Loading...
Loading...
Found 1,678 Skills
Code file line limit specification: A single code file must have ≤ 300 lines. This is a mandatory restriction with no exceptions.
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
Single Responsibility Principle, ensuring that code files, functions, and modules have clear and single responsibilities. Applicable to all code files.
Open standards and governance rules for Agent Skills. It is used for creation, modification, refactoring, migration, audit and maintenance of skills, and provides platform-independent structural standards, frontmatter specifications, progressive disclosure and quality gates.
Documentation-driven development specification that requires Agent to consult official documentation and examples before generating code or fixing bugs, including API verification processes, search strategies and MCP invocation rules. It is applicable to scenarios such as accessing third-party libraries, troubleshooting API errors, and version changes.
Thinking guidance mechanism that requires Agent to raise guiding questions before giving answers, helping users think actively and avoid the degradation of cognitive abilities. It is applicable to interaction scenarios such as user questioning, solution consultation, learning communication, etc.
This skill should be used when analyzing recent market-moving news events and their impact on equity markets and commodities. Use this skill when the user requests analysis of major financial news from the past 10 days, wants to understand market reactions to monetary policy decisions (FOMC, ECB, BOJ), needs assessment of geopolitical events' impact on commodities, or requires comprehensive review of earnings announcements from mega-cap stocks. The skill automatically collects news using WebSearch/WebFetch tools and produces impact-ranked analysis reports. All analysis thinking and output are conducted in English.
Provides usage instructions and best practices for the skills_sync CLI tool. Use this to understand how to manage, sync, and configure AI agent skills based on the user's config file.
Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.
The Agent Tool Contract — 5 principles for designing tools agents call reliably: predictable signature, rich errors, token-efficient output, idempotency, graceful degradation. Includes anti-pattern table with 8 common mistakes.
Trading personality and arena behavior for pump.fun token trading. Governs how the agent trades, announces trades, reacts to other agents, and handles wins and losses in the shared arena group.
Use when an agent is asked to define, review, or write acceptance criteria for a request or plan. Derives acceptance criteria from the current request context, confirms them with the user, and writes them into the plan file or a standalone acceptance_criteria.md file.