Ask Codex what was said at 12:40, and what the slide on screen actually read. Real Video for Codex turns any video into keyframes, a transcript and on-screen text with timecodes, processing on your machine; Codex answers with timestamps. Needs the Codex CLI installed and signed in. Codex sends that text and those frames to OpenAI and uses your ChatGPT quota. Ships with the skill and a doctor self-check. Already own crv Pro? Both arrive free in the next Pro version.
Create a reversible, project-local Codex copy of Claude Code agents, skills, commands, compatible hooks, MCP, and persistent GPT routing—while keeping Claude untouched.
Tell me what your coding agent keeps getting wrong, and I write the CLAUDE.md or AGENTS.md that would have stopped it. Not a template filled in from your README - a file built from the landmines only you know: the command that needs an undocumented env var, the directory nobody should hand-edit, the decision that looks wrong and is deliberate. A complete file in the first reply, gaps marked TODO, three questions at most. Free for three requests.
把用户提供的小说原文 / 现成剧本，经**六个角色技能框架接力**转化为「分镜图提示词 + 视频脚本 + AI 视频提示词」。三个**稳定输出机制**：每个角色有独立技能框架（完整工作方法）；环节间有固定数据契约；质量门前置到每个角色并加终检。
Generate, audit, co-author, and maintain software documentation under a style your agent cannot drift from. Version 3.0.0 adds controlled language (STE-derived), a distilled house style enforced by mechanical gates (vale, markdownlint, cspell), canonical vocabulary that steers agents, OKF v0.2 knowledge bundles with a working attester, and the 2026 spec-driven development landscape with 11 tool-neutral templates. Works across software, hardware, firmware, and embedded projects in any runtime.
Runs a five-axis consistency check on every turn — verifying character voice, world rules, timeline, dormant lore, and new contradictions — then proactively surfaces unused story elements, so your canon survives from chapter one to the final scene.
Socratic learning plus a local markdown wiki you place. First run asks where and how to tend it; later sessions teach 50:50 and write notes in your words.
Turn open-ended survey responses into a reviewable codebook, coded CSV, theme summary, quote table, and insight deck outline. 将开放式问卷回答整理成可人工复核的 codebook、编码表、主题摘要、引用表和洞察汇报大纲。No fabrication, no PII leakage, no statistical overclaiming.