Recently added agent tools.

|

Optimizes web application performance through code splitting, lazy loading, caching strategies, and Core Web Vitals monitoring. Use when improving page load times, implementing service workers, or reducing bundle sizes.

|

当用户明确提到某个具体股票或上市公司时——如'保隆科技最近怎么了''帮我快速看一下600519''茅台最近有什么重要信息'。整合行情、公告、新闻和研报。行业整体问题用 industry-brief，研报专项用 research-digest，公告专项用 announcement-brief。

Reconcile this session's code delta back into the Living Blueprint and per-folder intent layer so they stay an accurate snapshot of the codebase. Mostly descriptive (what the code now is), not rules. Pure producer — edits files only, never commits or opens a PR.

변경된 파일을 기능별로 그룹화하여 커밋 생성

Apply UX psychology principles to frontend design. Use when designing UI components, improving user experience, increasing conversion, or making design decisions. Covers 43 psychological concepts including cognitive biases, behavioral patterns, visual design principles, and engagement techniques. Triggers on requests like "design a pricing page", "improve signup flow", "increase engagement", or "apply psychology to UI".

Drive a Genie change test-first through the genie MCP tools, working entirely from the live image (no files). Use when adding behavior or fixing a bug in the image — anything where a test should lead.

Use when implementing Apollo caching strategies including cache policies, optimistic UI, cache updates, and normalization.

Nslookup reference tool. Use when working with nslookup in network contexts.

Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.

Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.

Workflow for developing web-based visual content and verifying the rendered output using Browser and Vision AI tools.

firecrawl-ci-integration is a tool to set up and configure automated CI/CD pipelines and testing integration with FireCrawl using GitHub Actions.

sandbox-sdk enables building secure, isolated code execution environments for AI code interpretation, CI/CD, and interactive development workflows.

Protocol-level two-agent paper writing workflow. Use when the user wants Codex to plan and review from global context while DeepSeek writes or revises the manuscript through the global deepseek-agent skill, with muxing-style-review used for explicit prose style checks.

An AI tool to manage and update Things 3 todos, projects, and tags on macOS via CLI for improved productivity and task organization.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Agent skill for load-balancer - invoke with $agent-load-balancer

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give

A structured guide tool for conducting user interviews using story-based questions and bias mitigation to uncover customer needs and opportunities.

An AI mentor designed to teach and support beginners in learning the Turkish language through interactive lessons and practice.

Design data-quality monitoring for production pipelines and stores — checks across the six dimensions (freshness, completeness/volume, uniqueness, validity, consistency/referential integrity, distribution drift), placed at the right pipeline stage (ingest, transform, serving), each with severity, an owner, and a failure action (block, quarantine to a reviewable location, or alert-and-pass — never silent auto-fix), plus per-dataset quality SLAs and incident routing. Produces the monitor spec and

125+ agent skills for Longbridge Securities — real-time quotes, charts, fundamentals, portfolio analysis, options, and more for HK/US/A-share/SG markets. Trilingual: Simplified Chinese, Traditional Chinese, English.

Aplica el patrón ultrathink de revisión Nivel 1 a un ADR del corpus de Runcriticon. Detecta gaps en bloques A-G, propone sub-decisiones con anchors, lanza tandas de preguntas con AskUserQuestion, y termina con PRs encadenadas de revisión + aceptación. Úsala cuando se proponga reabrir un ADR aceptado, cuando entre un ADR nuevo, o cuando el equipo quiera auditar un ADR contra el patrón consolidado.

Audit codebases for cross-industry regulatory compliance across SOX, GDPR, HIPAA, PCI-DSS, CCPA/CPRA, FedRAMP, FISMA, COPPA, and FERPA. Reviews audit trail completeness (who/what/when/where/why with tamper-evident storage), data retention policies and right-to-erasure workflows, RBAC/ABAC access control with least-privilege enforcement, privileged access management and JIT elevation, change management controls (branch protection, deployment gates, emergency change process), DSAR and ROPA reporti

>

Python resource management with context managers, cleanup patterns, and streaming. Use when managing connections, file handles, implementing cleanup logic, or building streaming responses with accumulated state.

|

An AI agent that automates playing Pokemon games via headless emulation and RAM state analysis.

Scaffold, implement, test, and deploy a new Poe tile from a prompt.

Use when implementing search functionality with production-grade patterns and safeguards.

>

AI agent for tech and internet domain search agent tasks.

Upgrade rough ideas, partial plans, feature concepts, product brainstorms, or implementation sketches into plans that are ready to execute or convert into formal specs. Use whenever the user wants to refine, stress-test, scope, harden, sequence, clarify, or prepare work for implementation, PRDs, spec-driven development, or agent/developer handoff.

Use when aligning long FASTQ reads to a reference genome with Subread's long-read aligner, optionally in RNA-seq mode.

This skill should be used when the user asks to "analyze a USD file", "load a USD file", "inspect USD", "headless USD", "prim info", "search prims", "mesh info", "scene summary", "bounding box", or needs to work with USD files without a running Isaac Sim instance.

Expert in Swift and SwiftUI development for iOS, macOS, and Apple platforms

|

[omh] Hermes GitHub event operations workflow: route PR, issue, CI, and review webhook events into triage, review, or fix handoff cards. Use when the user says: github-event-ops, github event ops, github ops, github triage, github pr, github review, github action, github actions.

Search the bioRxiv preprint server and retrieve paper metadata or download PDFs via its API. Use when finding life sciences preprints by keywords, authors, DOI, date ranges, or categories, or when conducting a biology literature review of not-yet-peer-reviewed work. Part of the AlterLab Academic Skills suite.

>

Facilitate game brainstorming sessions with game-specific techniques. Use when the user says "brainstorm game" or "game ideas"

Create Beamer-style academic PPTX presentations using python-pptx. Produces publication-quality .pptx files with navy-blue Metropolis theme (16:9, frame title bars, progress bar) for conference talks, job market presentations, and seminar slides. Called by /present command.

Show PR diff and local changes

Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.

|

Delete Oracle Cloud Always Free resources safely with the oci CLI — terminate the instance and unwind NSG, subnet, route table, internet gateway and VCN in reverse order. Use for "tear it down", "destroy everything", "clean up my free tier", `oci compute instance terminate`, `oci network vcn delete`, Conflict or "has dependencies" errors, orphaned boot volumes, stopping charges, and verifying nothing billable survived.

Review code changes since a commit, classify correctness and maintainability findings, apply only high-confidence safe fixes when enabled, and report remaining issues. Run proactively with --fix after non-trivial implementation, before fresh verification, change explanation, or branch completion. Also use for explicit polish, changed-code review, commit-range review, or pre-PR quality requests.

Investigate a Linux workstation crash or unexpected reboot. Use when the user asks why their machine crashed, rebooted without warning, or wants to understand what happened after coming back to a crashed system.