks requiring prompt refinement, UI specification, or design system integration.

中文简介正在准备中。当前显示原文说明。