{ "task": "T-mtb58zsc", "agent": "innovator-hunt (Hunter)", "round": "retrain v3 HUNT", "crawl_date": "2026-08-27", "fetched_at_utc": "2026-08-27T06:51:49Z", "method": "curl 直读 raw.githubusercontent.com 全文,字节数与 api.github.com git/trees/main 返回逐一核对一致;行号为文件内 1-based 行号", "notes": [ ".agents/skills/h3-prompt-writing/* 与 .claude/skills/h3-prompt-writing/* 为同字节副本(2177/15773/23553),本清单引用 .claude 路径", "platform.minimax.io / platform.minimaxi.com 本轮不可达(WebFetch 域校验被拒、curl 三次超时),开放平台 API schema 未核实" ], "sources": [ { "id": "s01", "title": "MiniMax-H3 官方技能总说明 SKILL.md", "url": "https://raw.githubusercontent.com/MiniMax-AI/MiniMax-H3/main/.claude/skills/h3-prompt-writing/SKILL.md", "bytes": 2177, "sha256_16": "a48f9db1231cebe6", "crawl_time": "2026-08-27T06:44:00Z", "quotes": [ { "line": 14, "text": "4. Preserve the exact field names, section order, labels, and timing notation from the selected guide." }, { "line": 27, "text": "Ref2VA rewrites use `subject_definitions`, `summary`, `retention_analysis`, `detailed_description`, `overall_soundscape`, and `non_diegetic_music` in that order. Reference labels stay consistent across all sections." }, { "line": 33, "text": "- Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language." } ], "used_for": ["需求(2) 读法A风险依据", "补充B 台词原语言保真"] }, { "id": "s02", "title": "官方基础模式规范 base-en.txt(全文 223 行到手)", "url": "https://raw.githubusercontent.com/MiniMax-AI/MiniMax-H3/main/.claude/skills/h3-prompt-writing/references/base-en.txt", "bytes": 15773, "sha256_16": "2cfebc096a6e0837", "crawl_time": "2026-08-27T06:45:30Z", "quotes": [ { "line": 54, "text": "`` is the actual first frame of the video at 0.00 seconds and belongs to `[Shot 1]`. The description should first establish the style, subjects, composition, and scene anchors in the image, then describe the next action. Character identity, clothing, colors, key objects, and spatial relationships should remain consistent." }, { "line": 92, "text": "For ordinary cuts, use `the camera cuts to`, `the shot cuts to`, `the shot transitions to`, `the shot changes to`, or `the shot switches to`. When explicitly requested by the user, cross-dissolve, fade, or wipe may also be used. A cut should introduce new information about the subject, space, state, viewpoint, or time." }, { "line": 127, "text": "Subjects who speak, sing, or produce an off-screen human voice use stable IDs such as `(S1)` and `(S2)`. When multiple already-numbered speakers speak or sing together, use a compound ID such as `(S1,S2)`. A speaker keeps the same ID across shots; characters who never vocalize receive no speaker ID." }, { "line": 129, "text": "When a speaker first appears, provide enough information from the visual and audio context to establish a stable identity, such as character type, age, gender, whether the person is on-screen, pitch, timbre, speaking rate, or accent. Place the speaker's identifying phrase, ID, action, and delivery outside ``. Inside ``, include only the language tag and the actual user-provided spoken content. Preserve every original word and punctuation mark verbatim; do not translate or rewrite them." }, { "line": 136, "text": "For voiceover, use the exact phrase `says in an off-screen voiceover`. Immediately after every voiceover `` block, state that the corresponding on-screen character's lips remain closed:" }, { "line": 139, "text": "The man (S1) says in an off-screen voiceover: [English] I still remember that road. while his lips remain completely closed." }, { "line": 172, "text": "With no reference image, construct the complete timeline directly from the text. You may add scene, character, action, and sound details that remain consistent with the user's intent." } ], "used_for": ["盲区① 双说话人编号", "盲区④ 画外音", "盲区⑥ 最接近的道具一致性条款", "补充A 原故事情节最接近条款", "§5.6 标点作用域·verbatim 一侧"] }, { "id": "s03", "title": "官方 Ref2VA 规范 ref-en.txt(全文 342 行到手)", "url": "https://raw.githubusercontent.com/MiniMax-AI/MiniMax-H3/main/.claude/skills/h3-prompt-writing/references/ref-en.txt", "bytes": 23553, "sha256_16": "1e574f356716ad55", "crawl_time": "2026-08-27T06:46:10Z", "quotes": [ { "line": 5, "text": "Write all six rewrite sections in English. Preserve the original language only for dialogue and lyrics inside `` and for text visibly present in the scene." }, { "line": 26, "text": "Full-reference rewrites use four types of labels to identify the source and role of referenced content:" }, { "line": 28, "text": "| `` | Visible content abstracted from reference assets that can be reused or modified in the target video |" }, { "line": 29, "text": "| `` | A reference image used as a concrete target frame or shot-planning anchor |" }, { "line": 30, "text": "| `