productivity▌

Research a prospect, then draft personalized outreach based on findings. \n \n Researches prospects first using web search by default, enhanced with optional enrichment tools (verified contact info, background) and CRM data (prior relationship context) \n Generates email drafts with personalized opening, relevant hook, and clear CTA, plus LinkedIn alternatives when email unavailable \n Supports three delivery modes: auto-create email draft if email connector enabled, output text for manual copy,

CLI for bootstrapping wordspace projects with reusable .prose workflows from GitHub. \n \n Three core commands: init to set up a new project with interactive workflow selection, search to filter available workflows, and add to download specific workflows by name \n Interactive workflow picker during init supports flexible selection syntax (individual numbers, ranges, or \"all\"/\"none\") \n Automatically creates project structure with .claude/settings.local.json for Claude permissions, workflows

Persistent, searchable memory bank for AI agents with automatic project documentation sync. \n \n Provides four core MCP tools: memory_search for querying by text/type/tags, memory_write for recording knowledge and decisions, memory_read for retrieving specific entries, and memory_stats for usage analytics \n Organizes memories by type (architecture, patterns, decisions) and supports custom tagging for flexible retrieval and organization \n Runs as an MCP server that syncs with your project work

Annotation-driven caching abstraction for Spring Boot service methods with multi-provider support. \n \n Supports multiple cache providers (ConcurrentMap, Caffeine, Redis, Ehcache, JCache) via pluggable CacheManager beans without changing business code \n Provides @Cacheable , @CachePut , @CacheEvict , and @Caching annotations with SpEL-based key generation, conditional caching, and synchronization control \n Includes configuration patterns for TTL, capacity limits, and scheduled eviction; integ

Help track compliance requirements, prepare for audits, and maintain regulatory readiness.

Full-text search across past Claude Code and Codex sessions with BM25 ranking and flexible query syntax. \n \n Supports keyword search, exact phrases, boolean operators (AND, OR, NOT), and prefix matching across all indexed conversations \n Filters results by project path, recency (days), and source (Claude Code or Codex sessions) \n Includes session resumption commands and a transcript reader to view raw conversation files \n Automatically indexes user and assistant messages from ~/.claude/proj

Automatically fetches current documentation from Context7 when users ask about libraries, frameworks, or code examples. \n \n Proactively triggers on implementation queries, configuration requests, documentation lookups, library mentions, and code generation prompts in both English and Chinese \n Extracts library name and version from user queries, searches Context7 API, and selects the best match by name, trust score, and version specificity \n Fetches relevant documentation snippets and integr

Use this skill when adding or changing framework feature flags in Next.js internals.

Classical machine learning with scikit-learn for classification, regression, clustering, and preprocessing. \n \n Covers supervised learning (linear models, trees, SVMs, ensembles, neural networks), unsupervised learning (K-Means, DBSCAN, PCA, t-SNE), and model evaluation with cross-validation and hyperparameter tuning \n Includes preprocessing transformers for scaling, encoding categorical variables, imputing missing values, and feature engineering \n Provides Pipeline and ColumnTransformer for

Debugging tools for Turso database using bytecode comparison, logging, and deterministic simulation. \n \n Bytecode comparison workflow identifies whether behavior differences stem from code generation bugs or VM/storage layer issues by comparing SQLite and Turso EXPLAIN output \n Logging via RUST_LOG environment variable captures detailed traces from turso_core and simulator components during test runs \n ThreadSanitizer stress tests detect threading issues across configurable thread counts and