productivity▌

Complete guide for provisioning, securing, and integrating Cloud Firestore into applications. \n \n Covers provisioning setup in Firebase projects and local environments using Firebase CLI \n Includes comprehensive security rules guidance for data protection and access control \n Provides SDK integration instructions for web applications using the modular SDK \n References index management, query optimization, and best practices documentation \n

Typed knowledge graph for structured agent memory, entity management, and cross-skill state sharing. \n \n Supports 15+ core entity types (Person, Project, Task, Event, Document, etc.) with typed properties, relations, and constraint validation \n Enables graph queries, traversals, and dependency tracking; model multi-step plans as sequences of validated graph transformations \n Stores data as append-only JSONL by default; schema-driven validation prevents invalid mutations and enforces cardinal

Configure Claude Code, Codex CLI, and Gemini CLI for reduced-approval Ralph automation while enforcing project boundaries and secret denylists. \n \n Provides two preset permission profiles: repo-scoped (default, safer) and sandbox (full bypass for disposable environments only) \n Implements dynamic safety checkpoints via platform-specific hooks that block Tier 1 dangerous operations (rm -rf, git reset --hard, .env access, sudo) at execution time \n Supports Claude Code, Codex CLI, and Gemini CL

Identify large Google Drive files consuming storage quota. \n \n Lists files sorted by size in descending order to quickly spot storage hogs \n Returns file metadata including ID, name, size, MIME type, and owners for informed deletion or archival decisions \n Requires the gws-drive skill to be loaded before execution \n

Map identified threats to appropriate security controls and mitigations for effective defense-in-depth planning. \n \n Provides control categorization by type (preventive, detective, corrective) and layer (network, application, data, endpoint, process), with templates for building threat-to-control mappings and calculating coverage gaps \n Includes a standard control library with 15+ pre-built controls covering authentication, encryption, logging, access control, and availability, each mapped to

Extract and save website content as markdown files for offline access and analysis. \n \n Supports configurable crawl depth (1-5 levels), breadth limits, and page caps to balance coverage against performance \n Includes path filtering via regex patterns to focus on specific sections and exclude irrelevant content \n Offers two modes: full-page extraction for data collection, or semantic chunking with natural language instructions for feeding results into LLM context \n Provides a companion Map A

Structured Architectural Decision Record generator with AI-optimized formatting and sequential file management. \n \n Generates standardized ADR documents with front matter, context, decision rationale, and consequences organized into positive and negative outcomes \n Requires four inputs (decision title, context, decision, alternatives, stakeholders) with validation to prompt for missing information before generation \n Uses coded bullet-point system (3-4 letter codes + 3-digit numbers) across

event (v1) \n \n 前置条件： 先阅读 ../lark-shared/SKILL.md 了解认证、权限处理和安全规则。 \n \n Shortcuts（推荐优先使用） \n Shortcut 是对常用操作的高级封装（ lark-cli event +<verb> [flags] ）。有 Shortcut 的操作优先使用。 \n \n \n \n Shortcut \n 说明 \n \n \n \n \n +subscribe \n Subscribe to Lark events via WebSocket long connection (read-only, NDJSON output); bot-only; supports compact agent-friendly format, regex routing, file output \n \n \n

Structured logging pattern using wide events for comprehensive request-level debugging and analytics. \n \n Consolidates all request context into a single JSON event per service, emitted at completion, rather than scattering log lines throughout handlers \n Emphasizes high cardinality fields (user IDs, request IDs) and high dimensionality (many fields per event) to enable flexible querying and correlation across services \n Requires business context in every event: subscription tier, cart value,

Search your coding memory for past work, sessions, and implementation details. \n \n Queries personal session memories, project/repo memories, or both in parallel using optional scope flags ( --user , --repo , --both ) \n Returns formatted results with timestamps and relevance scores to help recall previous decisions, implementations, and coding patterns \n Designed for retrieving context about past work when users ask about earlier sessions, how something was implemented, or what they worked on