Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Hook JSON input/output API reference — what data hooks receive via stdin and what JSON they can return to control Claude Code behavior. Use when writing hook scripts, checking exit code behavior, buil…
Plan, split, and track multi-step work using Shrimp Task Manager MCP (or equivalent). Use for multi-file refactors, migrations, or any work that benefits from task tracking.
Compatibility alias for the canonical `workflow-rig` front door. Use when older prompts mention `agent-workloads` or when you need the legacy workload-planning guidance; for new work, load `workflow-r…
Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation.
Use when creating a new skill and publishing it to a GitHub repo for installation via npx skills add. Covers scaffold, spec compliance, skill-judge evaluation, commit, push, and install verification. …
Use when the user needs to choose, prioritize, or make a go/no-go decision among options.
Creates a new album with the correct directory structure and templates. Use IMMEDIATELY when the user says 'make a new album' or similar, before any discussion.
Persistent memory discipline for Engram contributors. Trigger: Decisions, bugfixes, discoveries, preferences, or session closure.
Hook recipes and working examples — plugin hooks, frontmatter hooks in skills/agents/commands, prompt-based LLM hooks, and complete code examples in Python and Node.js. Use when building hook scripts,…
Digital forensics, steganography, and packet analysis for CTF challenges and investigation.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (…
When the user wants to solve VRP with time windows (VRPTW), optimize routes with delivery time constraints, or handle appointment scheduling. Also use when the user mentions "VRPTW," "time window rout…
Core planning principles for Portfolio Buddy 2 development. Use when: planning any feature implementation, modification, or refactoring. Ensures code preservation, mobile/desktop optimization, and tho…
Use when the user asks for a roadmap, timeline, phased plan, or execution sequence.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This sk…
Process account maintenance requests across the full account lifecycle. Use when changing a client address or contact info and verifying identity, updating beneficiary designations after marriage divo…
Use when auditing docs vs code drift, syncing docs after changes, optimizing CLAUDE.md or SKILL.md for AI consumption, validating GLFM and Markdown, or summarizing files/URLs/images — routes each task…
PDF generation toolkit. Create invoices, reports, certificates, forms, charts, tables, barcodes, QR codes, Canvas/Platypus APIs, for professional document automation.
Execute DeFi operations on Starknet including token swaps via avnu aggregator, DCA recurring buys, STRK staking, and lending/borrowing. Supports gasless transactions.
Analyze and assimilate project-specific Claude configurations
Recover session state from memory-keeper after context loss.
Guides VibeCoder (non-technical users) through natural language development (legacy). Use when user mentions どうすればいい, 次は何, 使い方, 困った, help, what should I do. Do NOT load for: 技术人员的工作, 直接的实现指示, 审查.
The Chinese operation guide for the MindOS knowledge base is only used for Agent tasks within the MindOS knowledge base (mindRoot path). It is triggered only when the target of the operation is a file…
Write, review, or fix skills and AGENTS.md files. Use when creating a new skill, auditing an existing one, refactoring a bloated AGENTS.md, or reviewing whether content passes the authoring test. Do N…