全部能力

Full LLM lifecycle skill — strategy selection, PEFT/LoRA, evaluation, and deployment. Use when building, fine-tuning, or operating LLM systems.

Orchestrate the full one-person company workflow across all OPC skills. Use when Codex needs to start, continue, or review the complete 一人企业方法论流程, read prior…

Resolve human PR review comments on current PR. Fetches unanswered human comments, evaluates each piece of feedback, applies fixes, and replies to every…

Analyze project features against ICP (Ideal Customer Profile) needs to identify gaps and recommend roadmap priorities. Use this skill when asked to evaluate…

适用于大型任务的重流程编排——研究、规划、对抗性审查、分阶段实施、审计、交付。当用户提到“epic”时使用，……

Qualify leads using the BANT framework (Budget, Authority, Need, Timeline) with discovery questions and scoring criteria

Designated Publisher for aibtc.news: review signals, curate the front page, compile and inscribe the daily brief, manage treasury and payouts

Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications,…

Validate, commit, and push.

List, upload, download, and manage files on B2C Commerce instances via WebDAV. Use this skill whenever the user needs to upload files to IMPEX directories,…

Audit and improve CRM data quality by identifying missing fields, inconsistent values, duplicate records, and stale data

Analyze sentiment in text using ML models. Use when: analyzing customer reviews; processing NPS feedback; monitoring brand mentions; evaluating campaign…

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

opc-dashboard-review — an installable skill for AI agents, published by easychen/opc-methodology.

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural…

Review contracts against your organization's negotiation playbook, flagging deviations and generating redline suggestions. Use when reviewing vendor contracts,…

Create and refine OpenCode agents via guided Q&A. Use proactively for agent creation, performance improvement, or configuration design. Examples: - user: "Create an agent for code reviews" → ask about scope, permissions, tools, model preferences, generate AGENTS.md frontmatter - user: "My agent ignores context" → analyze description clarity, allowed-tools, permissions, suggest improvements - user: "Add a database expert agent" → gather requirements, set convex-database-expert in subagent_type, configure permissions - user: "Make my agent faster" → suggest smaller models, reduce allowed-tools, tighten permissions

Authors, reviews, installs, and debugs GitHub Agentic Workflows in repositories, including workflow markdown, frontmatter, gh aw compile and run flows, safe…

Complete guide for Light Protocol on Solana - includes ZK Compression for rent-free compressed tokens and PDAs using zero-knowledge proofs, and the Light Token…

Run automated Lighthouse audits for Core Web Vitals and SEO. Use when: checking page performance; auditing SEO technical issues; monitoring Core Web Vitals;…