数据与 AI技能

Secure skill template with prompt injection defenses. Copy this template when creating new skills.

中文简介正在准备中。当前显示原文说明。

Use when refining a draft user prompt before sending it to a coding agent. Decomposes goal/context/constraints/acceptance/output-format, detects ambiguity and model-coupled framing, then emits a model-agnostic rewrite. Supports --analyze, --score, and --deep. NOT for prompts from scratch (mk:brainstorming), plans/reviews (mk:elicit), implementation plans (mk:plan-creator), or general codebase scouting (mk:scout).

中文简介正在准备中。当前显示原文说明。

JIRA time tracking via the jira-as wrapper: log work, list/update/delete worklogs, set estimates, generate reports, bulk-log. Triggers: 'log 2h on KEY', 'show worklog for KEY', 'time report for sprint', 'bulk-log 30m to JQL'. Worklog edit/delete loses data — agent confirms. NOT for sprint capacity (mk:jira-agile).

中文简介正在准备中。当前显示原文说明。

Retrieve up-to-date library, framework, and project documentation using scripts + MCP tools (Context7, Context Hub) with intelligent fallback. Use this skill whenever the user or agent needs documentation for any library, framework, API, SDK, or internal project spec. Triggers on "docs for [X]", "how does [library] work", "find documentation", "API reference for", "look up [feature] in [library]", "latest docs", "what's the API for", "find our [internal spec]", or any request that requires current, accurate documentation rather than relying on training data. Always prefer this skill over raw WebSearch for documentation retrieval — it returns structured, context-efficient results.

中文简介正在准备中。当前显示原文说明。

Use when transforming existing code into agent-consumable surfaces — CLI (npm-publishable), MCP server (stdio/SSE/Streamable HTTP), and a companion skill. Triggers on 'agentize', 'henshin', 'expose as MCP', 'wrap as CLI', 'publish to npm', 'make LLM-accessible', 'turn into agent tool', 'expose feature as tool'. Runs when the user has existing code and wants to ship it to agents. NOT for building new code from scratch (see mk:bootstrap); NOT for reviewing or verifying existing code (see mk:review).

中文简介正在准备中。当前显示原文说明。

Use when the user asks about website analytics, traffic, visitors, page views, referrers, conversions, goals, or mentions "fusionaly". Answers from a self-hosted Fusionaly instance through its MCP tools (or its SQL API), in plain English with numbers.

中文简介正在准备中。当前显示原文说明。

Use when user asks about website analytics, traffic, visitors, page views, referrers, or mentions "fusionaly". Queries Fusionaly analytics via SQL API.

中文简介正在准备中。当前显示原文说明。

Django Redis caching with django-cacheops. This skill should be used when implementing caching, adding cache invalidation, optimizing API performance, modifying models that affect cached data, or debugging cache-related issues in the Django backend.

中文简介正在准备中。当前显示原文说明。

Zod schema validation and React Hook Form integration for TypeScript frontends. This skill should be used when creating forms, defining API schemas, validating form data, implementing type-safe validation, using ZodResolver with React Hook Form, or migrating legacy forms to the Zod + React Hook Form pattern.

中文简介正在准备中。当前显示原文说明。

Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)

中文简介正在准备中。当前显示原文说明。

Apache Spark 4.0.2 best practices for PySpark and Scala distributed data processing

中文简介正在准备中。当前显示原文说明。

PostgreSQL performance optimization guidelines from Supabase. Apply when writing SQL, designing schemas, configuring RLS, or optimizing database performance.

中文简介正在准备中。当前显示原文说明。

Semble (MinishLab) MCP wrapper — semantic code search via embeddings (98% token reduction vs grep+read, NDCG@10=0.854)

中文简介正在准备中。当前显示原文说明。

Use the project wiki as RAG knowledge source — search wiki pages to answer codebase questions before exploring raw files

中文简介正在准备中。当前显示原文说明。

Load a skill profile to switch active plugin set. Use when user wants to focus on a specific workflow (web-app/data-eng/harness-dev/minimal) and reduce skill enumeration block size per

中文简介正在准备中。当前显示原文说明。

Redis best practices for caching, data structures, and in-memory data architecture

中文简介正在准备中。当前显示原文说明。

Neo4j best practices for Cypher query optimization, graph data modeling, indexing, and safe execution of LLM-generated Cypher

中文简介正在准备中。当前显示原文说明。

Data pipeline architecture patterns for ETL/ELT design, orchestration, and data quality frameworks

中文简介正在准备中。当前显示原文说明。

PostgreSQL best practices for database design, query optimization, and performance tuning

中文简介正在准备中。当前显示原文说明。

Prevent session idle during background agent work via SubagentStop prompt hook auto-continuation

中文简介正在准备中。当前显示原文说明。

Execute Gemini CLI prompts and return results

中文简介正在准备中。当前显示原文说明。

Routes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.

中文简介正在准备中。当前显示原文说明。

Parameterized prompt templates using Jinja2 patterns for reusable, dynamic agent prompts

中文简介正在准备中。当前显示原文说明。

Entry point for every browser task in ego (ego lite, ego-browser) — load this instead of the `ego-browser` skill: it starts by running `ego-browser skill`, the guide that skill points to. Multi-step clicking (fill known values into a form, set filters, open a row/card/menu by name, reach a page via nav or site search) runs on Jev, one ~0.4 s typed decision per step instead of an LLM turn. Reading, extraction, screenshots, login and free text stay plain ego calls.

中文简介正在准备中。当前显示原文说明。