LLM 與 Agent
6763 skills in 數據與 AI > LLM 與 Agent
wp-performance
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
codex
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
gemini-manager
This skill should be used when the user wants Claude Code to act purely as a manager/architect while Gemini CLI does all the coding work. Claude Code drives Gemini like an intern - issuing tasks, reviewing output, requesting fixes - but never writes code itself. Use when user says "manage gemini", "architect mode", "drive gemini", or wants to delegate all implementation to Gemini.
wp-plugin-development
Use when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security (nonces/capabilities/sanitization/escaping), and release packaging.
octave-literacy
Fundamental reading and writing capability for the OCTAVE format. Inject this to give an agent basic structural competence without the overhead of full architectural specifications. Triggers on: octave format, write octave, octave syntax, structured output.
Python Rope Refactor
Rope-first workflow for ANY mechanical Python rename/move (functions/methods/classes/variables/modules/packages), updating imports/references via scripts/rope_refactor.py; use even for small renames; only fallback if rope fails/dynamic imports.
nuxt-content
Use when working with Nuxt Content v3 - provides collections (local/remote/API sources), queryCollection API, MDC rendering, database configuration, NuxtStudio integration, hooks, i18n patterns, and LLMs integration
linting-codebase
Parallel lint fixing pattern - runs lint checks, groups issues into independentstreams, and dispatches AI agents to fix all issues until the codebase is clean.
testing-agents-with-subagents
Agent testing methodology - run agents with test inputs, observe outputs,iterate until outputs are accurate and well-structured.
using-ops-team
5 specialist operations agents for platform engineering, incident response,cloud cost optimization, infrastructure architecture, and security operations.Dispatch when you need production operations expertise.
using-ring
Mandatory orchestrator protocol - establishes ORCHESTRATOR principle (dispatch agents,don't operate directly) and skill discovery workflow for every conversation.
rp-explorer
Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.
pre-dev-research
Gate 0 research phase for pre-dev workflow. Dispatches 3 parallel research agentsto gather codebase patterns, external best practices, and framework documentationBEFORE creating PRD/TRD. Outputs research.md with file:line references.
using-dev-team
7 specialist developer agents for backend (Go/TypeScript), DevOps, frontend,design, QA, and SRE. Dispatch when you need deep technology expertise.
self-learning-skills
Memory sidecar for agent work: recall before tasks, record learnings after tasks, review recommendations, optional backport bundles.
dev-testing
Gate 3 of development cycle - ensures unit test coverage meets threshold (85%+)for all acceptance criteria using TDD methodology.
subagent-driven-development
Autonomous plan execution - fresh subagent per task with automated code reviewbetween tasks. No human-in-loop, high throughput with quality gates.
dev-implementation
Gate 0 of the development cycle. Executes code implementation using the appropriatespecialized agent based on task content and project language. Handles TDD workflowwith RED-GREEN phases. Follows project standards defined in docs/PROJECT_RULES.md.
aws-s3-management
Manage S3 buckets with versioning, encryption, access control, lifecycle policies, and replication. Use for object storage, static sites, and data lakes.
android-kotlin-development
Develop native Android apps with Kotlin. Covers MVVM with Jetpack, Compose for modern UI, Retrofit for API calls, Room for local storage, and navigation architecture.