aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Analyzes sales call transcripts using the POWERFUL framework to extract insights and action items. Use this skill when reviewing call recordings, coaching reps, qualifying opportunities, or extracting deal intelligence from conversations.
Creates automated email sequences for every stage of the customer journey including welcome, nurture, conversion, and launch flows. This skill should be used when building automated email flows, launching products, improving email-driven conversions, or onboarding new customers.
Discovers differentiated market positioning using 8 proven frameworks. This skill should be used when launching a new product or service, entering competitive markets, refreshing stale positioning, or when current messaging sounds like every other competitor.
Session lifecycle management. Parent skill for session-related skills: learning (pattern extraction) and compact (context compression).
Creates comprehensive prospect profiles and knowledge capsules for sales preparation. Use this skill when researching new prospects, preparing for calls, onboarding to new accounts, or updating prospect intelligence.
Build Solana programs with Anchor framework or native Rust. Use when developing Solana smart contracts, implementing token operations, testing programs, deploying to networks, or working with Solana development. Covers both high-level Anchor framework (recommended) and low-level native Rust for advanced use cases.
Decompose complex tasks into parallel sub-agents. Use for multi-step operations, batch processing, or when user mentions "parallel", "agents", "orchestrate", "subtasks", or "concurrent". Supports simulated parallel execution and real Claude CLI sub-agent launching.
Create and manage scheduled tasks that execute Claude CLI at specified times. Use when user mentions "定时", "scheduled", "timer", "cron", "每天", "每小时", "定期", "remind", "提醒", or wants to run automated tasks periodically. Supports cron expressions, interval-based, and one-time scheduling.
Content planning framework using the 6 Circles Method for identifying high-value topics without paid SEO tools. This skill should be used when building content strategy from scratch, planning quarterly content calendars, finding content gaps, or when unsure what to write about next.
Backend development patterns for services, error handling, logging, caching. Use when building backend services, APIs, or microservices.
Build with ZK Compression on Solana using Light Protocol. Use when creating compressed tokens, compressed PDAs, or integrating ZK compression into Solana programs. Covers compressed account model, state trees, validity proofs, and client integration with Helius/Photon RPC.
DevOps patterns: containerization, CI/CD, deployment strategies, monitoring. Use when containerizing apps, setting up pipelines, or deploying services.
Rephrase or completely rewrite content matching user's preferred tone, voice, and style.
Orchestrate parallel phase execution from plan files. Parses symphony-phases blocks, builds dependency DAG, and executes phases concurrently using Task tool. Supports artifact propagation between phases and automatic dependency resolution using Kahn's algorithm.
Use when user wants to find past records or notes on a topic. Triggered when intention involves remembering, locating, or querying knowledge. Searches vault by content, tags, and frontmatter.
Work with labeled multidimensional arrays for scientific data analysis using Xarray. Use when handling climate data, satellite imagery, oceanographic data, or any multidimensional datasets with coordinates and metadata. Ideal for NetCDF/HDF5 files, time series analysis, and large datasets requiring lazy loading with Dask.
Use when user wants to structure or organize knowledge on a topic. Triggered when intention involves creating overview, index, or knowledge map. Creates or updates Map of Content in 05_MOC.
Create and publish distributable scientific Python packages following Scientific Python community best practices with pyproject.toml, src layout, and Hatchling. Use when building Python libraries, publishing to PyPI, structuring research software, creating command-line tools, or preparing packages for distribution. Ideal for package metadata configuration, dependency management, and automated publishing workflows.