Agents
Agents d’IA i automatització
trace
Yeachan-Heo
Show agent flow trace timeline and summary
cancel
Yeachan-Heo
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
learn-about-omx
Yeachan-Heo
Learn about your OMX usage patterns and get personalized recommendations
ecomode
Yeachan-Heo
Token-efficient model routing modifier
ralph
Yeachan-Heo
Self-referential loop until task completion with architect verification
analyze
Yeachan-Heo
"Run deep investigation of architecture, bugs, performance issues, or dependencies and return structured findings with file:line evidence. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs root cause analysis before making changes. Routes to architect agent or Codex MCP for thorough cross-file reasoning."
autopilot
Yeachan-Heo
Full autonomous execution from idea to working code
frontend-ui-ux
Yeachan-Heo
Designer-developer for UI/UX work
claude-agent-sdk
sammcj
Use when working with Anthropic Claude Agent SDK. Provides architecture guidance, implementation patterns, best practices, and common pitfalls.
design-intent-specialist
joaquimscosta
Creates accurate frontend implementations from visual references while maintaining design consistency. Use when user provides Figma URLs, screenshots, design images, requests visual implementation from reference, or asks to build UI matching a design. Automatically checks existing design intent patterns before implementation.
browser-extension-launch
davepoon
面向没有编程经验的用户，把想法做成可试用的浏览器插件，并完成检查、商店材料、审核提交和上线验证；也用于继续已有插件、排错和发布新版。用户说“帮我做个插件”“把插件上架”“继续我的插件”时使用。普通网站开发、仅查询插件知识不触发。
review-findings
davepoon
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. Delegates to the Forja (Dev) agent.
implement-feature
davepoon
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
work-pipeline
davepoon
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
code-health
davepoon
Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela (QA) agent.
feature-spec
davepoon
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
loop-me
tt-a1i
Grill me about specs for the workflows I want to build, within this workspace.
aws-strands-agents-agentcore
sammcj
Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.
announcement-analysis
belos-street
"公告与财报分析技能，快速解读公告、年报、季报内容，判断对股价影响，识别关键信息和投资价值。Invoke when user shares or asks to analyze company announcements, earnings reports, or financial statements."
asset-allocation-rebalancing
belos-street
"提供资产配置优化建议、再平衡时机判断、再平衡操作策略。当用户询问资产配置、投资组合再平衡、仓位管理时调用此技能。"
agent-orchestration-improve-agent
boisenoise
"Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration."
macro-sector-transmission
belos-street
"宏观—行业—个股传导研究框架，分析利率、汇率、财政、地产、出口、通胀等变化如何传导到行业和公司。Invoke when user asks about macro analysis, sector rotation, or how macro changes affect specific industries."
credit-analysis
belos-street
"系统化信用研究能力，覆盖主体信用、行业风险、财务健康度、现金流质量、评级对标、违约概率建模。Invoke when user asks for credit analysis, bond investment decisions, or credit risk assessment."
valuation-framework
belos-street
"估值与定价框架技能，帮助分析公司估值方法、当前估值水平、估值逻辑和市场定价原因，提供投资决策参考。Invoke when user asks about valuation, pricing logic, PE analysis, or how to value a company."