dososo/blcaptain-lingjian-video
Instructions file CodexOpenCode
AGENTS.md instructions for dososo/blcaptain-lingjian-video, a project described as: 一句话生成可逐关审核的发布级中文短视频：脚本·配音·画面·配乐·字幕·音效全自动 | One sentence → a publish-grade Chinese short video — script, voiceover, visuals, music, subtitles & SFX automated, auditable at every gate.
dososo/blcaptain-lingjian-video
Instructions file
A set of Claude Code instructions for the blcaptain-lingjian-video project. It tells the coding assistant where to start when reviewing the project.
dososo/blcaptain-lingjian-video
Skill Claude CodeCodex
A conversational workflow for making vertical short videos from text, links, or reference images. It moves through script, voice, and visuals with human approval at each stage, then creates a preview or publishing package.
dososo/blcaptain-lingjian-video
Skill Claude CodeCodex
A conversational workflow for making vertical short videos from text, links, or reference images. It moves through script, voice, and visuals with human approval at each stage, then creates a preview or publishing package.
Plugin Claude Code
Plugin marketplace listing 1 plugin: agent-loop-skill.
Plugin Claude Code
A workflow skill for long-running Codex, Claude Code, Cursor, and AI agent tasks with contracts, disk-backed state, role separation, verification traces, restarts, subjective scoring, and cleanup.
Cursor rule Cursor
Use for long-running, multi-step, verifiable, restartable AI agent tasks that need contracts, disk state, traces, role separation, subjective scoring, or cross-session continuity.
Instructions file CodexOpenCode
AGENTS.md instructions for dososo/agent-loop-skill, covering agent loop skill, core loop, contract first, disk state and role split.
Instructions file
Claude Code instructions for dososo/agent-loop-skill, covering agent loop skill, core loop, 1. write the loop, not just the prompt, 2. separate roles and 3. negotiate the contract first.
Skill Claude CodeCodex
Build and run long-running AI agent workflows for Codex, Claude Code, Cursor, and other coding agents with contracts, disk-backed state, role separation, verification traces, restart criteria, subjective scoring, and harness cleanup. Use when a user asks an agent to complete multi-step coding, product, research…
dososo/blcaptain-research-driven
Skill Claude CodeCodex
Improves research quality when accuracy matters; work depends on external facts such as documentation, APIs, pricing, licenses, standards, current events, research, or source code; a question is complex or multi-part; confidence is low; or sources conflict. Excludes casual chat, pure formatting, mechanical edits, and…