productivity▌

Dependency injection configuration and service management for Angular v20+ using inject() and providers. \n \n Use inject() for cleaner dependency declaration in components and services; configure providers at root, component, or route level to control singleton vs instance-per-component behavior \n Create and inject custom tokens for configuration objects, third-party values, and multi-provider collections; supports useValue, useClass, useFactory, and useExisting provider strategies \n Manage i

Design and audit internal link structures using hub-and-spoke topology, PageRank flow, and anchor text optimization. \n \n Supports five architecture models (hub-and-spoke, silo, flat, pyramid, mesh) with guidance on which fits different site sizes and content types \n Includes orphan page detection, link depth analysis, and anchor text diversity assessment to identify ranking barriers \n Provides concrete link injection plans with source pages, target pages, anchor text suggestions, and priorit

Audit and fix HTML accessibility issues across ARIA labels, keyboard navigation, focus management, and WCAG compliance. \n \n Covers nine rule categories prioritized by impact: accessible names, keyboard access, focus management, semantics, forms and errors, announcements, contrast, media, and tool boundaries \n Provides targeted fixes for common patterns like icon-only buttons, form error linking, and focus trapping in modals \n Includes quick reference for when to apply (interactive controls,

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

Automatically share Google Drive files with all attendees of a Calendar event. \n \n Requires gws-calendar and gws-drive skills as dependencies \n Retrieves event attendee list from Google Calendar, then grants each attendee reader access to specified Drive files \n Includes verification step to confirm sharing permissions were applied successfully \n

$1e

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md，其中包含认证、权限处理

Analyze codebases and map task-relevant files before implementing changes. \n \n Automatically searches for related files, dependencies, tests, and similar code patterns to establish full context \n Generates structured markdown output with files to modify, dependency relationships, test coverage, and reference patterns \n Includes risk assessment checklist for breaking changes, migrations, and configuration updates \n Designed as a pre-implementation step to prevent missed dependencies and unin

Create GitHub Issues automatically from implementation plan phases. \n \n Analyzes implementation plan files to identify phases and generates one issue per phase \n Uses feature_request.yml or chore_request.yml templates, with fallback to default issue format \n Checks for existing issues before creation to avoid duplicates, and updates existing issues when needed \n Includes phase details, requirements, and context in issue descriptions with appropriate labels \n

Prioritized keyword research with intent mapping, difficulty scoring, and cluster seeding for SEO strategy. \n \n Builds a three-tier keyword universe (head, body, long-tail) with monthly volume, difficulty scores (0-100), and intent classification across informational, commercial, transactional, and navigational categories \n Includes cannibalization screening to prevent targeting keywords your site already ranks for, plus low-hanging fruit detection for quick wins in positions 11-20 \n Scores